[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72A1RJ5SAER4D22WGJZ8B55":3,"skill-same:01M72A1RJ5SAER4D22WGJZ8B55":88},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":67,"commitSha":68,"skillDirectory":69,"forksCount":70,"repositoryHtmlUrl":71,"repositoryHomepageUrl":6,"ownerHtmlUrl":72,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":73,"install":74,"resources":87},"01M72A1RJ5SAER4D22WGJZ8B55","ETL Pipeline",null,"Design and automate Extract, Transform, Load data pipelines for data integration and analytics","claude-office-skills\u002Fskills","claude-office-skills","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F258027507?v=4","01M729XQC9FBRQ54AQZS0KY3ZK","AGI Lab","01M729XQCYW6WF9GY762P9RNQJ",572,"MIT","https:\u002F\u002Fgithub.com\u002Fclaude-office-skills\u002Fskills\u002Fblob\u002Fmain\u002Fetl-pipeline\u002FSKILL.md",[],[],"2026-11-10 18:39:20",false,"---\nname: ETL Pipeline\ndescription: Design and automate Extract, Transform, Load data pipelines for data integration and analytics\nversion: 1.0.0\nauthor: Claude Office Skills\ncategory: data\ntags:\n  - etl\n  - data-pipeline\n  - integration\n  - analytics\n  - automation\ndepartment: engineering\nmodels:\n  - claude-3-opus\n  - claude-3-sonnet\n  - gpt-4\nmcp:\n  server: data-mcp\n  tools:\n    - postgres_query\n    - mysql_query\n    - mongodb_aggregate\n    - bigquery_load\n    - snowflake_api\ncapabilities:\n  - Data extraction from multiple sources\n  - Data transformation and cleaning\n  - Automated data loading\n  - Pipeline orchestration\ninput:\n  - Source database connections\n  - Transformation rules\n  - Target schema definitions\n  - Schedule configurations\noutput:\n  - Transformed datasets\n  - Pipeline status reports\n  - Data quality metrics\n  - Error logs\nlanguages:\n  - en\nrelated_skills:\n  - sheets-automation\n  - database-sync\n  - api-integration\n---\n\n# ETL Pipeline\n\nComprehensive skill for designing and automating Extract, Transform, Load data pipelines.\n\n## Pipeline Architecture\n\n### Core ETL Flow\n\n```\nDATA PIPELINE ARCHITECTURE:\n┌─────────────────────────────────────────────────────────┐\n│                     EXTRACT                              │\n├─────────┬─────────┬─────────┬─────────┬─────────────────┤\n│ Postgres│  MySQL  │ MongoDB │  APIs   │  Files (CSV\u002FJSON)│\n└────┬────┴────┬────┴────┬────┴────┬────┴────────┬────────┘\n     │         │         │         │              │\n     └─────────┴─────────┴────┬────┴──────────────┘\n                              ▼\n┌─────────────────────────────────────────────────────────┐\n│                    TRANSFORM                             │\n│  • Clean & Validate    • Aggregate & Join               │\n│  • Normalize           • Calculate Metrics              │\n│  • Deduplicate         • Apply Business Rules           │\n└────────────────────────┬────────────────────────────────┘\n                         ▼\n┌─────────────────────────────────────────────────────────┐\n│                      LOAD                                │\n├─────────────┬─────────────┬─────────────┬───────────────┤\n│  BigQuery   │  Snowflake  │  Redshift   │  Data Lake    │\n└─────────────┴─────────────┴─────────────┴───────────────┘\n```\n\n## Source Connectors\n\n### Database Connections\n\n```yaml\nsources:\n  postgres:\n    type: postgresql\n    host: db.example.com\n    port: 5432\n    database: production\n    ssl: true\n    extraction:\n      method: incremental\n      key: updated_at\n      batch_size: 10000\n\n  mysql:\n    type: mysql\n    host: mysql.example.com\n    port: 3306\n    database: analytics\n    extraction:\n      method: cdc\n      binlog: true\n\n  mongodb:\n    type: mongodb\n    connection_string: mongodb+srv:\u002F\u002F...