{
  "name": "@claudeautopm/plugin-data",
  "version": "2.0.0",
  "schemaVersion": "2.0",
  "displayName": "Data Engineering & ML",
  "description": "Data engineering, ETL pipelines, and ML workflow specialists with Airflow, Kedro, LangGraph, Kafka, dbt, and pandas",
  "category": "data",
  "metadata": {
    "category": "Data Engineering & ML",
    "author": "ClaudeAutoPM Team",
    "license": "MIT",
    "homepage": "https://github.com/rafeekpro/ClaudeAutoPM",
    "repository": {
      "type": "git",
      "url": "git+https://github.com/rafeekpro/ClaudeAutoPM.git",
      "directory": "packages/plugin-data"
    },
    "size": "~25 KB (gzipped)",
    "required": false,
    "tags": [
      "data-engineering",
      "ml",
      "etl",
      "airflow",
      "kedro",
      "langgraph",
      "kafka",
      "dbt",
      "pandas"
    ]
  },
  "agents": [
    {
      "name": "airflow-orchestration-expert",
      "file": "agents/airflow-orchestration-expert.md",
      "category": "data",
      "description": "Apache Airflow workflow orchestration with DAG development, task dependencies, TaskFlow API, operators, sensors, and executors. Expert in data pipelines and ETL/ELT processes.",
      "version": "2.0.0",
      "tags": [
        "airflow",
        "orchestration",
        "dag",
        "etl",
        "data-pipeline"
      ],
      "mcp": [],
      "context7": [
        "/apache/airflow"
      ]
    },
    {
      "name": "kedro-pipeline-expert",
      "file": "agents/kedro-pipeline-expert.md",
      "category": "data",
      "description": "Kedro data pipeline development with project structure, data catalog, pipeline orchestration, nodes, and configuration. Expert in reproducible data science workflows and MLOps.",
      "version": "2.0.0",
      "tags": [
        "kedro",
        "pipeline",
        "data-science",
        "mlops",
        "reproducible"
      ],
      "mcp": [],
      "context7": [
        "/kedro-org/kedro",
        "/kedro-org/kedro-plugins"
      ]
    },
    {
      "name": "langgraph-workflow-expert",
      "file": "agents/langgraph-workflow-expert.md",
      "category": "data",
      "description": "LangGraph workflow orchestration with state machines, conditional routing, multi-agent collaboration, and graph-based AI workflows. Expert in stateful applications and complex decision trees.",
      "version": "2.0.0",
      "tags": [
        "langgraph",
        "workflow",
        "state-machine",
        "ai",
        "multi-agent"
      ],
      "mcp": [],
      "context7": [
        "/langchain-ai/langgraph",
        "/websites/langchain-ai_github_io_langgraph"
      ]
    }
  ],
  "commands": [
    {
      "subdirectory": "commands/",
      "description": "Data Engineering & ML commands (4 total)",
      "type": "collection",
      "discovery": "auto",
      "tags": [
        "airflow",
        "dag",
        "scaffold",
        "etl",
        "taskflow",
        "lineage",
        "openlineage",
        "data-catalog",
        "governance",
        "data-quality",
        "great-expectations",
        "validation"
      ]
    }
  ],
  "rules": [
    {
      "name": "data-quality-standards",
      "file": "rules/data-quality-standards.md",
      "priority": "high",
      "description": "Comprehensive data quality standards with Context7-verified best practices: validation, completeness, consistency, accuracy, timeliness for Airflow, Kedro, pandas, dbt",
      "tags": [
        "data-quality",
        "validation",
        "standards",
        "testing",
        "metrics"
      ],
      "appliesTo": [
        "commands",
        "agents"
      ],
      "enforcesOn": [
        "airflow-orchestration-expert",
        "kedro-pipeline-expert",
        "langgraph-workflow-expert"
      ]
    },
    {
      "name": "etl-pipeline-standards",
      "file": "rules/etl-pipeline-standards.md",
      "priority": "high",
      "description": "ETL/ELT pipeline best practices with Context7-verified patterns: idempotency, incremental processing, error handling, data lineage, monitoring for all frameworks",
      "tags": [
        "etl",
        "pipeline",
        "standards",
        "best-practices",
        "idempotency"
      ],
      "appliesTo": [
        "commands",
        "agents"
      ],
      "enforcesOn": [
        "airflow-orchestration-expert",
        "kedro-pipeline-expert"
      ]
    }
  ],
  "scripts": [
    {
      "name": "airflow-dag-example",
      "file": "scripts/examples/airflow-dag-example.py",
      "description": "Airflow DAG example demonstrating Context7 patterns: TaskFlow API, task dependencies, sensors, parallel extraction, error handling",
      "type": "example",
      "executable": true,
      "category": "data",
      "tags": [
        "airflow",
        "dag",
        "example",
        "taskflow",
        "context7"
      ]
    },
    {
      "name": "kafka-streaming-example",
      "file": "scripts/examples/kafka-streaming-example.py",
      "description": "Kafka producer/consumer example demonstrating Context7 patterns: reliable configuration, callbacks, manual commits, graceful shutdown",
      "type": "example",
      "executable": true,
      "category": "data",
      "tags": [
        "kafka",
        "streaming",
        "example",
        "producer",
        "consumer",
        "context7"
      ]
    },
    {
      "name": "dbt-transform-example",
      "file": "scripts/examples/dbt-transform-example.sql",
      "description": "dbt transformation example demonstrating Context7 patterns: Jinja macros, ref/source, materializations, tests, documentation",
      "type": "example",
      "executable": true,
      "category": "data",
      "tags": [
        "dbt",
        "transformation",
        "example",
        "jinja",
        "context7"
      ]
    },
    {
      "name": "pandas-etl-example",
      "file": "scripts/examples/pandas-etl-example.py",
      "description": "pandas ETL example demonstrating Context7 patterns: vectorized operations, GroupBy aggregations, efficient merging, data validation, quality metrics",
      "type": "example",
      "executable": true,
      "category": "data",
      "tags": [
        "pandas",
        "etl",
        "example",
        "validation",
        "context7"
      ]
    }
  ],
  "features": {
    "airflow_orchestration": {
      "enabled": true,
      "description": "Apache Airflow workflow orchestration with DAGs and TaskFlow API"
    },
    "kedro_pipelines": {
      "enabled": true,
      "description": "Kedro reproducible data science pipelines and MLOps"
    },
    "langgraph_workflows": {
      "enabled": true,
      "description": "LangGraph stateful AI workflows and multi-agent systems"
    },
    "kafka_streaming": {
      "enabled": true,
      "description": "Apache Kafka event streaming and real-time data pipelines"
    },
    "dbt_transformations": {
      "enabled": true,
      "description": "dbt data transformations with Jinja and SQL"
    },
    "pandas_etl": {
      "enabled": true,
      "description": "pandas data manipulation and ETL processing"
    },
    "data_quality": {
      "enabled": true,
      "description": "Comprehensive data quality validation and monitoring"
    },
    "etl_standards": {
      "enabled": true,
      "description": "ETL/ELT pipeline best practices and standards"
    }
  },
  "dependencies": [],
  "peerPlugins": [
    "@claudeautopm/plugin-core"
  ],
  "mcpServers": {
    "recommended": [
      "context7"
    ],
    "optional": []
  },
  "keywords": [
    "claudeautopm",
    "plugin",
    "data-engineering",
    "ml",
    "machine-learning",
    "etl",
    "analytics",
    "airflow",
    "kedro",
    "langgraph",
    "kafka",
    "dbt",
    "pandas"
  ],
  "compatibleWith": ">=3.0.0"
}