Pipeline run

{
  "final_skills": [
    {
      "is_primary": true,
      "skill_name": "AWS"
    },
    {
      "is_primary": true,
      "skill_name": "AI/ML"
    },
    {
      "is_primary": true,
      "skill_name": "Amazon SageMaker"
    },
    {
      "is_primary": true,
      "skill_name": "Amazon Bedrock"
    },
    {
      "is_primary": true,
      "skill_name": "AWS Lambda"
    },
    {
      "is_primary": true,
      "skill_name": "ECS"
    },
    {
      "is_primary": true,
      "skill_name": "EKS"
    },
    {
      "is_primary": true,
      "skill_name": "EC2"
    },
    {
      "is_primary": true,
      "skill_name": "AWS Glue"
    },
    {
      "is_primary": true,
      "skill_name": "Amazon Athena"
    },
    {
      "is_primary": true,
      "skill_name": "Redshift"
    },
    {
      "is_primary": true,
      "skill_name": "AWS Data Pipeline"
    },
    {
      "is_primary": true,
      "skill_name": "S3"
    },
    {
      "is_primary": true,
      "skill_name": "Kinesis"
    },
    {
      "is_primary": true,
      "skill_name": "Amazon API Gateway"
    },
    {
      "is_primary": true,
      "skill_name": "Python"
    },
    {
      "is_primary": false,
      "skill_name": "TensorFlow"
    },
    {
      "is_primary": false,
      "skill_name": "PyTorch"
    },
    {
      "is_primary": false,
      "skill_name": "Scikit-learn"
    },
    {
      "is_primary": false,
      "skill_name": "GitHub Actions"
    },
    {
      "is_primary": false,
      "skill_name": "Airflow"
    },
    {
      "is_primary": false,
      "skill_name": "Terraform"
    },
    {
      "is_primary": false,
      "skill_name": "Docker"
    },
    {
      "is_primary": false,
      "skill_name": "Kubernetes"
    },
    {
      "is_primary": false,
      "skill_name": "Pinecone"
    },
    {
      "is_primary": false,
      "skill_name": "OpenSearch"
    },
    {
      "is_primary": false,
      "skill_name": "FAISS"
    }
  ],
  "run_id": null
}

{
  "alias_matches": [
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 348,
      "existing_alias_text": "AWS",
      "input_term": "AWS",
      "matched_canonical": {
        "category_id": 13,
        "display_name": "AWS",
        "id": 163,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "PLATFORM",
        "slug": "aws",
        "sub_category_id": 161,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 3408,
      "existing_alias_text": "AI/ML",
      "input_term": "AI/ML",
      "matched_canonical": {
        "category_id": 16,
        "display_name": "AI/ML",
        "id": 2611,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "CONCEPT",
        "slug": "ai-ml",
        "sub_category_id": 2131,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 3409,
      "existing_alias_text": "Amazon SageMaker",
      "input_term": "Amazon SageMaker",
      "matched_canonical": {
        "category_id": 13,
        "display_name": "Amazon SageMaker",
        "id": 2612,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "PLATFORM",
        "slug": "amazon-sagemaker",
        "sub_category_id": 326,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 3410,
      "existing_alias_text": "Amazon Bedrock",
      "input_term": "Amazon Bedrock",
      "matched_canonical": {
        "category_id": 14,
        "display_name": "Amazon Bedrock",
        "id": 2613,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "CLOUD_SERVICE",
        "slug": "amazon-bedrock",
        "sub_category_id": 2132,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 3411,
      "existing_alias_text": "AWS Lambda",
      "input_term": "AWS Lambda",
      "matched_canonical": {
        "category_id": 14,
        "display_name": "AWS Lambda",
        "id": 2614,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "CLOUD_SERVICE",
        "slug": "aws-lambda",
        "sub_category_id": 262,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 3412,
      "existing_alias_text": "ECS",
      "input_term": "ECS",
      "matched_canonical": {
        "category_id": 2,
        "display_name": "ECS",
        "id": 2615,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "CONCEPT",
        "slug": "ecs",
        "sub_category_id": 2133,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 1093,
      "existing_alias_text": "EKS",
      "input_term": "EKS",
      "matched_canonical": {
        "category_id": 14,
        "display_name": "EKS",
        "id": 725,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "CLOUD_SERVICE",
        "slug": "eks",
        "sub_category_id": 251,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 2372,
      "existing_alias_text": "EC2",
      "input_term": "EC2",
      "matched_canonical": {
        "category_id": 14,
        "display_name": "EC2",
        "id": 1773,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "CLOUD_SERVICE",
        "slug": "ec2",
        "sub_category_id": 1544,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 730,
      "existing_alias_text": "AWS Glue",
      "input_term": "AWS Glue",
      "matched_canonical": {
        "category_id": 14,
        "display_name": "AWS Glue",
        "id": 466,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "CLOUD_SERVICE",
        "slug": "aws-glue",
        "sub_category_id": 385,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 3413,
      "existing_alias_text": "Amazon Athena",
      "input_term": "Amazon Athena",
      "matched_canonical": {
        "category_id": 14,
        "display_name": "Amazon Athena",
        "id": 2616,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "CLOUD_SERVICE",
        "slug": "amazon-athena",
        "sub_category_id": 388,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 3367,
      "existing_alias_text": "Redshift",
      "input_term": "Redshift",
      "matched_canonical": {
        "category_id": 13,
        "display_name": "Redshift",
        "id": 2570,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "PLATFORM",
        "slug": "redshift",
        "sub_category_id": 2098,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 3414,
      "existing_alias_text": "AWS Data Pipeline",
      "input_term": "AWS Data Pipeline",
      "matched_canonical": {
        "category_id": 14,
        "display_name": "AWS Data Pipeline",
        "id": 2617,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "CLOUD_SERVICE",
        "slug": "aws-data-pipeline",
        "sub_category_id": 2134,
        "typical_lifespan": "SHORT_LIVED",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 3415,
      "existing_alias_text": "S3",
      "input_term": "S3",
      "matched_canonical": {
        "category_id": 13,
        "display_name": "S3",
        "id": 2618,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "PLATFORM",
        "slug": "s3",
        "sub_category_id": 2135,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 3416,
      "existing_alias_text": "Kinesis",
      "input_term": "Kinesis",
      "matched_canonical": {
        "category_id": 14,
        "display_name": "Kinesis",
        "id": 2619,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "CLOUD_SERVICE",
        "slug": "kinesis",
        "sub_category_id": 2136,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 3417,
      "existing_alias_text": "Amazon API Gateway",
      "input_term": "Amazon API Gateway",
      "matched_canonical": {
        "category_id": 14,
        "display_name": "Amazon API Gateway",
        "id": 2620,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "CLOUD_SERVICE",
        "slug": "amazon-api-gateway",
        "sub_category_id": 2137,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 608,
      "existing_alias_text": "Python",
      "input_term": "Python",
      "matched_canonical": {
        "category_id": 5,
        "display_name": "Python",
        "id": 393,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "LANGUAGE",
        "slug": "python",
        "sub_category_id": 54,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 862,
      "existing_alias_text": "TensorFlow",
      "input_term": "TensorFlow",
      "matched_canonical": {
        "category_id": 6,
        "display_name": "TensorFlow",
        "id": 558,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "LIBRARY",
        "slug": "tensorflow",
        "sub_category_id": 456,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 861,
      "existing_alias_text": "PyTorch",
      "input_term": "PyTorch",
      "matched_canonical": {
        "category_id": 6,
        "display_name": "PyTorch",
        "id": 557,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "LIBRARY",
        "slug": "pytorch",
        "sub_category_id": 456,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 852,
      "existing_alias_text": "scikit-learn",
      "input_term": "Scikit-learn",
      "matched_canonical": {
        "category_id": 6,
        "display_name": "scikit-learn",
        "id": 554,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "LIBRARY",
        "slug": "scikit-learn",
        "sub_category_id": 458,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 1800,
      "existing_alias_text": "GitHub Actions",
      "input_term": "GitHub Actions",
      "matched_canonical": {
        "category_id": 14,
        "display_name": "GitHub Actions",
        "id": 1250,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "CLOUD_SERVICE",
        "slug": "github-actions",
        "sub_category_id": 1019,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 540,
      "existing_alias_text": "Airflow",
      "input_term": "Airflow",
      "matched_canonical": {
        "category_id": 11,
        "display_name": "Airflow",
        "id": 325,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "TOOL",
        "slug": "airflow",
        "sub_category_id": 335,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 290,
      "existing_alias_text": "Terraform",
      "input_term": "Terraform",
      "matched_canonical": {
        "category_id": 11,
        "display_name": "Terraform",
        "id": 144,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "TOOL",
        "slug": "terraform",
        "sub_category_id": 171,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 299,
      "existing_alias_text": "Docker",
      "input_term": "Docker",
      "matched_canonical": {
        "category_id": 11,
        "display_name": "Docker",
        "id": 153,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "TOOL",
        "slug": "docker",
        "sub_category_id": 170,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 304,
      "existing_alias_text": "Kubernetes",
      "input_term": "Kubernetes",
      "matched_canonical": {
        "category_id": 13,
        "display_name": "Kubernetes",
        "id": 158,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "PLATFORM",
        "slug": "kubernetes",
        "sub_category_id": 1524,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 3418,
      "existing_alias_text": "Pinecone",
      "input_term": "Pinecone",
      "matched_canonical": {
        "category_id": 13,
        "display_name": "Pinecone",
        "id": 2621,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "PLATFORM",
        "slug": "pinecone",
        "sub_category_id": 2138,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 3419,
      "existing_alias_text": "OpenSearch",
      "input_term": "OpenSearch",
      "matched_canonical": {
        "category_id": 12,
        "display_name": "OpenSearch",
        "id": 2622,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "TOOL",
        "slug": "opensearch",
        "sub_category_id": 2139,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 3420,
      "existing_alias_text": "FAISS",
      "input_term": "FAISS",
      "matched_canonical": {
        "category_id": 6,
        "display_name": "FAISS",
        "id": 2623,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "LIBRARY",
        "slug": "faiss",
        "sub_category_id": 2140,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    }
  ],
  "candidate_roles": [
    {
      "display_name": "DevOps Engineer",
      "id": 1,
      "rationale": null,
      "role_archetype": "A DevOps Engineer enables reliable, repeatable delivery of software by designing and operating the processes that connect development and production. They focus on improving deployment flow, operational stability, and collaboration between teams through automation, standardization, and monitoring of delivery and runtime practices.",
      "slug": "devops-engineer",
      "source": "db"
    },
    {
      "display_name": "Cybersecurity Engineer",
      "id": 9,
      "rationale": null,
      "role_archetype": null,
      "slug": "cybersecurity-engineer",
      "source": "db"
    },
    {
      "display_name": "AI Engineer",
      "id": 12,
      "rationale": null,
      "role_archetype": null,
      "slug": "ai-engineer",
      "source": "db"
    },
    {
      "display_name": "Data Scientist",
      "id": 7,
      "rationale": null,
      "role_archetype": null,
      "slug": "data-scientist",
      "source": "db"
    },
    {
      "display_name": "MLOps Engineer",
      "id": 5,
      "rationale": null,
      "role_archetype": null,
      "slug": "mlops-engineer",
      "source": "db"
    },
    {
      "display_name": "Machine Learning Engineer",
      "id": 10,
      "rationale": null,
      "role_archetype": null,
      "slug": "machine-learning-engineer",
      "source": "db"
    },
    {
      "display_name": "Data Engineer",
      "id": 6,
      "rationale": null,
      "role_archetype": null,
      "slug": "data-engineer",
      "source": "db"
    },
    {
      "display_name": "Cloud Engineer",
      "id": 18,
      "rationale": null,
      "role_archetype": null,
      "slug": "cloud-engineer",
      "source": "db"
    },
    {
      "display_name": "Storage Engineer",
      "id": 22,
      "rationale": null,
      "role_archetype": null,
      "slug": "storage-engineer",
      "source": "db"
    },
    {
      "display_name": "Backend Engineer",
      "id": 14,
      "rationale": null,
      "role_archetype": null,
      "slug": "backend-engineer",
      "source": "db"
    },
    {
      "display_name": "Data Analyst",
      "id": 20,
      "rationale": null,
      "role_archetype": null,
      "slug": "data-analyst",
      "source": "db"
    },
    {
      "display_name": "Azure Cloud Engineer",
      "id": 4,
      "rationale": null,
      "role_archetype": null,
      "slug": "azure-cloud-engineer",
      "source": "db"
    },
    {
      "display_name": "Virtualization Engineer",
      "id": 26,
      "rationale": null,
      "role_archetype": null,
      "slug": "virtualization-engineer",
      "source": "db"
    },
    {
      "display_name": "Network Engineer",
      "id": 21,
      "rationale": null,
      "role_archetype": null,
      "slug": "network-engineer",
      "source": "db"
    },
    {
      "display_name": "Automation Tester",
      "id": 16,
      "rationale": null,
      "role_archetype": null,
      "slug": "automation-tester",
      "source": "db"
    }
  ],
  "chosen_role": {
    "display_name": "MLOps Engineer",
    "id": 5,
    "rationale": "The primary skills indicate a strong focus on AWS and AI/ML technologies, which align well with the responsibilities of an MLOps Engineer.",
    "role_archetype": null,
    "slug": "mlops-engineer",
    "source": "db"
  },
  "dimensions": [
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Cloud Platform Operations",
        "id": 26,
        "rationale": "Uses cloud provider services to support delivery and runtime environments. The focus is on consumer-level operation of cloud services rather than deep cloud architecture ownership.",
        "slug": "cloud-platform-operations",
        "source": "db"
      },
      "input_skill": "AWS",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "DevOps Engineer",
          "id": 1,
          "rationale": null,
          "role_archetype": "A DevOps Engineer enables reliable, repeatable delivery of software by designing and operating the processes that connect development and production. They focus on improving deployment flow, operational stability, and collaboration between teams through automation, standardization, and monitoring of delivery and runtime practices.",
          "slug": "devops-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Cloud Security Platforms",
        "id": 332,
        "rationale": "Cloud-native security products used to assess posture, detect misconfigurations, and monitor workloads across AWS, Azure, and GCP. This is a distinct product family because the role often works across multiple CNAPP/CSPM/CWPP offerings and cloud-native detectors.",
        "slug": "cloud-security-platforms",
        "source": "db"
      },
      "input_skill": "AWS",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Cybersecurity Engineer",
          "id": 9,
          "rationale": null,
          "role_archetype": null,
          "slug": "cybersecurity-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "AI Inference Cost, Latency, and Throughput Optimization",
        "id": 260,
        "rationale": "Improving the speed, throughput, and cost efficiency of AI and ML-powered product features without sacrificing correctness or user experience. Includes token budgeting, prompt compression, batching, caching, model selection, quantization, pruning, async inference, warm starts, streaming UX, timeout tuning, concurrency control, and profiling. Excludes infrastructure autoscaling, model serving capacity planning, generic backend performance tuning, and unrelated data/warehouse optimization.",
        "slug": "ai-inference-cost-latency-and-throughput-optimization",
        "source": "db"
      },
      "input_skill": "AI/ML",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "AI Engineer",
          "id": 12,
          "rationale": null,
          "role_archetype": null,
          "slug": "ai-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "AI Service Architecture Patterns",
        "id": 270,
        "rationale": "Structuring AI capabilities within the product and service landscape. This includes deciding whether AI logic lives in handlers, workers, gateways, or dedicated orchestration services.",
        "slug": "ai-service-architecture-patterns",
        "source": "db"
      },
      "input_skill": "AI/ML",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "AI Engineer",
          "id": 12,
          "rationale": null,
          "role_archetype": null,
          "slug": "ai-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Applied Machine Learning Toolkits",
        "id": 94,
        "rationale": "Libraries and frameworks used to prototype and compare models quickly. This dimension captures the concrete tooling layer beneath modeling methods and evaluation.",
        "slug": "applied-machine-learning-toolkits",
        "source": "db"
      },
      "input_skill": "AI/ML",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Data Scientist",