\n    database: app_data\n    extraction:\n      method: change_streams\n```\n\n### API Sources\n\n```yaml\napi_sources:\n  stripe:\n    type: rest_api\n    base_url: https:\u002F\u002Fapi.stripe.com\u002Fv1\n    auth: bearer_token\n    endpoints:\n      - \u002Fcharges\n      - \u002Fcustomers\n      - \u002Fsubscriptions\n    pagination: cursor\n    rate_limit: 100\u002Fsecond\n\n  salesforce:\n    type: salesforce\n    instance_url: https:\u002F\u002Fcompany.salesforce.com\n    auth: oauth2\n    objects:\n      - Account\n      - Opportunity\n      - Contact\n    bulk_api: true\n```\n\n## Transformation Layer\n\n### Common Transformations\n\n```python\n# Data Cleaning\ntransformations = {\n    \"clean_nulls\": {\n        \"operation\": \"fill_null\",\n        \"columns\": [\"email\", \"phone\"],\n        \"value\": \"unknown\"\n    },\n    \n    \"standardize_dates\": {\n        \"operation\": \"date_parse\",\n        \"columns\": [\"created_at\", \"updated_at\"],\n        \"format\": \"ISO8601\"\n    },\n    \n    \"normalize_currency\": {\n        \"operation\": \"convert_currency\",\n        \"source_column\": \"amount\",\n        \"currency_column\": \"currency\",\n        \"target\": \"USD\"\n    },\n    \n    \"deduplicate\": {\n        \"operation\": \"distinct\",\n        \"key_columns\": [\"customer_id\", \"transaction_id\"],\n        \"keep\": \"latest\"\n    }\n}\n```\n\n### Aggregation Rules\n\n```sql\n-- Daily Revenue Aggregation\nSELECT \n    DATE(created_at) as date,\n    product_category,\n    COUNT(*) as transactions,\n    SUM(amount) as total_revenue,\n    AVG(amount) as avg_order_value,\n    COUNT(DISTINCT customer_id) as unique_customers\nFROM orders\nWHERE created_at >= '${start_date}'\nGROUP BY 1, 2\n```\n\n### Join Operations\n\n```yaml\njoins:\n  - name: enrich_orders\n    left: orders\n    right: customers\n    type: left\n    on:\n      - left: customer_id\n        right: id\n    select:\n      - orders.*\n      - customers.email\n      - customers.segment\n      - customers.lifetime_value\n\n  - name: add_product_details\n    left: enriched_orders\n    right: products\n    type: left\n    on:\n      - left: product_id\n        right: id\n```\n\n## Load Strategies\n\n### BigQuery Load\n\n```yaml\nbigquery_load:\n  project: my-project\n  dataset: analytics\n  table: fact_orders\n  \n  schema:\n    - name: order_id\n      type: STRING\n      mode: REQUIRED\n    - name: customer_id\n      type: STRING\n    - name: amount\n      type: NUMERIC\n    - name: created_at\n      type: TIMESTAMP\n  \n  load_config:\n    write_disposition: WRITE_APPEND\n    create_disposition: CREATE_IF_NEEDED\n    clustering_fields: [customer_id]\n    time_partitioning:\n      field: created_at\n      type: DAY\n```\n\n### Snowflake Load\n\n```yaml\nsnowflake_load:\n  warehouse: ETL_WH\n  database: ANALYTICS\n  schema: PUBLIC\n  table: FACT_ORDERS\n  \n  staging:\n    stage: '@MY_STAGE'\n    file_format: JSON\n  \n  copy_options:\n    on_error: CONTINUE\n    purge: true\n    match_by_column_name: CASE_INSENSITIVE\n```\n\n## Pipeline Orchestration\n\n### DAG Definition\n\n```yaml\npipeline:\n  name: daily_analytics_etl\n  schedule: \"0 2 * * *\"  # 2 AM daily\n  \n  tasks:\n    - id: extract_orders\n      type: extract\n      source: postgres\n      query: \"SELECT * FROM orders WHERE date = '${execution_date}'\"\n      \n    - id: extract_customers\n      type: extract\n      source: postgres\n      query: \"SELECT * FROM customers\"\n      \n    - id: transform_data\n      type: transform\n      dependencies: [extract_orders, extract_customers]\n      operations:\n        - join_customers\n        - calculate_metrics\n        - apply_business_rules\n      \n    - id: load_warehouse\n      type: load\n      dependencies: [transform_data]\n      target: bigquery\n      table: fact_orders\n      \n    - id: notify_complete\n      type: notification\n      dependencies: [load_warehouse]\n      channel: slack\n      message: \"Daily ETL completed successfully\"\n```\n\n### Error Handling\n\n```yaml\nerror_handling:\n  retry:\n    max_attempts: 3\n    delay_seconds: 300\n    exponential_backoff: true\n  \n  on_failure:\n    - log_error\n    - send_alert\n    - save_failed_records\n  \n  dead_letter:\n    enabled: true\n    destination: s3:\u002F\u002Fetl-errors\u002F\n    retention_days: 30\n```\n\n## Data Quality\n\n### Validation Rules\n\n```yaml\nquality_checks:\n  - name: null_check\n    column: customer_id\n    rule: not_null\n    severity: error\n    \n  - name: range_check\n    column: amount\n    rule: between\n    min: 0\n    max: 100000\n    severity: warning\n    \n  - name: uniqueness\n    columns: [order_id]\n    rule: unique\n    severity: error\n    \n  - name: referential_integrity\n    column: product_id\n    reference_table: products\n    reference_column: id\n    severity: error\n    \n  - name: freshness\n    column: updated_at\n    rule: max_age_hours\n    value: 24\n    severity: warning\n```\n\n### Quality Metrics Dashboard\n\n```\nDATA QUALITY REPORT - ${date}\n═══════════════════════════════════════\nTotal Records Processed: 1,250,000\nPassed Validation:       1,247,500 (99.8%)\nFailed Validation:           2,500 (0.2%)\n\nISSUES BY TYPE:\n┌─────────────────┬────────┬──────────┐\n│ Issue Type      │ Count  │ Severity │\n├─────────────────┼────────┼──────────┤\n│ Null values     │ 1,200  │ Warning  │\n│ Invalid format  │   850  │ Error    │\n│ Out of range    │   300  │ Warning  │\n│ Duplicates      │   150  │ Error    │\n└─────────────────┴────────┴──────────┘\n```\n\n## Monitoring & Alerting\n\n### Pipeline Metrics\n\n```yaml\nmetrics:\n  - name: pipeline_duration\n    type: gauge\n    labels: [pipeline_name, status]\n    \n  - name: records_processed\n    type: counter\n    labels: [pipeline_name, source, destination]\n    \n  - name: error_count\n    type: counter\n    labels: [pipeline_name, error_type]\n    \n  - name: data_freshness\n    type: gauge\n    labels: [table_name]\n```\n\n### Alert Configuration\n\n```yaml\nalerts:\n  - name: pipeline_failed\n    condition: status == 'failed'\n    channels: [pagerduty, slack]\n    \n  - name: high_error_rate\n    condition: error_rate > 0.05\n    channels: [slack]\n    \n  - name: slow_pipeline\n    condition: duration > 2 * avg_duration\n    channels: [slack]\n    \n  - name: data_freshness\n    condition: freshness_hours > 24\n    channels: [email]\n```\n\n## Best Practices\n\n1. **Incremental Loading**: Use incremental extraction when possible\n2. **Idempotency**: Ensure pipelines can be re-run safely\n3. **Partitioning**: Partition large tables by date\n4. **Monitoring**: Track pipeline health metrics\n5. **Documentation**: Document all transformations\n6. **Testing**: Test with sample data before production\n7. **Version Control**: Track pipeline changes in git\n","# ETL Pipeline\n\nComprehensive skill for designing and automating Extract, Transform, Load data pipelines.