          "id": 7,
          "rationale": null,
          "role_archetype": null,
          "slug": "data-scientist",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Managed ML Platform Workflows",
        "id": 367,
        "rationale": "Cloud ML platforms for building and operating models end-to-end, including notebooks, experiments, managed training jobs, and pipeline/studio workflows. Examples: SageMaker Studio, SageMaker notebooks, SageMaker Pipelines, managed training jobs.",
        "slug": "d_split_01_01",
        "source": "db"
      },
      "input_skill": "Amazon SageMaker",
      "llm_role": null,
      "roles_from_db": []
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Managed Model Hosting and Endpoints",
        "id": 368,
        "rationale": "Cloud-managed services for deploying trained models as online or batch inference endpoints, including endpoint provisioning, batch transform, and rollout coordination. Examples: SageMaker endpoints, SageMaker batch transform.",
        "slug": "d_split_01_02",
        "source": "db"
      },
      "input_skill": "Amazon SageMaker",
      "llm_role": null,
      "roles_from_db": []
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Model Serving Deployment and Runtime Packaging",
        "id": 52,
        "rationale": "Operational deployment of trained models into online, batch, or streaming serving environments, including packaging models and model servers into containers or managed inference runtimes, coordinating rollout, and handing off to inference systems. Covers serving frameworks and platforms such as TensorFlow Serving, TorchServe, Triton Inference Server, BentoML, KServe, and Seldon Core, plus container/runtime concerns like Docker images, GPU-enabled containers, base image selection, container entrypoints, runtime dependencies, and image scanning for model services.",
        "slug": "model-serving-deployment-and-runtime-packaging",
        "source": "db"
      },
      "input_skill": "Amazon SageMaker",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "MLOps Engineer",
          "id": 5,
          "rationale": null,
          "role_archetype": null,
          "slug": "mlops-engineer",
          "source": "db"
        },
        {
          "display_name": "Machine Learning Engineer",
          "id": 10,
          "rationale": null,
          "role_archetype": null,
          "slug": "machine-learning-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Cloud Model Runtime Services",
        "id": 121,
        "rationale": "Consumer-level use of cloud services that host or support model inference applications. This cluster is coherent because MLEs often deploy and tune services on managed cloud compute, networking, and storage primitives.",
        "slug": "cloud-model-runtime-services",
        "source": "db"
      },
      "input_skill": "Amazon Bedrock",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Machine Learning Engineer",
          "id": 10,
          "rationale": null,
          "role_archetype": null,
          "slug": "machine-learning-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Cloud Data Platform Services",
        "id": 81,
        "rationale": "Consumer-level use of cloud services that support data engineering workloads. This includes managed compute, storage, networking-adjacent services, and security primitives used to run pipelines and data platforms.",
        "slug": "cloud-data-platform-services",
        "source": "db"
      },
      "input_skill": "AWS Lambda",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Data Engineer",
          "id": 6,
          "rationale": null,
          "role_archetype": null,
          "slug": "data-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Version Control Systems",
        "id": 365,
        "rationale": "Tools and workflows for tracking source changes, branching, merging, and collaborating on code history. Git belongs here because it is the canonical distributed version control system used to manage revisions and coordinate team development.",
        "slug": "d_init_01",
        "source": "db"
      },
      "input_skill": "ECS",
      "llm_role": null,
      "roles_from_db": []
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Cloud Model Runtime Services",
        "id": 121,
        "rationale": "Consumer-level use of cloud services that host or support model inference applications. This cluster is coherent because MLEs often deploy and tune services on managed cloud compute, networking, and storage primitives.",
        "slug": "cloud-model-runtime-services",
        "source": "db"
      },
      "input_skill": "EKS",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Machine Learning Engineer",
          "id": 10,
          "rationale": null,
          "role_archetype": null,
          "slug": "machine-learning-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Orchestration Platforms",
        "id": 25,
        "rationale": "Operates the platforms that schedule and run containerized workloads and related deployment primitives. This is separate from image delivery because it concerns runtime placement and service rollout behavior.",
        "slug": "orchestration-platforms",
        "source": "db"
      },
      "input_skill": "EKS",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Cloud Engineer",
          "id": 18,
          "rationale": null,
          "role_archetype": null,
          "slug": "cloud-engineer",
          "source": "db"
        },
        {
          "display_name": "DevOps Engineer",
          "id": 1,
          "rationale": null,
          "role_archetype": "A DevOps Engineer enables reliable, repeatable delivery of software by designing and operating the processes that connect development and production. They focus on improving deployment flow, operational stability, and collaboration between teams through automation, standardization, and monitoring of delivery and runtime practices.",
          "slug": "devops-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Cloud Provider Core Services",
        "id": 290,
        "rationale": "Core managed services used to provision and operate cloud environments. This is the base cloud surface for compute, storage, networking, and platform primitives the role configures and maintains.",
        "slug": "cloud-provider-core-services",
        "source": "db"
      },
      "input_skill": "EC2",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Cloud Engineer",
          "id": 18,
          "rationale": null,
          "role_archetype": null,
          "slug": "cloud-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Cloud Data Platform Services",
        "id": 81,
        "rationale": "Consumer-level use of cloud services that support data engineering workloads. This includes managed compute, storage, networking-adjacent services, and security primitives used to run pipelines and data platforms.",
        "slug": "cloud-data-platform-services",
        "source": "db"
      },
      "input_skill": "AWS Glue",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Data Engineer",
          "id": 6,
          "rationale": null,
          "role_archetype": null,
          "slug": "data-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Cloud Data Platform Security and Networking",
        "id": 369,
        "rationale": "Identity, access, secrets, and networking primitives used to support cloud data platforms and pipelines.",
        "slug": "d_split_01_04",
        "source": "db"
      },
      "input_skill": "Amazon Athena",
      "llm_role": null,
      "roles_from_db": []
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Cloud Data Platform Services",
        "id": 81,
        "rationale": "Consumer-level use of cloud services that support data engineering workloads. This includes managed compute, storage, networking-adjacent services, and security primitives used to run pipelines and data platforms.",
        "slug": "cloud-data-platform-services",
        "source": "db"
      },
      "input_skill": "Amazon Athena",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Data Engineer",
          "id": 6,
          "rationale": null,
          "role_archetype": null,
          "slug": "data-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Managed ML Platform Workflows",
        "id": 367,
        "rationale": "Cloud ML platforms for building and operating models end-to-end, including notebooks, experiments, managed training jobs, and pipeline/studio workflows. Examples: SageMaker Studio, SageMaker notebooks, SageMaker Pipelines, managed training jobs.",
        "slug": "d_split_01_01",
        "source": "db"
      },
      "input_skill": "Amazon Athena",
      "llm_role": null,
      "roles_from_db": []
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Data Warehousing Platforms",
        "id": 72,
        "rationale": "Cloud and on-prem analytical storage systems used to persist curated datasets and serve downstream consumers. This cluster is about the warehouse/lakehouse layer where transformed data is organized for access.",
        "slug": "data-warehousing-platforms",
        "source": "db"
      },
      "input_skill": "Redshift",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Data Engineer",
          "id": 6,
          "rationale": null,
          "role_archetype": null,
          "slug": "data-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Cloud Data Platform Services",
        "id": 81,
        "rationale": "Consumer-level use of cloud services that support data engineering workloads. This includes managed compute, storage, networking-adjacent services, and security primitives used to run pipelines and data platforms.",
        "slug": "cloud-data-platform-services",
        "source": "db"
      },
      "input_skill": "AWS Data Pipeline",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Data Engineer",
          "id": 6,
          "rationale": null,
          "role_archetype": null,
          "slug": "data-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Storage Provisioning and Automation",
        "id": 311,
        "rationale": "Covers the scripts, APIs, and operational workflows used to create, resize, map, and retire storage resources. This cluster is coherent because storage engineers often automate repetitive provisioning and maintenance tasks.",
        "slug": "storage-provisioning-and-automation",
        "source": "db"
      },
      "input_skill": "S3",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Storage Engineer",
          "id": 22,
          "rationale": null,
          "role_archetype": null,
          "slug": "storage-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Streaming Data Processing",
        "id": 69,
        "rationale": "Tools and patterns for ingesting and transforming event streams with low latency. This cluster covers continuous processing, windowing, and stateful stream jobs used to keep data fresh.",
        "slug": "streaming-data-processing",
        "source": "db"
      },
      "input_skill": "Kinesis",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Data Engineer",
          "id": 6,
          "rationale": null,
          "role_archetype": null,
          "slug": "data-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Web Service Frameworks",
        "id": 141,
        "rationale": "Server frameworks used to build HTTP APIs, route requests, validate inputs, and structure backend application code. This cluster is coherent because it defines how backend services expose behavior to clients and other services.",
        "slug": "web-service-frameworks",
        "source": "db"
      },
      "input_skill": "Amazon API Gateway",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Backend Engineer",
          "id": 14,
          "rationale": null,
          "role_archetype": null,
          "slug": "backend-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Analytical Programming Languages",
        "id": 82,
        "rationale": "Languages used to clean, transform, analyze, and prototype models in notebooks and scripts. This is the core coding surface for expressing statistical logic and data manipulation in a reproducible way.",
        "slug": "analytical-programming-languages",
        "source": "db"
      },
      "input_skill": "Python",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Data Analyst",
          "id": 20,
          "rationale": null,
          "role_archetype": null,
          "slug": "data-analyst",
          "source": "db"
        },
        {
          "display_name": "Data Scientist",
          "id": 7,
          "rationale": null,
          "role_archetype": null,
          "slug": "data-scientist",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Automation Scripting and CLI",
        "id": 48,
        "rationale": "Uses scripts and command-line tooling to execute repeatable Azure operations and reduce manual work. This is a practical cluster because the role frequently automates provisioning, checks, and remediation tasks.",
        "slug": "automation-scripting-and-cli",
        "source": "db"
      },
      "input_skill": "Python",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Azure Cloud Engineer",
          "id": 4,
          "rationale": null,
          "role_archetype": null,
          "slug": "azure-cloud-engineer",
          "source": "db"
        },
        {
          "display_name": "Cloud Engineer",
          "id": 18,
          "rationale": null,
          "role_archetype": null,
          "slug": "cloud-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Automation and Scripting for Operations",
        "id": 361,
        "rationale": "Scripts and lightweight automation used to execute repetitive virtualization tasks and enforce operational consistency. This is the practical glue that reduces manual host and VM administration.",
        "slug": "automation-and-scripting-for-operations",
        "source": "db"
      },
      "input_skill": "Python",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Virtualization Engineer",
          "id": 26,
          "rationale": null,
          "role_archetype": null,
          "slug": "virtualization-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Network Automation and Scripting",
        "id": 285,
        "rationale": "Covers scripts and automation used to configure, validate, and audit network devices and services. This cluster is coherent because repeatable network operations increasingly depend on programmatic changes and checks.",
        "slug": "network-automation-and-scripting",
        "source": "db"
      },
      "input_skill": "Python",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Network Engineer",
          "id": 21,
          "rationale": null,
          "role_archetype": null,
          "slug": "network-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Programming Languages for AI Workflows",
        "id": 261,
        "rationale": "Languages used to implement AI feature logic, orchestration, and response handling inside product code. This is the core coding surface for turning prompts and model calls into reliable application behavior.",
        "slug": "programming-languages-for-ai-workflows",
        "source": "db"
      },
      "input_skill": "Python",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "AI Engineer",
          "id": 12,
          "rationale": null,
          "role_archetype": null,
          "slug": "ai-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Programming Languages for Backend Systems",
        "id": 140,
        "rationale": "Languages used to implement server-side business logic, request handlers, workers, and service integrations. This is the core coding surface for backend feature delivery and maintenance.",
        "slug": "programming-languages-for-backend-systems",
        "source": "db"
      },
      "input_skill": "Python",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Backend Engineer",
          "id": 14,
          "rationale": null,
          "role_archetype": null,
          "slug": "backend-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Programming Languages for Data Work",
        "id": 67,
        "rationale": "Languages used to implement data pipelines, transformations, and operational utilities. This is the code layer for expressing extraction, parsing, validation, and orchestration logic in data engineering workflows.",
        "slug": "programming-languages-for-data-work",
        "source": "db"
      },
      "input_skill": "Python",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Data Engineer",
          "id": 6,
          "rationale": null,
          "role_archetype": null,
          "slug": "data-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Programming Languages for ML Systems",
        "id": 113,
        "rationale": "Languages used to implement model integration code, inference services, and feature-processing logic. This is the core coding surface for turning trained models into product-facing software components.",
        "slug": "programming-languages-for-ml-systems",
        "source": "db"
      },
      "input_skill": "Python",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Machine Learning Engineer",
          "id": 10,
          "rationale": null,
          "role_archetype": null,
          "slug": "machine-learning-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Programming Languages for Security Work",
        "id": 328,
        "rationale": "Languages used to automate security tasks, write detection logic, and build analysis or remediation tooling. This is the core coding surface for a cybersecurity engineer across scripts, queries, and small utilities.",
        "slug": "programming-languages-for-security-work",
        "source": "db"
      },
      "input_skill": "Python",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Cybersecurity Engineer",
          "id": 9,
          "rationale": null,
          "role_archetype": null,
          "slug": "cybersecurity-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Programming Languages for Test Automation",
        "id": 193,
        "rationale": "Languages used to implement automated checks, helper utilities, and test harness code. This is the core coding surface for turning test ideas into maintainable automation.",
        "slug": "programming-languages-for-test-automation",
        "source": "db"
      },
      "input_skill": "Python",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Automation Tester",
          "id": 16,
          "rationale": null,
          "role_archetype": null,
          "slug": "automation-tester",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Security Automation and Scripting",
        "id": 258,
        "rationale": "Automating repeatable security checks, enrichment, and remediation workflows. This cluster is coherent because the role often needs lightweight automation to scale analysis and response.",
        "slug": "security-automation-and-scripting",
        "source": "db"
      },
      "input_skill": "Python",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Cybersecurity Engineer",
          "id": 9,
          "rationale": null,
          "role_archetype": null,
          "slug": "cybersecurity-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Applied Machine Learning Toolkits",
        "id": 94,
        "rationale": "Libraries and frameworks used to prototype and compare models quickly. This dimension captures the concrete tooling layer beneath modeling methods and evaluation.",
        "slug": "applied-machine-learning-toolkits",
        "source": "db"
      },
      "input_skill": "TensorFlow",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Data Scientist",
          "id": 7,
          "rationale": null,
          "role_archetype": null,
          "slug": "data-scientist",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Applied Machine Learning Toolkits",
        "id": 94,
        "rationale": "Libraries and frameworks used to prototype and compare models quickly. This dimension captures the concrete tooling layer beneath modeling methods and evaluation.",
        "slug": "applied-machine-learning-toolkits",
        "source": "db"
      },
      "input_skill": "PyTorch",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Data Scientist",
          "id": 7,
          "rationale": null,
          "role_archetype": null,
          "slug": "data-scientist",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Applied Machine Learning Toolkits",
        "id": 94,
        "rationale": "Libraries and frameworks used to prototype and compare models quickly. This dimension captures the concrete tooling layer beneath modeling methods and evaluation.",
        "slug": "applied-machine-learning-toolkits",
        "source": "db"
      },
      "input_skill": "Scikit-learn",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Data Scientist",
          "id": 7,
          "rationale": null,
          "role_archetype": null,
          "slug": "data-scientist",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Continuous Integration Test Integration",
        "id": 207,
        "rationale": "Integrating automated checks into shared build and merge workflows so results are repeatable and visible. This cluster is coherent because automation testers commonly configure test execution triggers, artifacts, and reporting hooks.",
        "slug": "continuous-integration-test-integration",
        "source": "db"
      },
      "input_skill": "GitHub Actions",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Automation Tester",
          "id": 16,
          "rationale": null,
          "role_archetype": null,
          "slug": "automation-tester",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Workflow Orchestration Systems",
        "id": 64,
        "rationale": "Operational orchestration of ML jobs, dependencies, and handoffs across training, validation, deployment, and retraining. This is a useful split from training pipelines because it emphasizes the scheduler and control plane.",
        "slug": "workflow-orchestration-systems",
        "source": "db"
      },
      "input_skill": "Airflow",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Data Engineer",
          "id": 6,
          "rationale": null,
          "role_archetype": null,
          "slug": "data-engineer",
          "source": "db"
        },
        {
          "display_name": "MLOps Engineer",
          "id": 5,
          "rationale": null,
          "role_archetype": null,
          "slug": "mlops-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Infrastructure Provisioning Templates",
        "id": 291,
        "rationale": "Declarative templates and modules used to create repeatable cloud resources and environments. This cluster covers the infrastructure definitions the role applies, reviews, and updates to keep environments consistent.",
        "slug": "infrastructure-provisioning-templates",
        "source": "db"
      },
      "input_skill": "Terraform",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Cloud Engineer",
          "id": 18,
          "rationale": null,
          "role_archetype": null,
          "slug": "cloud-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Infrastructure as Code",
        "id": 22,
        "rationale": "Defines infrastructure and platform resources through versioned code so environments are repeatable and reviewable. This is a coherent cluster because it underpins environment consistency and change control.",
        "slug": "infrastructure-as-code",
        "source": "db"
      },
      "input_skill": "Terraform",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "DevOps Engineer",
          "id": 1,
          "rationale": null,
          "role_archetype": "A DevOps Engineer enables reliable, repeatable delivery of software by designing and operating the processes that connect development and production. They focus on improving deployment flow, operational stability, and collaboration between teams through automation, standardization, and monitoring of delivery and runtime practices.",
          "slug": "devops-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Infrastructure as Code and Declarative Provisioning",
        "id": 36,
        "rationale": "Defines cloud and platform infrastructure declaratively through versioned code so environments are repeatable, reviewable, and automatable. This includes authoring and maintaining IaC templates/modules, managing parameters and state, and using plan/apply workflows to provision and update resources across Azure and other cloud platforms.",
        "slug": "infrastructure-as-code-and-declarative-provisioning",
        "source": "db"
      },
      "input_skill": "Terraform",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Azure Cloud Engineer",
          "id": 4,
          "rationale": null,
          "role_archetype": null,
          "slug": "azure-cloud-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Containerization and Image Delivery",
        "id": 24,
        "rationale": "Builds, packages, and ships application and support workloads as container images. This cluster covers the artifact format and the mechanics of producing deployable images.",
        "slug": "containerization-and-image-delivery",
        "source": "db"
      },
      "input_skill": "Docker",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "DevOps Engineer",
          "id": 1,
          "rationale": null,
          "role_archetype": "A DevOps Engineer enables reliable, repeatable delivery of software by designing and operating the processes that connect development and production. They focus on improving deployment flow, operational stability, and collaboration between teams through automation, standardization, and monitoring of delivery and runtime practices.",
          "slug": "devops-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Model Serving Deployment and Runtime Packaging",
        "id": 52,
        "rationale": "Operational deployment of trained models into online, batch, or streaming serving environments, including packaging models and model servers into containers or managed inference runtimes, coordinating rollout, and handing off to inference systems. Covers serving frameworks and platforms such as TensorFlow Serving, TorchServe, Triton Inference Server, BentoML, KServe, and Seldon Core, plus container/runtime concerns like Docker images, GPU-enabled containers, base image selection, container entrypoints, runtime dependencies, and image scanning for model services.",
        "slug": "model-serving-deployment-and-runtime-packaging",
        "source": "db"
      },
      "input_skill": "Docker",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "MLOps Engineer",
          "id": 5,
          "rationale": null,
          "role_archetype": null,
          "slug": "mlops-engineer",
          "source": "db"
        },
        {
          "display_name": "Machine Learning Engineer",
          "id": 10,
          "rationale": null,
          "role_archetype": null,
          "slug": "machine-learning-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Orchestration Platforms",
        "id": 25,
        "rationale": "Operates the platforms that schedule and run containerized workloads and related deployment primitives. This is separate from image delivery because it concerns runtime placement and service rollout behavior.",
        "slug": "orchestration-platforms",
        "source": "db"
      },
      "input_skill": "Kubernetes",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Cloud Engineer",
          "id": 18,
          "rationale": null,
          "role_archetype": null,
          "slug": "cloud-engineer",
          "source": "db"
        },
        {
          "display_name": "DevOps Engineer",
          "id": 1,
          "rationale": null,
          "role_archetype": "A DevOps Engineer enables reliable, repeatable delivery of software by designing and operating the processes that connect development and production. They focus on improving deployment flow, operational stability, and collaboration between teams through automation, standardization, and monitoring of delivery and runtime practices.",
          "slug": "devops-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Cloud Model Runtime Services",
        "id": 121,
        "rationale": "Consumer-level use of cloud services that host or support model inference applications. This cluster is coherent because MLEs often deploy and tune services on managed cloud compute, networking, and storage primitives.",
        "slug": "cloud-model-runtime-services",
        "source": "db"
      },
      "input_skill": "Pinecone",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Machine Learning Engineer",
          "id": 10,
          "rationale": null,
          "role_archetype": null,
          "slug": "machine-learning-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Cloud Data Platform Services",
        "id": 81,
        "rationale": "Consumer-level use of cloud services that support data engineering workloads. This includes managed compute, storage, networking-adjacent services, and security primitives used to run pipelines and data platforms.",
        "slug": "cloud-data-platform-services",
        "source": "db"
      },
      "input_skill": "OpenSearch",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Data Engineer",
          "id": 6,
          "rationale": null,
          "role_archetype": null,
          "slug": "data-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Version Control Systems",
        "id": 365,
        "rationale": "Tools and workflows for tracking source changes, branching, merging, and collaborating on code history. Git belongs here because it is the canonical distributed version control system used to manage revisions and coordinate team development.",
        "slug": "d_init_01",
        "source": "db"
      },
      "input_skill": "OpenSearch",
      "llm_role": null,
      "roles_from_db": []
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Applied Machine Learning Toolkits",
        "id": 94,
        "rationale": "Libraries and frameworks used to prototype and compare models quickly. This dimension captures the concrete tooling layer beneath modeling methods and evaluation.",
        "slug": "applied-machine-learning-toolkits",
        "source": "db"
      },
      "input_skill": "FAISS",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Data Scientist",
          "id": 7,
          "rationale": null,
          "role_archetype": null,
          "slug": "data-scientist",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Version Control Systems",
        "id": 365,
        "rationale": "Tools and workflows for tracking source changes, branching, merging, and collaborating on code history. Git belongs here because it is the canonical distributed version control system used to manage revisions and coordinate team development.",
        "slug": "d_init_01",
        "source": "db"
      },
      "input_skill": "FAISS",
      "llm_role": null,
      "roles_from_db": []
    }
  ],
  "input_final_skills": [
    "AWS",
    "AI/ML",
    "Amazon SageMaker",
    "Amazon Bedrock",
    "AWS Lambda",
    "ECS",
    "EKS",
    "EC2",
    "AWS Glue",
    "Amazon Athena",
    "Redshift",
    "AWS Data Pipeline",
    "S3",
    "Kinesis",
    "Amazon API Gateway",
    "Python",
    "TensorFlow",
    "PyTorch",
    "Scikit-learn",
    "GitHub Actions",
    "Airflow",
    "Terraform",
    "Docker",
    "Kubernetes",
    "Pinecone",
    "OpenSearch",
    "FAISS"
  ],
  "input_llm_skills": [
    "AWS",
    "AI/ML",
    "Amazon SageMaker",
    "Amazon Bedrock",
    "AWS Lambda",
    "ECS",
    "EKS",
    "EC2",
    "AWS Glue",
    "Amazon Athena",
    "Redshift",
    "AWS Data Pipeline",
    "S3",
    "Kinesis",
    "Amazon API Gateway",
    "Python",
    "TensorFlow",
    "PyTorch",
    "Scikit-learn",
    "GitHub Actions",
    "Airflow",
    "Terraform",
    "Docker",
    "Kubernetes",
    "Pinecone",
    "OpenSearch",
    "FAISS"
  ],
  "new_aliases_persisted": 0,
  "run_id": "832dda01-52e1-4739-b122-0a9cf9bc8100",
  "skills_detail": [
    {
      "aliases_in_db": [
        {
          "alias_text": "AWS",
          "alias_type": "CANONICAL",
          "id": 348,
          "is_primary": true,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 13,
        "display_name": "AWS",
        "id": 163,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "PLATFORM",
        "slug": "aws",
        "sub_category_id": 161,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Cloud Platform Operations",
            "id": 26,
            "rationale": "Uses cloud provider services to support delivery and runtime environments. The focus is on consumer-level operation of cloud services rather than deep cloud architecture ownership.",
            "slug": "cloud-platform-operations",
            "source": "db"
          },
          "input_skill": "AWS",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "DevOps Engineer",
              "id": 1,
              "rationale": null,
              "role_archetype": "A DevOps Engineer enables reliable, repeatable delivery of software by designing and operating the processes that connect development and production. They focus on improving deployment flow, operational stability, and collaboration between teams through automation, standardization, and monitoring of delivery and runtime practices.",
              "slug": "devops-engineer",
              "source": "db"
            }
          ]
        },
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Cloud Security Platforms",
            "id": 332,
            "rationale": "Cloud-native security products used to assess posture, detect misconfigurations, and monitor workloads across AWS, Azure, and GCP. This is a distinct product family because the role often works across multiple CNAPP/CSPM/CWPP offerings and cloud-native detectors.",
            "slug": "cloud-security-platforms",
            "source": "db"
          },
          "input_skill": "AWS",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Cybersecurity Engineer",
              "id": 9,
              "rationale": null,
              "role_archetype": null,
              "slug": "cybersecurity-engineer",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "AWS",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "AI/ML",
          "alias_type": "CANONICAL",
          "id": 3408,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 16,
        "display_name": "AI/ML",
        "id": 2611,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "CONCEPT",
        "slug": "ai-ml",
        "sub_category_id": 2131,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "AI Inference Cost, Latency, and Throughput Optimization",
            "id": 260,
            "rationale": "Improving the speed, throughput, and cost efficiency of AI and ML-powered product features without sacrificing correctness or user experience. Includes token budgeting, prompt compression, batching, caching, model selection, quantization, pruning, async inference, warm starts, streaming UX, timeout tuning, concurrency control, and profiling. Excludes infrastructure autoscaling, model serving capacity planning, generic backend performance tuning, and unrelated data/warehouse optimization.",
            "slug": "ai-inference-cost-latency-and-throughput-optimization",
            "source": "db"
          },
          "input_skill": "AI/ML",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "AI Engineer",
              "id": 12,
              "rationale": null,
              "role_archetype": null,
              "slug": "ai-engineer",
              "source": "db"
            }
          ]
        },
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "AI Service Architecture Patterns",
            "id": 270,
            "rationale": "Structuring AI capabilities within the product and service landscape. This includes deciding whether AI logic lives in handlers, workers, gateways, or dedicated orchestration services.",
            "slug": "ai-service-architecture-patterns",
            "source": "db"
          },
          "input_skill": "AI/ML",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "AI Engineer",
              "id": 12,
              "rationale": null,
              "role_archetype": null,
              "slug": "ai-engineer",
              "source": "db"
            }
          ]
        },
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Applied Machine Learning Toolkits",
            "id": 94,
            "rationale": "Libraries and frameworks used to prototype and compare models quickly. This dimension captures the concrete tooling layer beneath modeling methods and evaluation.",
            "slug": "applied-machine-learning-toolkits",
            "source": "db"
          },
          "input_skill": "AI/ML",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Data Scientist",
              "id": 7,
              "rationale": null,
              "role_archetype": null,
              "slug": "data-scientist",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "AI/ML",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "Amazon SageMaker",
          "alias_type": "CANONICAL",
          "id": 3409,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 13,
        "display_name": "Amazon SageMaker",
        "id": 2612,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "PLATFORM",
        "slug": "amazon-sagemaker",
        "sub_category_id": 326,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Managed ML Platform Workflows",
            "id": 367,
            "rationale": "Cloud ML platforms for building and operating models end-to-end, including notebooks, experiments, managed training jobs, and pipeline/studio workflows. Examples: SageMaker Studio, SageMaker notebooks, SageMaker Pipelines, managed training jobs.",