\n\n## Pipeline Architecture\n\n### Core ETL Flow\n\n```\nDATA PIPELINE ARCHITECTURE:\n┌─────────────────────────────────────────────────────────┐\n│                     EXTRACT                              │\n├─────────┬─────────┬─────────┬─────────┬─────────────────┤\n│ Postgres│  MySQL  │ MongoDB │  APIs   │  Files (CSV\u002FJSON)│\n└────┬────┴────┬────┴────┬────┴────┬────┴────────┬────────┘\n     │         │         │         │              │\n     └─────────┴─────────┴────┬────┴──────────────┘\n                              ▼\n┌─────────────────────────────────────────────────────────┐\n│                    TRANSFORM                             │\n│  • Clean & Validate    • Aggregate & Join               │\n│  • Normalize           • Calculate Metrics              │\n│  • Deduplicate         • Apply Business Rules           │\n└────────────────────────┬────────────────────────────────┘\n                         ▼\n┌─────────────────────────────────────────────────────────┐\n│                      LOAD                                │\n├─────────────┬─────────────┬─────────────┬───────────────┤\n│  BigQuery   │  Snowflake  │  Redshift   │  Data Lake    │\n└─────────────┴─────────────┴─────────────┴───────────────┘\n```\n\n## Source Connectors\n\n### Database Connections\n\n```yaml\nsources:\n  postgres:\n    type: postgresql\n    host: db.example.com\n    port: 5432\n    database: production\n    ssl: true\n    extraction:\n      method: incremental\n      key: updated_at\n      batch_size: 10000\n\n  mysql:\n    type: mysql\n    host: mysql.example.com\n    port: 3306\n    database: analytics\n    extraction:\n      method: cdc\n      binlog: true\n\n  mongodb:\n    type: mongodb\n    connection_string: mongodb+srv:\u002F\u002F...\n    database: app_data\n    extraction:\n      method: change_streams\n```\n\n### API Sources\n\n```yaml\napi_sources:\n  stripe:\n    type: rest_api\n    base_url: https:\u002F\u002Fapi.stripe.com\u002Fv1\n    auth: bearer_token\n    endpoints:\n      - \u002Fcharges\n      - \u002Fcustomers\n      - \u002Fsubscriptions\n    pagination: cursor\n    rate_limit: 100\u002Fsecond\n\n  salesforce:\n    type: salesforce\n    instance_url: https:\u002F\u002Fcompany.salesforce.com\n    auth: oauth2\n    objects:\n      - Account\n      - Opportunity\n      - Contact\n    bulk_api: true\n```\n\n## Transformation Layer\n\n### Common Transformations\n\n```python\n# Data Cleaning\ntransformations = {\n    \"clean_nulls\": {\n        \"operation\": \"fill_null\",\n        \"columns\": [\"email\", \"phone\"],\n        \"value\": \"unknown\"\n    },\n    \n    \"standardize_dates\": {\n        \"operation\": \"date_parse\",\n        \"columns\": [\"created_at\", \"updated_at\"],\n        \"format\": \"ISO8601\"\n    },\n    \n    \"normalize_currency\": {\n        \"operation\": \"convert_currency\",\n        \"source_column\": \"amount\",\n        \"currency_column\": \"currency\",\n        \"target\": \"USD\"\n    },\n    \n    \"deduplicate\": {\n        \"operation\": \"distinct\",\n        \"key_columns\": [\"customer_id\", \"transaction_id\"],\n        \"keep\": \"latest\"\n    }\n}\n```\n\n### Aggregation Rules\n\n```sql\n-- Daily Revenue Aggregation\nSELECT \n    DATE(created_at) as date,\n    product_category,\n    COUNT(*) as transactions,\n    SUM(amount) as total_revenue,\n    AVG(amount) as avg_order_value,\n    COUNT(DISTINCT customer_id) as unique_customers\nFROM orders\nWHERE created_at >= '${start_date}'\nGROUP BY 1, 2\n```\n\n### Join Operations\n\n```yaml\njoins:\n  - name: enrich_orders\n    left: orders\n    right: customers\n    type: left\n    on:\n      - left: customer_id\n        right: id\n    select:\n      - orders.