            "slug": "d_split_01_01",
            "source": "db"
          },
          "input_skill": "Amazon SageMaker",
          "llm_role": null,
          "roles_from_db": []
        },
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Managed Model Hosting and Endpoints",
            "id": 368,
            "rationale": "Cloud-managed services for deploying trained models as online or batch inference endpoints, including endpoint provisioning, batch transform, and rollout coordination. Examples: SageMaker endpoints, SageMaker batch transform.",
            "slug": "d_split_01_02",
            "source": "db"
          },
          "input_skill": "Amazon SageMaker",
          "llm_role": null,
          "roles_from_db": []
        },
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Model Serving Deployment and Runtime Packaging",
            "id": 52,
            "rationale": "Operational deployment of trained models into online, batch, or streaming serving environments, including packaging models and model servers into containers or managed inference runtimes, coordinating rollout, and handing off to inference systems. Covers serving frameworks and platforms such as TensorFlow Serving, TorchServe, Triton Inference Server, BentoML, KServe, and Seldon Core, plus container/runtime concerns like Docker images, GPU-enabled containers, base image selection, container entrypoints, runtime dependencies, and image scanning for model services.",
            "slug": "model-serving-deployment-and-runtime-packaging",
            "source": "db"
          },
          "input_skill": "Amazon SageMaker",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "MLOps Engineer",
              "id": 5,
              "rationale": null,
              "role_archetype": null,
              "slug": "mlops-engineer",
              "source": "db"
            },
            {
              "display_name": "Machine Learning Engineer",
              "id": 10,
              "rationale": null,
              "role_archetype": null,
              "slug": "machine-learning-engineer",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "Amazon SageMaker",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "Amazon Bedrock",
          "alias_type": "CANONICAL",
          "id": 3410,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 14,
        "display_name": "Amazon Bedrock",
        "id": 2613,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "CLOUD_SERVICE",
        "slug": "amazon-bedrock",
        "sub_category_id": 2132,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Cloud Model Runtime Services",
            "id": 121,
            "rationale": "Consumer-level use of cloud services that host or support model inference applications. This cluster is coherent because MLEs often deploy and tune services on managed cloud compute, networking, and storage primitives.",
            "slug": "cloud-model-runtime-services",
            "source": "db"
          },
          "input_skill": "Amazon Bedrock",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Machine Learning Engineer",
              "id": 10,
              "rationale": null,
              "role_archetype": null,
              "slug": "machine-learning-engineer",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "Amazon Bedrock",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "AWS Lambda",
          "alias_type": "CANONICAL",
          "id": 3411,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 14,
        "display_name": "AWS Lambda",
        "id": 2614,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "CLOUD_SERVICE",
        "slug": "aws-lambda",
        "sub_category_id": 262,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Cloud Data Platform Services",
            "id": 81,
            "rationale": "Consumer-level use of cloud services that support data engineering workloads. This includes managed compute, storage, networking-adjacent services, and security primitives used to run pipelines and data platforms.",
            "slug": "cloud-data-platform-services",
            "source": "db"
          },
          "input_skill": "AWS Lambda",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Data Engineer",
              "id": 6,
              "rationale": null,
              "role_archetype": null,
              "slug": "data-engineer",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "AWS Lambda",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "ECS",
          "alias_type": "CANONICAL",
          "id": 3412,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 2,
        "display_name": "ECS",
        "id": 2615,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "CONCEPT",
        "slug": "ecs",
        "sub_category_id": 2133,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Version Control Systems",
            "id": 365,
            "rationale": "Tools and workflows for tracking source changes, branching, merging, and collaborating on code history. Git belongs here because it is the canonical distributed version control system used to manage revisions and coordinate team development.",
            "slug": "d_init_01",
            "source": "db"
          },
          "input_skill": "ECS",
          "llm_role": null,
          "roles_from_db": []
        }
      ],
      "input_skill": "ECS",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "EKS",
          "alias_type": "CANONICAL",
          "id": 1093,
          "is_primary": true,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 14,
        "display_name": "EKS",
        "id": 725,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "CLOUD_SERVICE",
        "slug": "eks",
        "sub_category_id": 251,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Cloud Model Runtime Services",
            "id": 121,
            "rationale": "Consumer-level use of cloud services that host or support model inference applications. This cluster is coherent because MLEs often deploy and tune services on managed cloud compute, networking, and storage primitives.",
            "slug": "cloud-model-runtime-services",
            "source": "db"
          },
          "input_skill": "EKS",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Machine Learning Engineer",
              "id": 10,
              "rationale": null,
              "role_archetype": null,
              "slug": "machine-learning-engineer",
              "source": "db"
            }
          ]
        },
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Orchestration Platforms",
            "id": 25,
            "rationale": "Operates the platforms that schedule and run containerized workloads and related deployment primitives. This is separate from image delivery because it concerns runtime placement and service rollout behavior.",
            "slug": "orchestration-platforms",
            "source": "db"
          },
          "input_skill": "EKS",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Cloud Engineer",
              "id": 18,
              "rationale": null,
              "role_archetype": null,
              "slug": "cloud-engineer",
              "source": "db"
            },
            {
              "display_name": "DevOps Engineer",
              "id": 1,
              "rationale": null,
              "role_archetype": "A DevOps Engineer enables reliable, repeatable delivery of software by designing and operating the processes that connect development and production. They focus on improving deployment flow, operational stability, and collaboration between teams through automation, standardization, and monitoring of delivery and runtime practices.",
              "slug": "devops-engineer",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "EKS",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "EC2",
          "alias_type": "CANONICAL",
          "id": 2372,
          "is_primary": true,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 14,
        "display_name": "EC2",
        "id": 1773,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "CLOUD_SERVICE",
        "slug": "ec2",
        "sub_category_id": 1544,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Cloud Provider Core Services",
            "id": 290,
            "rationale": "Core managed services used to provision and operate cloud environments. This is the base cloud surface for compute, storage, networking, and platform primitives the role configures and maintains.",
            "slug": "cloud-provider-core-services",
            "source": "db"
          },
          "input_skill": "EC2",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Cloud Engineer",
              "id": 18,
              "rationale": null,
              "role_archetype": null,
              "slug": "cloud-engineer",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "EC2",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "AWS Glue",
          "alias_type": "CANONICAL",
          "id": 730,
          "is_primary": true,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 14,
        "display_name": "AWS Glue",
        "id": 466,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "CLOUD_SERVICE",
        "slug": "aws-glue",
        "sub_category_id": 385,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Cloud Data Platform Services",
            "id": 81,
            "rationale": "Consumer-level use of cloud services that support data engineering workloads. This includes managed compute, storage, networking-adjacent services, and security primitives used to run pipelines and data platforms.",
            "slug": "cloud-data-platform-services",
            "source": "db"
          },
          "input_skill": "AWS Glue",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Data Engineer",
              "id": 6,
              "rationale": null,
              "role_archetype": null,
              "slug": "data-engineer",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "AWS Glue",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "Amazon Athena",
          "alias_type": "CANONICAL",
          "id": 3413,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 14,
        "display_name": "Amazon Athena",
        "id": 2616,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "CLOUD_SERVICE",
        "slug": "amazon-athena",
        "sub_category_id": 388,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Cloud Data Platform Security and Networking",
            "id": 369,
            "rationale": "Identity, access, secrets, and networking primitives used to support cloud data platforms and pipelines.",
            "slug": "d_split_01_04",
            "source": "db"
          },
          "input_skill": "Amazon Athena",
          "llm_role": null,
          "roles_from_db": []
        },
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Cloud Data Platform Services",
            "id": 81,
            "rationale": "Consumer-level use of cloud services that support data engineering workloads. This includes managed compute, storage, networking-adjacent services, and security primitives used to run pipelines and data platforms.",
            "slug": "cloud-data-platform-services",
            "source": "db"
          },
          "input_skill": "Amazon Athena",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Data Engineer",
              "id": 6,
              "rationale": null,
              "role_archetype": null,
              "slug": "data-engineer",
              "source": "db"
            }
          ]
        },
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Managed ML Platform Workflows",
            "id": 367,
            "rationale": "Cloud ML platforms for building and operating models end-to-end, including notebooks, experiments, managed training jobs, and pipeline/studio workflows. Examples: SageMaker Studio, SageMaker notebooks, SageMaker Pipelines, managed training jobs.",
            "slug": "d_split_01_01",
            "source": "db"
          },
          "input_skill": "Amazon Athena",
          "llm_role": null,
          "roles_from_db": []
        }
      ],
      "input_skill": "Amazon Athena",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "Redshift",
          "alias_type": "CANONICAL",
          "id": 3367,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 13,
        "display_name": "Redshift",
        "id": 2570,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "PLATFORM",
        "slug": "redshift",
        "sub_category_id": 2098,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Data Warehousing Platforms",
            "id": 72,
            "rationale": "Cloud and on-prem analytical storage systems used to persist curated datasets and serve downstream consumers. This cluster is about the warehouse/lakehouse layer where transformed data is organized for access.",
            "slug": "data-warehousing-platforms",
            "source": "db"
          },
          "input_skill": "Redshift",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Data Engineer",
              "id": 6,
              "rationale": null,
              "role_archetype": null,
              "slug": "data-engineer",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "Redshift",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "AWS Data Pipeline",
          "alias_type": "CANONICAL",
          "id": 3414,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 14,
        "display_name": "AWS Data Pipeline",
        "id": 2617,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "CLOUD_SERVICE",
        "slug": "aws-data-pipeline",
        "sub_category_id": 2134,
        "typical_lifespan": "SHORT_LIVED",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Cloud Data Platform Services",
            "id": 81,
            "rationale": "Consumer-level use of cloud services that support data engineering workloads. This includes managed compute, storage, networking-adjacent services, and security primitives used to run pipelines and data platforms.",
            "slug": "cloud-data-platform-services",
            "source": "db"
          },
          "input_skill": "AWS Data Pipeline",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Data Engineer",
              "id": 6,
              "rationale": null,
              "role_archetype": null,
              "slug": "data-engineer",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "AWS Data Pipeline",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "S3",
          "alias_type": "CANONICAL",
          "id": 3415,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 13,
        "display_name": "S3",
        "id": 2618,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "PLATFORM",
        "slug": "s3",
        "sub_category_id": 2135,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Storage Provisioning and Automation",
            "id": 311,
            "rationale": "Covers the scripts, APIs, and operational workflows used to create, resize, map, and retire storage resources. This cluster is coherent because storage engineers often automate repetitive provisioning and maintenance tasks.",
            "slug": "storage-provisioning-and-automation",
            "source": "db"
          },
          "input_skill": "S3",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Storage Engineer",
              "id": 22,
              "rationale": null,
              "role_archetype": null,
              "slug": "storage-engineer",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "S3",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "Kinesis",
          "alias_type": "CANONICAL",
          "id": 3416,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 14,
        "display_name": "Kinesis",
        "id": 2619,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "CLOUD_SERVICE",
        "slug": "kinesis",
        "sub_category_id": 2136,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Streaming Data Processing",
            "id": 69,
            "rationale": "Tools and patterns for ingesting and transforming event streams with low latency. This cluster covers continuous processing, windowing, and stateful stream jobs used to keep data fresh.",
            "slug": "streaming-data-processing",
            "source": "db"
          },
          "input_skill": "Kinesis",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Data Engineer",
              "id": 6,
              "rationale": null,
              "role_archetype": null,
              "slug": "data-engineer",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "Kinesis",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "Amazon API Gateway",
          "alias_type": "CANONICAL",
          "id": 3417,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 14,
        "display_name": "Amazon API Gateway",
        "id": 2620,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "CLOUD_SERVICE",
        "slug": "amazon-api-gateway",
        "sub_category_id": 2137,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Web Service Frameworks",
            "id": 141,
            "rationale": "Server frameworks used to build HTTP APIs, route requests, validate inputs, and structure backend application code. This cluster is coherent because it defines how backend services expose behavior to clients and other services.",
            "slug": "web-service-frameworks",
            "source": "db"
          },
          "input_skill": "Amazon API Gateway",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Backend Engineer",
              "id": 14,
              "rationale": null,
              "role_archetype": null,
              "slug": "backend-engineer",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "Amazon API Gateway",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "Python",
          "alias_type": "CANONICAL",
          "id": 608,
          "is_primary": true,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Python 2",
          "alias_type": "VERSION",
          "id": 611,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Python 2.x",
          "alias_type": "VERSION",
          "id": 613,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Python 3",
          "alias_type": "VERSION",
          "id": 612,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Python 3.10",
          "alias_type": "VERSION",
          "id": 2330,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Python 3.11",
          "alias_type": "VERSION",
          "id": 2331,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Python 3.12",
          "alias_type": "VERSION",
          "id": 2332,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Python 3.x",
          "alias_type": "VERSION",
          "id": 614,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "py2",
          "alias_type": "VERSION",
          "id": 609,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "py3",
          "alias_type": "VERSION",
          "id": 610,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "python 2",
          "alias_type": "VERSION",
          "id": 2152,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "python 2.x",
          "alias_type": "VERSION",
          "id": 2154,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "python 3",
          "alias_type": "VERSION",
          "id": 990,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "python 3.10",
          "alias_type": "VERSION",
          "id": 992,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "python 3.11",
          "alias_type": "VERSION",
          "id": 993,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "python 3.12",
          "alias_type": "VERSION",
          "id": 994,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "python 3.x",
          "alias_type": "VERSION",
          "id": 991,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "python2",
          "alias_type": "VERSION",
          "id": 2150,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "python3",
          "alias_type": "VERSION",
          "id": 989,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 5,
        "display_name": "Python",
        "id": 393,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "LANGUAGE",
        "slug": "python",
        "sub_category_id": 54,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Analytical Programming Languages",
            "id": 82,
            "rationale": "Languages used to clean, transform, analyze, and prototype models in notebooks and scripts. This is the core coding surface for expressing statistical logic and data manipulation in a reproducible way.",
            "slug": "analytical-programming-languages",
            "source": "db"
          },
          "input_skill": "Python",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Data Analyst",
              "id": 20,
              "rationale": null,
              "role_archetype": null,
              "slug": "data-analyst",
              "source": "db"
            },
            {
              "display_name": "Data Scientist",
              "id": 7,
              "rationale": null,
              "role_archetype": null,
              "slug": "data-scientist",
              "source": "db"
            }
          ]
        },
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Automation Scripting and CLI",
            "id": 48,
            "rationale": "Uses scripts and command-line tooling to execute repeatable Azure operations and reduce manual work. This is a practical cluster because the role frequently automates provisioning, checks, and remediation tasks.",
            "slug": "automation-scripting-and-cli",
            "source": "db"
          },
          "input_skill": "Python",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Azure Cloud Engineer",
              "id": 4,
              "rationale": null,
              "role_archetype": null,
              "slug": "azure-cloud-engineer",
              "source": "db"
            },
            {
              "display_name": "Cloud Engineer",
              "id": 18,
              "rationale": null,
              "role_archetype": null,
              "slug": "cloud-engineer",
              "source": "db"
            }
          ]
        },
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Automation and Scripting for Operations",
            "id": 361,
            "rationale": "Scripts and lightweight automation used to execute repetitive virtualization tasks and enforce operational consistency. This is the practical glue that reduces manual host and VM administration.",
            "slug": "automation-and-scripting-for-operations",
            "source": "db"
          },
          "input_skill": "Python",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Virtualization Engineer",
              "id": 26,
              "rationale": null,
              "role_archetype": null,
              "slug": "virtualization-engineer",
              "source": "db"
            }
          ]
        },
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Network Automation and Scripting",
            "id": 285,
            "rationale": "Covers scripts and automation used to configure, validate, and audit network devices and services. This cluster is coherent because repeatable network operations increasingly depend on programmatic changes and checks.",
            "slug": "network-automation-and-scripting",
            "source": "db"
          },
          "input_skill": "Python",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Network Engineer",
              "id": 21,
              "rationale": null,
              "role_archetype": null,
              "slug": "network-engineer",
              "source": "db"
            }
          ]
        },
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Programming Languages for AI Workflows",
            "id": 261,
            "rationale": "Languages used to implement AI feature logic, orchestration, and response handling inside product code. This is the core coding surface for turning prompts and model calls into reliable application behavior.",
            "slug": "programming-languages-for-ai-workflows",
            "source": "db"
          },
          "input_skill": "Python",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "AI Engineer",
              "id": 12,
              "rationale": null,
              "role_archetype": null,
              "slug": "ai-engineer",
              "source": "db"
            }
          ]
        },
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Programming Languages for Backend Systems",
            "id": 140,
            "rationale": "Languages used to implement server-side business logic, request handlers, workers, and service integrations. This is the core coding surface for backend feature delivery and maintenance.",
            "slug": "programming-languages-for-backend-systems",
            "source": "db"
          },
          "input_skill": "Python",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Backend Engineer",
              "id": 14,
              "rationale": null,
              "role_archetype": null,
              "slug": "backend-engineer",
              "source": "db"
            }
          ]
        },
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Programming Languages for Data Work",
            "id": 67,
            "rationale": "Languages used to implement data pipelines, transformations, and operational utilities. This is the code layer for expressing extraction, parsing, validation, and orchestration logic in data engineering workflows.",
            "slug": "programming-languages-for-data-work",
            "source": "db"
          },
          "input_skill": "Python",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Data Engineer",
              "id": 6,
              "rationale": null,
              "role_archetype": null,
              "slug": "data-engineer",
              "source": "db"
            }
          ]
        },
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Programming Languages for ML Systems",
            "id": 113,
            "rationale": "Languages used to implement model integration code, inference services, and feature-processing logic. This is the core coding surface for turning trained models into product-facing software components.",
            "slug": "programming-languages-for-ml-systems",
            "source": "db"
          },
          "input_skill": "Python",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Machine Learning Engineer",
              "id": 10,
              "rationale": null,
              "role_archetype": null,
              "slug": "machine-learning-engineer",
              "source": "db"
            }
          ]
        },
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Programming Languages for Security Work",
            "id": 328,
            "rationale": "Languages used to automate security tasks, write detection logic, and build analysis or remediation tooling. This is the core coding surface for a cybersecurity engineer across scripts, queries, and small utilities.",
            "slug": "programming-languages-for-security-work",
            "source": "db"
          },
          "input_skill": "Python",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Cybersecurity Engineer",
              "id": 9,
              "rationale": null,
              "role_archetype": null,
              "slug": "cybersecurity-engineer",
              "source": "db"
            }
          ]
        },
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Programming Languages for Test Automation",
            "id": 193,
            "rationale": "Languages used to implement automated checks, helper utilities, and test harness code. This is the core coding surface for turning test ideas into maintainable automation.",
            "slug": "programming-languages-for-test-automation",
            "source": "db"
          },
          "input_skill": "Python",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Automation Tester",
              "id": 16,
              "rationale": null,
              "role_archetype": null,
              "slug": "automation-tester",
              "source": "db"
            }
          ]
        },
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Security Automation and Scripting",
            "id": 258,
            "rationale": "Automating repeatable security checks, enrichment, and remediation workflows. This cluster is coherent because the role often needs lightweight automation to scale analysis and response.",
            "slug": "security-automation-and-scripting",
            "source": "db"
          },
          "input_skill": "Python",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Cybersecurity Engineer",
              "id": 9,
              "rationale": null,
              "role_archetype": null,
              "slug": "cybersecurity-engineer",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "Python",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "TensorFlow",
          "alias_type": "CANONICAL",
          "id": 862,
          "is_primary": true,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "TF1",
          "alias_type": "VERSION",
          "id": 863,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "TF2",
          "alias_type": "VERSION",
          "id": 864,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "TensorFlow 1",
          "alias_type": "VERSION",
          "id": 865,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "TensorFlow 1.x",
          "alias_type": "VERSION",
          "id": 867,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "TensorFlow 2",
          "alias_type": "VERSION",
          "id": 866,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "TensorFlow 2.x",
          "alias_type": "VERSION",
          "id": 868,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 6,
        "display_name": "TensorFlow",
        "id": 558,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "LIBRARY",
        "slug": "tensorflow",
        "sub_category_id": 456,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Applied Machine Learning Toolkits",
            "id": 94,
            "rationale": "Libraries and frameworks used to prototype and compare models quickly. This dimension captures the concrete tooling layer beneath modeling methods and evaluation.",
            "slug": "applied-machine-learning-toolkits",
            "source": "db"
          },
          "input_skill": "TensorFlow",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Data Scientist",
              "id": 7,
              "rationale": null,
              "role_archetype": null,
              "slug": "data-scientist",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "TensorFlow",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "PyTorch",
          "alias_type": "CANONICAL",
          "id": 861,
          "is_primary": true,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 6,
        "display_name": "PyTorch",
        "id": 557,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "LIBRARY",
        "slug": "pytorch",
        "sub_category_id": 456,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Applied Machine Learning Toolkits",
            "id": 94,
            "rationale": "Libraries and frameworks used to prototype and compare models quickly. This dimension captures the concrete tooling layer beneath modeling methods and evaluation.",
            "slug": "applied-machine-learning-toolkits",
            "source": "db"
          },
          "input_skill": "PyTorch",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Data Scientist",
              "id": 7,
              "rationale": null,
              "role_archetype": null,
              "slug": "data-scientist",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "PyTorch",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "scikit-learn",
          "alias_type": "CANONICAL",
          "id": 852,
          "is_primary": true,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 6,
        "display_name": "scikit-learn",
        "id": 554,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "LIBRARY",
        "slug": "scikit-learn",
        "sub_category_id": 458,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Applied Machine Learning Toolkits",
            "id": 94,
            "rationale": "Libraries and frameworks used to prototype and compare models quickly. This dimension captures the concrete tooling layer beneath modeling methods and evaluation.",
            "slug": "applied-machine-learning-toolkits",
            "source": "db"
          },
          "input_skill": "Scikit-learn",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Data Scientist",
              "id": 7,
              "rationale": null,
              "role_archetype": null,
              "slug": "data-scientist",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "Scikit-learn",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "GitHub Actions",
          "alias_type": "CANONICAL",
          "id": 1800,
          "is_primary": true,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 14,
        "display_name": "GitHub Actions",
        "id": 1250,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "CLOUD_SERVICE",
        "slug": "github-actions",
        "sub_category_id": 1019,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Continuous Integration Test Integration",
            "id": 207,
            "rationale": "Integrating automated checks into shared build and merge workflows so results are repeatable and visible. This cluster is coherent because automation testers commonly configure test execution triggers, artifacts, and reporting hooks.",
            "slug": "continuous-integration-test-integration",
            "source": "db"
          },
          "input_skill": "GitHub Actions",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Automation Tester",
              "id": 16,
              "rationale": null,
              "role_archetype": null,
              "slug": "automation-tester",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "GitHub Actions",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "Airflow",
          "alias_type": "CANONICAL",
          "id": 540,
          "is_primary": true,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 11,
        "display_name": "Airflow",
        "id": 325,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "TOOL",
        "slug": "airflow",
        "sub_category_id": 335,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Workflow Orchestration Systems",
            "id": 64,
            "rationale": "Operational orchestration of ML jobs, dependencies, and handoffs across training, validation, deployment, and retraining. This is a useful split from training pipelines because it emphasizes the scheduler and control plane.",
            "slug": "workflow-orchestration-systems",
            "source": "db"
          },
          "input_skill": "Airflow",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Data Engineer",
              "id": 6,
              "rationale": null,
              "role_archetype": null,
              "slug": "data-engineer",
              "source": "db"
            },
            {
              "display_name": "MLOps Engineer",
              "id": 5,
              "rationale": null,
              "role_archetype": null,
              "slug": "mlops-engineer",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "Airflow",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "Terraform",
          "alias_type": "CANONICAL",
          "id": 290,
          "is_primary": true,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 11,
        "display_name": "Terraform",
        "id": 144,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "TOOL",
        "slug": "terraform",
        "sub_category_id": 171,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Infrastructure Provisioning Templates",
            "id": 291,
            "rationale": "Declarative templates and modules used to create repeatable cloud resources and environments. This cluster covers the infrastructure definitions the role applies, reviews, and updates to keep environments consistent.",
            "slug": "infrastructure-provisioning-templates",
            "source": "db"
          },
          "input_skill": "Terraform",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Cloud Engineer",
              "id": 18,
              "rationale": null,
              "role_archetype": null,
              "slug": "cloud-engineer",
              "source": "db"
            }
          ]
        },
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Infrastructure as Code",
            "id": 22,
            "rationale": "Defines infrastructure and platform resources through versioned code so environments are repeatable and reviewable. This is a coherent cluster because it underpins environment consistency and change control.",
            "slug": "infrastructure-as-code",
            "source": "db"
          },
          "input_skill": "Terraform",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "DevOps Engineer",
              "id": 1,
              "rationale": null,
              "role_archetype": "A DevOps Engineer enables reliable, repeatable delivery of software by designing and operating the processes that connect development and production. They focus on improving deployment flow, operational stability, and collaboration between teams through automation, standardization, and monitoring of delivery and runtime practices.",
              "slug": "devops-engineer",
              "source": "db"
            }
          ]
        },
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Infrastructure as Code and Declarative Provisioning",
            "id": 36,
            "rationale": "Defines cloud and platform infrastructure declaratively through versioned code so environments are repeatable, reviewable, and automatable. This includes authoring and maintaining IaC templates/modules, managing parameters and state, and using plan/apply workflows to provision and update resources across Azure and other cloud platforms.",
            "slug": "infrastructure-as-code-and-declarative-provisioning",
            "source": "db"
          },
          "input_skill": "Terraform",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Azure Cloud Engineer",
              "id": 4,
              "rationale": null,
              "role_archetype": null,
              "slug": "azure-cloud-engineer",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "Terraform",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "Docker",
          "alias_type": "CANONICAL",
          "id": 299,
          "is_primary": true,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 11,
        "display_name": "Docker",
        "id": 153,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "TOOL",
        "slug": "docker",
        "sub_category_id": 170,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Containerization and Image Delivery",
            "id": 24,
            "rationale": "Builds, packages, and ships application and support workloads as container images. This cluster covers the artifact format and the mechanics of producing deployable images.",
            "slug": "containerization-and-image-delivery",
            "source": "db"
          },
          "input_skill": "Docker",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "DevOps Engineer",
              "id": 1,
              "rationale": null,
              "role_archetype": "A DevOps Engineer enables reliable, repeatable delivery of software by designing and operating the processes that connect development and production. They focus on improving deployment flow, operational stability, and collaboration between teams through automation, standardization, and monitoring of delivery and runtime practices.",
              "slug": "devops-engineer",
              "source": "db"
            }
          ]
        },
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Model Serving Deployment and Runtime Packaging",
            "id": 52,
            "rationale": "Operational deployment of trained models into online, batch, or streaming serving environments, including packaging models and model servers into containers or managed inference runtimes, coordinating rollout, and handing off to inference systems. Covers serving frameworks and platforms such as TensorFlow Serving, TorchServe, Triton Inference Server, BentoML, KServe, and Seldon Core, plus container/runtime concerns like Docker images, GPU-enabled containers, base image selection, container entrypoints, runtime dependencies, and image scanning for model services.",
            "slug": "model-serving-deployment-and-runtime-packaging",
            "source": "db"
          },
          "input_skill": "Docker",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "MLOps Engineer",
              "id": 5,
              "rationale": null,
              "role_archetype": null,
              "slug": "mlops-engineer",
              "source": "db"
            },
            {
              "display_name": "Machine Learning Engineer",
              "id": 10,
              "rationale": null,
              "role_archetype": null,
              "slug": "machine-learning-engineer",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "Docker",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "Kubernetes",
          "alias_type": "CANONICAL",
          "id": 304,
          "is_primary": true,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.0",
          "alias_type": "VERSION",
          "id": 307,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.0+",
          "alias_type": "VERSION",
          "id": 2366,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.1",
          "alias_type": "VERSION",
          "id": 308,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.10",
          "alias_type": "VERSION",
          "id": 318,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.11",
          "alias_type": "VERSION",
          "id": 319,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.12",
          "alias_type": "VERSION",
          "id": 320,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.13",
          "alias_type": "VERSION",
          "id": 321,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.14",
          "alias_type": "VERSION",
          "id": 322,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.15",
          "alias_type": "VERSION",
          "id": 323,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.16",
          "alias_type": "VERSION",
          "id": 324,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.17",
          "alias_type": "VERSION",
          "id": 325,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.18",
          "alias_type": "VERSION",
          "id": 326,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.19",
          "alias_type": "VERSION",
          "id": 327,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.2",
          "alias_type": "VERSION",
          "id": 309,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.20",
          "alias_type": "VERSION",
          "id": 328,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.21",
          "alias_type": "VERSION",
          "id": 329,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.22",
          "alias_type": "VERSION",
          "id": 330,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.23",
          "alias_type": "VERSION",
          "id": 331,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.24",
          "alias_type": "VERSION",
          "id": 332,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.25",
          "alias_type": "VERSION",
          "id": 333,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.26",
          "alias_type": "VERSION",
          "id": 334,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.27",
          "alias_type": "VERSION",
          "id": 335,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.28",
          "alias_type": "VERSION",
          "id": 336,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.29",
          "alias_type": "VERSION",
          "id": 337,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.3",
          "alias_type": "VERSION",
          "id": 310,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.30",
          "alias_type": "VERSION",
          "id": 338,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.4",
          "alias_type": "VERSION",
          "id": 311,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.5",
          "alias_type": "VERSION",
          "id": 312,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.6",
          "alias_type": "VERSION",
          "id": 313,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.7",
          "alias_type": "VERSION",
          "id": 314,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.8",
          "alias_type": "VERSION",
          "id": 315,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.9",
          "alias_type": "VERSION",
          "id": 316,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes 1.x",
          "alias_type": "VERSION",
          "id": 317,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "Kubernetes v1",
          "alias_type": "VERSION",
          "id": 306,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        },
        {
          "alias_text": "k8s",
          "alias_type": "VERSION",
          "id": 305,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 13,
        "display_name": "Kubernetes",
        "id": 158,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "PLATFORM",
        "slug": "kubernetes",
        "sub_category_id": 1524,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Orchestration Platforms",
            "id": 25,
            "rationale": "Operates the platforms that schedule and run containerized workloads and related deployment primitives. This is separate from image delivery because it concerns runtime placement and service rollout behavior.",
            "slug": "orchestration-platforms",
            "source": "db"
          },
          "input_skill": "Kubernetes",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Cloud Engineer",
              "id": 18,
              "rationale": null,
              "role_archetype": null,
              "slug": "cloud-engineer",
              "source": "db"
            },
            {
              "display_name": "DevOps Engineer",
              "id": 1,
              "rationale": null,
              "role_archetype": "A DevOps Engineer enables reliable, repeatable delivery of software by designing and operating the processes that connect development and production. They focus on improving deployment flow, operational stability, and collaboration between teams through automation, standardization, and monitoring of delivery and runtime practices.",
              "slug": "devops-engineer",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "Kubernetes",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "Pinecone",
          "alias_type": "CANONICAL",
          "id": 3418,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 13,
        "display_name": "Pinecone",
        "id": 2621,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "PLATFORM",
        "slug": "pinecone",
        "sub_category_id": 2138,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Cloud Model Runtime Services",
            "id": 121,
            "rationale": "Consumer-level use of cloud services that host or support model inference applications. This cluster is coherent because MLEs often deploy and tune services on managed cloud compute, networking, and storage primitives.",
            "slug": "cloud-model-runtime-services",
            "source": "db"
          },
          "input_skill": "Pinecone",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Machine Learning Engineer",
              "id": 10,
              "rationale": null,
              "role_archetype": null,
              "slug": "machine-learning-engineer",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "Pinecone",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "OpenSearch",
          "alias_type": "CANONICAL",
          "id": 3419,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 12,
        "display_name": "OpenSearch",
        "id": 2622,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "TOOL",
        "slug": "opensearch",
        "sub_category_id": 2139,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Cloud Data Platform Services",
            "id": 81,
            "rationale": "Consumer-level use of cloud services that support data engineering workloads. This includes managed compute, storage, networking-adjacent services, and security primitives used to run pipelines and data platforms.",
            "slug": "cloud-data-platform-services",
            "source": "db"
          },
          "input_skill": "OpenSearch",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Data Engineer",
              "id": 6,
              "rationale": null,
              "role_archetype": null,
              "slug": "data-engineer",
              "source": "db"
            }
          ]
        },
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Version Control Systems",
            "id": 365,
            "rationale": "Tools and workflows for tracking source changes, branching, merging, and collaborating on code history. Git belongs here because it is the canonical distributed version control system used to manage revisions and coordinate team development.",
            "slug": "d_init_01",
            "source": "db"
          },
          "input_skill": "OpenSearch",
          "llm_role": null,
          "roles_from_db": []
        }
      ],
      "input_skill": "OpenSearch",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "FAISS",
          "alias_type": "CANONICAL",
          "id": 3420,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 6,
        "display_name": "FAISS",
        "id": 2623,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "LIBRARY",
        "slug": "faiss",
        "sub_category_id": 2140,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Applied Machine Learning Toolkits",
            "id": 94,
            "rationale": "Libraries and frameworks used to prototype and compare models quickly. This dimension captures the concrete tooling layer beneath modeling methods and evaluation.",
            "slug": "applied-machine-learning-toolkits",
            "source": "db"
          },
          "input_skill": "FAISS",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Data Scientist",
              "id": 7,
              "rationale": null,
              "role_archetype": null,
              "slug": "data-scientist",
              "source": "db"
            }
          ]
        },
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Version Control Systems",
            "id": 365,
            "rationale": "Tools and workflows for tracking source changes, branching, merging, and collaborating on code history. Git belongs here because it is the canonical distributed version control system used to manage revisions and coordinate team development.",
            "slug": "d_init_01",
            "source": "db"
          },
          "input_skill": "FAISS",
          "llm_role": null,
          "roles_from_db": []
        }
      ],
      "input_skill": "FAISS",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    }
  ],
  "unmatched_skills": []
}

{
  "chosen_role": {
    "display_name": "MLOps Engineer",
    "id": 5,
    "rationale": "The primary skills indicate a strong focus on AWS and AI/ML technologies, which align well with the responsibilities of an MLOps Engineer.",
    "role_archetype": null,
    "slug": "mlops-engineer",
    "source": "db"
  },
  "chosen_role_resolution": "in_db",
  "final_input_skills": [
    {
      "skill": "AWS",
      "tag": "in_db"
    },
    {
      "skill": "AI/ML",
      "tag": "in_db"
    },
    {
      "skill": "Amazon SageMaker",
      "tag": "in_db"
    },
    {
      "skill": "Amazon Bedrock",
      "tag": "in_db"
    },
    {
      "skill": "AWS Lambda",
      "tag": "in_db"
    },
    {
      "skill": "ECS",
      "tag": "in_db"
    },
    {
      "skill": "EKS",
      "tag": "in_db"
    },
    {
      "skill": "EC2",
      "tag": "in_db"
    },
    {
      "skill": "AWS Glue",
      "tag": "in_db"
    },
    {
      "skill": "Amazon Athena",
      "tag": "in_db"
    },
    {
      "skill": "Redshift",
      "tag": "in_db"
    },
    {
      "skill": "AWS Data Pipeline",
      "tag": "in_db"
    },
    {
      "skill": "S3",
      "tag": "in_db"
    },
    {
      "skill": "Kinesis",
      "tag": "in_db"
    },
    {
      "skill": "Amazon API Gateway",
      "tag": "in_db"
    },
    {
      "skill": "Python",
      "tag": "in_db"
    },
    {
      "skill": "TensorFlow",
      "tag": "in_db"
    },
    {
      "skill": "PyTorch",
      "tag": "in_db"
    },
    {
      "skill": "Scikit-learn",
      "tag": "in_db"
    },
    {
      "skill": "GitHub Actions",
      "tag": "in_db"
    },
    {
      "skill": "Airflow",
      "tag": "in_db"
    },
    {
      "skill": "Terraform",
      "tag": "in_db"
    },
    {
      "skill": "Docker",
      "tag": "in_db"
    },
    {
      "skill": "Kubernetes",
      "tag": "in_db"
    },
    {
      "skill": "Pinecone",
      "tag": "in_db"
    },
    {
      "skill": "OpenSearch",
      "tag": "in_db"
    },
    {
      "skill": "FAISS",
      "tag": "in_db"
    }
  ],
  "persistence": {
    "items": [
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Cloud Platform Operations",
          "id": 26,
          "rationale": "Uses cloud provider services to support delivery and runtime environments. The focus is on consumer-level operation of cloud services rather than deep cloud architecture ownership.",
          "slug": "cloud-platform-operations",
          "source": "db"
        },
        "dimension_id": 26,
        "input_skill": "AWS",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "DevOps Engineer",
            "id": 1,
            "rationale": null,
            "role_archetype": "A DevOps Engineer enables reliable, repeatable delivery of software by designing and operating the processes that connect development and production. They focus on improving deployment flow, operational stability, and collaboration between teams through automation, standardization, and monitoring of delivery and runtime practices.",
            "slug": "devops-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 163,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Cloud Security Platforms",
          "id": 332,
          "rationale": "Cloud-native security products used to assess posture, detect misconfigurations, and monitor workloads across AWS, Azure, and GCP. This is a distinct product family because the role often works across multiple CNAPP/CSPM/CWPP offerings and cloud-native detectors.",
          "slug": "cloud-security-platforms",
          "source": "db"
        },
        "dimension_id": 332,
        "input_skill": "AWS",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Cybersecurity Engineer",
            "id": 9,
            "rationale": null,
            "role_archetype": null,
            "slug": "cybersecurity-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 163,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "AI Inference Cost, Latency, and Throughput Optimization",
          "id": 260,
          "rationale": "Improving the speed, throughput, and cost efficiency of AI and ML-powered product features without sacrificing correctness or user experience. Includes token budgeting, prompt compression, batching, caching, model selection, quantization, pruning, async inference, warm starts, streaming UX, timeout tuning, concurrency control, and profiling. Excludes infrastructure autoscaling, model serving capacity planning, generic backend performance tuning, and unrelated data/warehouse optimization.",
          "slug": "ai-inference-cost-latency-and-throughput-optimization",
          "source": "db"
        },
        "dimension_id": 260,
        "input_skill": "AI/ML",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "AI Engineer",
            "id": 12,
            "rationale": null,
            "role_archetype": null,
            "slug": "ai-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 2611,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "AI Service Architecture Patterns",
          "id": 270,
          "rationale": "Structuring AI capabilities within the product and service landscape. This includes deciding whether AI logic lives in handlers, workers, gateways, or dedicated orchestration services.",
          "slug": "ai-service-architecture-patterns",
          "source": "db"
        },
        "dimension_id": 270,
        "input_skill": "AI/ML",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "AI Engineer",
            "id": 12,
            "rationale": null,
            "role_archetype": null,
            "slug": "ai-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 2611,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Applied Machine Learning Toolkits",
          "id": 94,
          "rationale": "Libraries and frameworks used to prototype and compare models quickly. This dimension captures the concrete tooling layer beneath modeling methods and evaluation.",
          "slug": "applied-machine-learning-toolkits",
          "source": "db"
        },
        "dimension_id": 94,
        "input_skill": "AI/ML",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Data Scientist",
            "id": 7,
            "rationale": null,
            "role_archetype": null,
            "slug": "data-scientist",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 2611,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Managed ML Platform Workflows",
          "id": 367,
          "rationale": "Cloud ML platforms for building and operating models end-to-end, including notebooks, experiments, managed training jobs, and pipeline/studio workflows. Examples: SageMaker Studio, SageMaker notebooks, SageMaker Pipelines, managed training jobs.",
          "slug": "d_split_01_01",
          "source": "db"
        },
        "dimension_id": 367,
        "input_skill": "Amazon SageMaker",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [],
        "skill_dimension_saved": true,
        "skill_id": 2612,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Managed Model Hosting and Endpoints",
          "id": 368,
          "rationale": "Cloud-managed services for deploying trained models as online or batch inference endpoints, including endpoint provisioning, batch transform, and rollout coordination. Examples: SageMaker endpoints, SageMaker batch transform.",
          "slug": "d_split_01_02",
          "source": "db"
        },
        "dimension_id": 368,
        "input_skill": "Amazon SageMaker",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [],
        "skill_dimension_saved": true,
        "skill_id": 2612,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Model Serving Deployment and Runtime Packaging",
          "id": 52,
          "rationale": "Operational deployment of trained models into online, batch, or streaming serving environments, including packaging models and model servers into containers or managed inference runtimes, coordinating rollout, and handing off to inference systems. Covers serving frameworks and platforms such as TensorFlow Serving, TorchServe, Triton Inference Server, BentoML, KServe, and Seldon Core, plus container/runtime concerns like Docker images, GPU-enabled containers, base image selection, container entrypoints, runtime dependencies, and image scanning for model services.",
          "slug": "model-serving-deployment-and-runtime-packaging",
          "source": "db"
        },
        "dimension_id": 52,
        "input_skill": "Amazon SageMaker",
        "llm_role": null,
        "matched_chosen_role": true,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension saved",
        "role_dimension_saved": true,
        "roles_from_db": [
          {
            "display_name": "MLOps Engineer",
            "id": 5,
            "rationale": null,
            "role_archetype": null,
            "slug": "mlops-engineer",
            "source": "db"
          },
          {
            "display_name": "Machine Learning Engineer",
            "id": 10,
            "rationale": null,
            "role_archetype": null,
            "slug": "machine-learning-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 2612,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Cloud Model Runtime Services",
          "id": 121,
          "rationale": "Consumer-level use of cloud services that host or support model inference applications. This cluster is coherent because MLEs often deploy and tune services on managed cloud compute, networking, and storage primitives.",
          "slug": "cloud-model-runtime-services",
          "source": "db"
        },
        "dimension_id": 121,
        "input_skill": "Amazon Bedrock",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Machine Learning Engineer",
            "id": 10,
            "rationale": null,
            "role_archetype": null,
            "slug": "machine-learning-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 2613,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Cloud Data Platform Services",
          "id": 81,
          "rationale": "Consumer-level use of cloud services that support data engineering workloads. This includes managed compute, storage, networking-adjacent services, and security primitives used to run pipelines and data platforms.",
          "slug": "cloud-data-platform-services",
          "source": "db"
        },
        "dimension_id": 81,
        "input_skill": "AWS Lambda",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Data Engineer",
            "id": 6,
            "rationale": null,
            "role_archetype": null,
            "slug": "data-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 2614,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Version Control Systems",
          "id": 365,
          "rationale": "Tools and workflows for tracking source changes, branching, merging, and collaborating on code history. Git belongs here because it is the canonical distributed version control system used to manage revisions and coordinate team development.",
          "slug": "d_init_01",
          "source": "db"
        },
        "dimension_id": 365,
        "input_skill": "ECS",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [],
        "skill_dimension_saved": true,
        "skill_id": 2615,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Cloud Model Runtime Services",
          "id": 121,
          "rationale": "Consumer-level use of cloud services that host or support model inference applications. This cluster is coherent because MLEs often deploy and tune services on managed cloud compute, networking, and storage primitives.",
          "slug": "cloud-model-runtime-services",
          "source": "db"
        },
        "dimension_id": 121,
        "input_skill": "EKS",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Machine Learning Engineer",
            "id": 10,
            "rationale": null,
            "role_archetype": null,
            "slug": "machine-learning-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 725,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Orchestration Platforms",
          "id": 25,
          "rationale": "Operates the platforms that schedule and run containerized workloads and related deployment primitives. This is separate from image delivery because it concerns runtime placement and service rollout behavior.",
          "slug": "orchestration-platforms",
          "source": "db"
        },
        "dimension_id": 25,
        "input_skill": "EKS",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Cloud Engineer",
            "id": 18,
            "rationale": null,
            "role_archetype": null,
            "slug": "cloud-engineer",
            "source": "db"
          },
          {
            "display_name": "DevOps Engineer",
            "id": 1,
            "rationale": null,
            "role_archetype": "A DevOps Engineer enables reliable, repeatable delivery of software by designing and operating the processes that connect development and production. They focus on improving deployment flow, operational stability, and collaboration between teams through automation, standardization, and monitoring of delivery and runtime practices.",
            "slug": "devops-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 725,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Cloud Provider Core Services",
          "id": 290,
          "rationale": "Core managed services used to provision and operate cloud environments. This is the base cloud surface for compute, storage, networking, and platform primitives the role configures and maintains.",
          "slug": "cloud-provider-core-services",
          "source": "db"
        },
        "dimension_id": 290,
        "input_skill": "EC2",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Cloud Engineer",
            "id": 18,
            "rationale": null,
            "role_archetype": null,
            "slug": "cloud-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 1773,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Cloud Data Platform Services",
          "id": 81,
          "rationale": "Consumer-level use of cloud services that support data engineering workloads. This includes managed compute, storage, networking-adjacent services, and security primitives used to run pipelines and data platforms.",
          "slug": "cloud-data-platform-services",
          "source": "db"
        },
        "dimension_id": 81,
        "input_skill": "AWS Glue",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Data Engineer",
            "id": 6,
            "rationale": null,
            "role_archetype": null,
            "slug": "data-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 466,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Cloud Data Platform Security and Networking",
          "id": 369,
          "rationale": "Identity, access, secrets, and networking primitives used to support cloud data platforms and pipelines.",
          "slug": "d_split_01_04",
          "source": "db"
        },
        "dimension_id": 369,
        "input_skill": "Amazon Athena",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [],
        "skill_dimension_saved": true,
        "skill_id": 2616,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Cloud Data Platform Services",
          "id": 81,
          "rationale": "Consumer-level use of cloud services that support data engineering workloads. This includes managed compute, storage, networking-adjacent services, and security primitives used to run pipelines and data platforms.",
          "slug": "cloud-data-platform-services",
          "source": "db"
        },
        "dimension_id": 81,
        "input_skill": "Amazon Athena",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Data Engineer",
            "id": 6,
            "rationale": null,
            "role_archetype": null,
            "slug": "data-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 2616,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Managed ML Platform Workflows",
          "id": 367,
          "rationale": "Cloud ML platforms for building and operating models end-to-end, including notebooks, experiments, managed training jobs, and pipeline/studio workflows. Examples: SageMaker Studio, SageMaker notebooks, SageMaker Pipelines, managed training jobs.",
          "slug": "d_split_01_01",
          "source": "db"
        },
        "dimension_id": 367,
        "input_skill": "Amazon Athena",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [],
        "skill_dimension_saved": true,
        "skill_id": 2616,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Data Warehousing Platforms",
          "id": 72,
          "rationale": "Cloud and on-prem analytical storage systems used to persist curated datasets and serve downstream consumers. This cluster is about the warehouse/lakehouse layer where transformed data is organized for access.",
          "slug": "data-warehousing-platforms",
          "source": "db"
        },
        "dimension_id": 72,
        "input_skill": "Redshift",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Data Engineer",
            "id": 6,
            "rationale": null,
            "role_archetype": null,
            "slug": "data-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 2570,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Cloud Data Platform Services",
          "id": 81,
          "rationale": "Consumer-level use of cloud services that support data engineering workloads. This includes managed compute, storage, networking-adjacent services, and security primitives used to run pipelines and data platforms.",
          "slug": "cloud-data-platform-services",
          "source": "db"
        },
        "dimension_id": 81,
        "input_skill": "AWS Data Pipeline",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Data Engineer",
            "id": 6,
            "rationale": null,
            "role_archetype": null,
            "slug": "data-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 2617,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Storage Provisioning and Automation",
          "id": 311,
          "rationale": "Covers the scripts, APIs, and operational workflows used to create, resize, map, and retire storage resources. This cluster is coherent because storage engineers often automate repetitive provisioning and maintenance tasks.",
          "slug": "storage-provisioning-and-automation",
          "source": "db"
        },
        "dimension_id": 311,
        "input_skill": "S3",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Storage Engineer",
            "id": 22,
            "rationale": null,
            "role_archetype": null,
            "slug": "storage-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 2618,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Streaming Data Processing",
          "id": 69,
          "rationale": "Tools and patterns for ingesting and transforming event streams with low latency. This cluster covers continuous processing, windowing, and stateful stream jobs used to keep data fresh.",
          "slug": "streaming-data-processing",
          "source": "db"
        },
        "dimension_id": 69,
        "input_skill": "Kinesis",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Data Engineer",
            "id": 6,
            "rationale": null,
            "role_archetype": null,
            "slug": "data-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 2619,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Web Service Frameworks",
          "id": 141,
          "rationale": "Server frameworks used to build HTTP APIs, route requests, validate inputs, and structure backend application code. This cluster is coherent because it defines how backend services expose behavior to clients and other services.",
          "slug": "web-service-frameworks",
          "source": "db"
        },
        "dimension_id": 141,
        "input_skill": "Amazon API Gateway",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Backend Engineer",
            "id": 14,
            "rationale": null,
            "role_archetype": null,
            "slug": "backend-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 2620,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Analytical Programming Languages",
          "id": 82,
          "rationale": "Languages used to clean, transform, analyze, and prototype models in notebooks and scripts. This is the core coding surface for expressing statistical logic and data manipulation in a reproducible way.",
          "slug": "analytical-programming-languages",
          "source": "db"
        },
        "dimension_id": 82,
        "input_skill": "Python",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Data Analyst",
            "id": 20,
            "rationale": null,
            "role_archetype": null,
            "slug": "data-analyst",
            "source": "db"
          },
          {
            "display_name": "Data Scientist",
            "id": 7,
            "rationale": null,
            "role_archetype": null,
            "slug": "data-scientist",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 393,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Automation Scripting and CLI",
          "id": 48,
          "rationale": "Uses scripts and command-line tooling to execute repeatable Azure operations and reduce manual work. This is a practical cluster because the role frequently automates provisioning, checks, and remediation tasks.",
          "slug": "automation-scripting-and-cli",
          "source": "db"
        },
        "dimension_id": 48,
        "input_skill": "Python",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Azure Cloud Engineer",
            "id": 4,
            "rationale": null,
            "role_archetype": null,
            "slug": "azure-cloud-engineer",
            "source": "db"
          },
          {
            "display_name": "Cloud Engineer",
            "id": 18,
            "rationale": null,
            "role_archetype": null,
            "slug": "cloud-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 393,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Automation and Scripting for Operations",
          "id": 361,
          "rationale": "Scripts and lightweight automation used to execute repetitive virtualization tasks and enforce operational consistency. This is the practical glue that reduces manual host and VM administration.",
          "slug": "automation-and-scripting-for-operations",
          "source": "db"
        },
        "dimension_id": 361,
        "input_skill": "Python",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Virtualization Engineer",
            "id": 26,
            "rationale": null,
            "role_archetype": null,
            "slug": "virtualization-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 393,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Network Automation and Scripting",
          "id": 285,
          "rationale": "Covers scripts and automation used to configure, validate, and audit network devices and services. This cluster is coherent because repeatable network operations increasingly depend on programmatic changes and checks.",
          "slug": "network-automation-and-scripting",
          "source": "db"
        },
        "dimension_id": 285,
        "input_skill": "Python",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Network Engineer",
            "id": 21,
            "rationale": null,
            "role_archetype": null,
            "slug": "network-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 393,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Programming Languages for AI Workflows",
          "id": 261,
          "rationale": "Languages used to implement AI feature logic, orchestration, and response handling inside product code. This is the core coding surface for turning prompts and model calls into reliable application behavior.",
          "slug": "programming-languages-for-ai-workflows",
          "source": "db"
        },
        "dimension_id": 261,
        "input_skill": "Python",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "AI Engineer",
            "id": 12,
            "rationale": null,
            "role_archetype": null,
            "slug": "ai-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 393,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Programming Languages for Backend Systems",
          "id": 140,
          "rationale": "Languages used to implement server-side business logic, request handlers, workers, and service integrations. This is the core coding surface for backend feature delivery and maintenance.",
          "slug": "programming-languages-for-backend-systems",
          "source": "db"
        },
        "dimension_id": 140,
        "input_skill": "Python",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Backend Engineer",
            "id": 14,
            "rationale": null,
            "role_archetype": null,
            "slug": "backend-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 393,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Programming Languages for Data Work",
          "id": 67,
          "rationale": "Languages used to implement data pipelines, transformations, and operational utilities. This is the code layer for expressing extraction, parsing, validation, and orchestration logic in data engineering workflows.",
          "slug": "programming-languages-for-data-work",
          "source": "db"
        },
        "dimension_id": 67,
        "input_skill": "Python",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Data Engineer",
            "id": 6,
            "rationale": null,
            "role_archetype": null,
            "slug": "data-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 393,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Programming Languages for ML Systems",
          "id": 113,
          "rationale": "Languages used to implement model integration code, inference services, and feature-processing logic. This is the core coding surface for turning trained models into product-facing software components.",
          "slug": "programming-languages-for-ml-systems",
          "source": "db"
        },
        "dimension_id": 113,
        "input_skill": "Python",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Machine Learning Engineer",
            "id": 10,
            "rationale": null,
            "role_archetype": null,
            "slug": "machine-learning-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 393,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Programming Languages for Security Work",
          "id": 328,
          "rationale": "Languages used to automate security tasks, write detection logic, and build analysis or remediation tooling. This is the core coding surface for a cybersecurity engineer across scripts, queries, and small utilities.",
          "slug": "programming-languages-for-security-work",
          "source": "db"
        },
        "dimension_id": 328,
        "input_skill": "Python",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Cybersecurity Engineer",
            "id": 9,
            "rationale": null,
            "role_archetype": null,
            "slug": "cybersecurity-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 393,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Programming Languages for Test Automation",
          "id": 193,
          "rationale": "Languages used to implement automated checks, helper utilities, and test harness code. This is the core coding surface for turning test ideas into maintainable automation.",
          "slug": "programming-languages-for-test-automation",
          "source": "db"
        },
        "dimension_id": 193,
        "input_skill": "Python",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Automation Tester",
            "id": 16,
            "rationale": null,
            "role_archetype": null,
            "slug": "automation-tester",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 393,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Security Automation and Scripting",
          "id": 258,
          "rationale": "Automating repeatable security checks, enrichment, and remediation workflows. This cluster is coherent because the role often needs lightweight automation to scale analysis and response.",
          "slug": "security-automation-and-scripting",
          "source": "db"
        },
        "dimension_id": 258,
        "input_skill": "Python",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Cybersecurity Engineer",
            "id": 9,
            "rationale": null,
            "role_archetype": null,
            "slug": "cybersecurity-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 393,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Applied Machine Learning Toolkits",
          "id": 94,
          "rationale": "Libraries and frameworks used to prototype and compare models quickly. This dimension captures the concrete tooling layer beneath modeling methods and evaluation.",
          "slug": "applied-machine-learning-toolkits",
          "source": "db"
        },
        "dimension_id": 94,
        "input_skill": "TensorFlow",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Data Scientist",
            "id": 7,
            "rationale": null,
            "role_archetype": null,
            "slug": "data-scientist",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 558,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Applied Machine Learning Toolkits",
          "id": 94,
          "rationale": "Libraries and frameworks used to prototype and compare models quickly. This dimension captures the concrete tooling layer beneath modeling methods and evaluation.",
          "slug": "applied-machine-learning-toolkits",
          "source": "db"
        },
        "dimension_id": 94,
        "input_skill": "PyTorch",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Data Scientist",
            "id": 7,
            "rationale": null,
            "role_archetype": null,
            "slug": "data-scientist",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 557,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Applied Machine Learning Toolkits",
          "id": 94,
          "rationale": "Libraries and frameworks used to prototype and compare models quickly. This dimension captures the concrete tooling layer beneath modeling methods and evaluation.",
          "slug": "applied-machine-learning-toolkits",
          "source": "db"
        },
        "dimension_id": 94,
        "input_skill": "Scikit-learn",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Data Scientist",
            "id": 7,
            "rationale": null,
            "role_archetype": null,
            "slug": "data-scientist",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 554,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Continuous Integration Test Integration",
          "id": 207,
          "rationale": "Integrating automated checks into shared build and merge workflows so results are repeatable and visible. This cluster is coherent because automation testers commonly configure test execution triggers, artifacts, and reporting hooks.",
          "slug": "continuous-integration-test-integration",
          "source": "db"
        },
        "dimension_id": 207,
        "input_skill": "GitHub Actions",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Automation Tester",
            "id": 16,
            "rationale": null,
            "role_archetype": null,
            "slug": "automation-tester",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 1250,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Workflow Orchestration Systems",
          "id": 64,
          "rationale": "Operational orchestration of ML jobs, dependencies, and handoffs across training, validation, deployment, and retraining. This is a useful split from training pipelines because it emphasizes the scheduler and control plane.",
          "slug": "workflow-orchestration-systems",
          "source": "db"
        },
        "dimension_id": 64,
        "input_skill": "Airflow",
        "llm_role": null,
        "matched_chosen_role": true,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension saved",
        "role_dimension_saved": true,
        "roles_from_db": [
          {
            "display_name": "Data Engineer",
            "id": 6,
            "rationale": null,
            "role_archetype": null,
            "slug": "data-engineer",
            "source": "db"
          },
          {
            "display_name": "MLOps Engineer",
            "id": 5,
            "rationale": null,
            "role_archetype": null,
            "slug": "mlops-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 325,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Infrastructure Provisioning Templates",
          "id": 291,
          "rationale": "Declarative templates and modules used to create repeatable cloud resources and environments. This cluster covers the infrastructure definitions the role applies, reviews, and updates to keep environments consistent.",
          "slug": "infrastructure-provisioning-templates",
          "source": "db"
        },
        "dimension_id": 291,
        "input_skill": "Terraform",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Cloud Engineer",
            "id": 18,
            "rationale": null,
            "role_archetype": null,
            "slug": "cloud-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 144,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Infrastructure as Code",
          "id": 22,
          "rationale": "Defines infrastructure and platform resources through versioned code so environments are repeatable and reviewable. This is a coherent cluster because it underpins environment consistency and change control.",
          "slug": "infrastructure-as-code",
          "source": "db"
        },
        "dimension_id": 22,
        "input_skill": "Terraform",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "DevOps Engineer",
            "id": 1,
            "rationale": null,
            "role_archetype": "A DevOps Engineer enables reliable, repeatable delivery of software by designing and operating the processes that connect development and production. They focus on improving deployment flow, operational stability, and collaboration between teams through automation, standardization, and monitoring of delivery and runtime practices.",
            "slug": "devops-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 144,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Infrastructure as Code and Declarative Provisioning",
          "id": 36,
          "rationale": "Defines cloud and platform infrastructure declaratively through versioned code so environments are repeatable, reviewable, and automatable. This includes authoring and maintaining IaC templates/modules, managing parameters and state, and using plan/apply workflows to provision and update resources across Azure and other cloud platforms.",
          "slug": "infrastructure-as-code-and-declarative-provisioning",
          "source": "db"
        },
        "dimension_id": 36,
        "input_skill": "Terraform",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Azure Cloud Engineer",
            "id": 4,
            "rationale": null,
            "role_archetype": null,
            "slug": "azure-cloud-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 144,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Containerization and Image Delivery",
          "id": 24,
          "rationale": "Builds, packages, and ships application and support workloads as container images. This cluster covers the artifact format and the mechanics of producing deployable images.",
          "slug": "containerization-and-image-delivery",
          "source": "db"
        },
        "dimension_id": 24,
        "input_skill": "Docker",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "DevOps Engineer",
            "id": 1,
            "rationale": null,
            "role_archetype": "A DevOps Engineer enables reliable, repeatable delivery of software by designing and operating the processes that connect development and production. They focus on improving deployment flow, operational stability, and collaboration between teams through automation, standardization, and monitoring of delivery and runtime practices.",
            "slug": "devops-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 153,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Model Serving Deployment and Runtime Packaging",
          "id": 52,
          "rationale": "Operational deployment of trained models into online, batch, or streaming serving environments, including packaging models and model servers into containers or managed inference runtimes, coordinating rollout, and handing off to inference systems. Covers serving frameworks and platforms such as TensorFlow Serving, TorchServe, Triton Inference Server, BentoML, KServe, and Seldon Core, plus container/runtime concerns like Docker images, GPU-enabled containers, base image selection, container entrypoints, runtime dependencies, and image scanning for model services.",
          "slug": "model-serving-deployment-and-runtime-packaging",
          "source": "db"
        },
        "dimension_id": 52,
        "input_skill": "Docker",
        "llm_role": null,
        "matched_chosen_role": true,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension saved",
        "role_dimension_saved": true,
        "roles_from_db": [
          {
            "display_name": "MLOps Engineer",
            "id": 5,
            "rationale": null,
            "role_archetype": null,
            "slug": "mlops-engineer",
            "source": "db"
          },
          {
            "display_name": "Machine Learning Engineer",
            "id": 10,
            "rationale": null,
            "role_archetype": null,
            "slug": "machine-learning-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 153,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Orchestration Platforms",
          "id": 25,
          "rationale": "Operates the platforms that schedule and run containerized workloads and related deployment primitives. This is separate from image delivery because it concerns runtime placement and service rollout behavior.",
          "slug": "orchestration-platforms",
          "source": "db"
        },
        "dimension_id": 25,
        "input_skill": "Kubernetes",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Cloud Engineer",
            "id": 18,
            "rationale": null,
            "role_archetype": null,
            "slug": "cloud-engineer",
            "source": "db"
          },
          {
            "display_name": "DevOps Engineer",
            "id": 1,
            "rationale": null,
            "role_archetype": "A DevOps Engineer enables reliable, repeatable delivery of software by designing and operating the processes that connect development and production. They focus on improving deployment flow, operational stability, and collaboration between teams through automation, standardization, and monitoring of delivery and runtime practices.",
            "slug": "devops-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 158,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Cloud Model Runtime Services",
          "id": 121,
          "rationale": "Consumer-level use of cloud services that host or support model inference applications. This cluster is coherent because MLEs often deploy and tune services on managed cloud compute, networking, and storage primitives.",
          "slug": "cloud-model-runtime-services",
          "source": "db"
        },
        "dimension_id": 121,
        "input_skill": "Pinecone",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Machine Learning Engineer",
            "id": 10,
            "rationale": null,
            "role_archetype": null,
            "slug": "machine-learning-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 2621,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Cloud Data Platform Services",
          "id": 81,
          "rationale": "Consumer-level use of cloud services that support data engineering workloads. This includes managed compute, storage, networking-adjacent services, and security primitives used to run pipelines and data platforms.",
          "slug": "cloud-data-platform-services",
          "source": "db"
        },
        "dimension_id": 81,
        "input_skill": "OpenSearch",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Data Engineer",
            "id": 6,
            "rationale": null,
            "role_archetype": null,
            "slug": "data-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 2622,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Version Control Systems",
          "id": 365,
          "rationale": "Tools and workflows for tracking source changes, branching, merging, and collaborating on code history. Git belongs here because it is the canonical distributed version control system used to manage revisions and coordinate team development.",
          "slug": "d_init_01",
          "source": "db"
        },
        "dimension_id": 365,
        "input_skill": "OpenSearch",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [],
        "skill_dimension_saved": true,
        "skill_id": 2622,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Applied Machine Learning Toolkits",
          "id": 94,
          "rationale": "Libraries and frameworks used to prototype and compare models quickly. This dimension captures the concrete tooling layer beneath modeling methods and evaluation.",
          "slug": "applied-machine-learning-toolkits",
          "source": "db"
        },
        "dimension_id": 94,
        "input_skill": "FAISS",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Data Scientist",
            "id": 7,
            "rationale": null,
            "role_archetype": null,
            "slug": "data-scientist",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 2623,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 5,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Version Control Systems",
          "id": 365,
          "rationale": "Tools and workflows for tracking source changes, branching, merging, and collaborating on code history. Git belongs here because it is the canonical distributed version control system used to manage revisions and coordinate team development.",
          "slug": "d_init_01",
          "source": "db"
        },
        "dimension_id": 365,
        "input_skill": "FAISS",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [],
        "skill_dimension_saved": true,
        "skill_id": 2623,
        "skill_tag": "in_db",
        "skipped_reason": null
      }
    ],
    "new_skills_created": 0,
    "role_dimension_saved": 0,
    "skill_dimension_saved": 0,
    "skipped": 0
  },
  "planner_output": null,
  "run_id": "832dda01-52e1-4739-b122-0a9cf9bc8100"
}