*\n      - customers.email\n      - customers.segment\n      - customers.lifetime_value\n\n  - name: add_product_details\n    left: enriched_orders\n    right: products\n    type: left\n    on:\n      - left: product_id\n        right: id\n```\n\n## Load Strategies\n\n### BigQuery Load\n\n```yaml\nbigquery_load:\n  project: my-project\n  dataset: analytics\n  table: fact_orders\n  \n  schema:\n    - name: order_id\n      type: STRING\n      mode: REQUIRED\n    - name: customer_id\n      type: STRING\n    - name: amount\n      type: NUMERIC\n    - name: created_at\n      type: TIMESTAMP\n  \n  load_config:\n    write_disposition: WRITE_APPEND\n    create_disposition: CREATE_IF_NEEDED\n    clustering_fields: [customer_id]\n    time_partitioning:\n      field: created_at\n      type: DAY\n```\n\n### Snowflake Load\n\n```yaml\nsnowflake_load:\n  warehouse: ETL_WH\n  database: ANALYTICS\n  schema: PUBLIC\n  table: FACT_ORDERS\n  \n  staging:\n    stage: '@MY_STAGE'\n    file_format: JSON\n  \n  copy_options:\n    on_error: CONTINUE\n    purge: true\n    match_by_column_name: CASE_INSENSITIVE\n```\n\n## Pipeline Orchestration\n\n### DAG Definition\n\n```yaml\npipeline:\n  name: daily_analytics_etl\n  schedule: \"0 2 * * *\"  # 2 AM daily\n  \n  tasks:\n    - id: extract_orders\n      type: extract\n      source: postgres\n      query: \"SELECT * FROM orders WHERE date = '${execution_date}'\"\n      \n    - id: extract_customers\n      type: extract\n      source: postgres\n      query: \"SELECT * FROM customers\"\n      \n    - id: transform_data\n      type: transform\n      dependencies: [extract_orders, extract_customers]\n      operations:\n        - join_customers\n        - calculate_metrics\n        - apply_business_rules\n      \n    - id: load_warehouse\n      type: load\n      dependencies: [transform_data]\n      target: bigquery\n      table: fact_orders\n      \n    - id: notify_complete\n      type: notification\n      dependencies: [load_warehouse]\n      channel: slack\n      message: \"Daily ETL completed successfully\"\n```\n\n### Error Handling\n\n```yaml\nerror_handling:\n  retry:\n    max_attempts: 3\n    delay_seconds: 300\n    exponential_backoff: true\n  \n  on_failure:\n    - log_error\n    - send_alert\n    - save_failed_records\n  \n  dead_letter:\n    enabled: true\n    destination: s3:\u002F\u002Fetl-errors\u002F\n    retention_days: 30\n```\n\n## Data Quality\n\n### Validation Rules\n\n```yaml\nquality_checks:\n  - name: null_check\n    column: customer_id\n    rule: not_null\n    severity: error\n    \n  - name: range_check\n    column: amount\n    rule: between\n    min: 0\n    max: 100000\n    severity: warning\n    \n  - name: uniqueness\n    columns: [order_id]\n    rule: unique\n    severity: error\n    \n  - name: referential_integrity\n    column: product_id\n    reference_table: products\n    reference_column: id\n    severity: error\n    \n  - name: freshness\n    column: updated_at\n    rule: max_age_hours\n    value: 24\n    severity: warning\n```\n\n### Quality Metrics Dashboard\n\n```\nDATA QUALITY REPORT - ${date}\n═══════════════════════════════════════\nTotal Records Processed: 1,250,000\nPassed Validation:       1,247,500 (99.8%)\nFailed Validation:           2,500 (0.2%)\n\nISSUES BY TYPE:\n┌─────────────────┬────────┬──────────┐\n│ Issue Type      │ Count  │ Severity │\n├─────────────────┼────────┼──────────┤\n│ Null values     │ 1,200  │ Warning  │\n│ Invalid format  │   850  │ Error    │\n│ Out of range    │   300  │ Warning  │\n│ Duplicates      │   150  │ Error    │\n└─────────────────┴────────┴──────────┘\n```\n\n## Monitoring & Alerting\n\n### Pipeline Metrics\n\n```yaml\nmetrics:\n  - name: pipeline_duration\n    type: gauge\n    labels: [pipeline_name, status]\n    \n  - name: records_processed\n    type: counter\n    labels: [pipeline_name, source, destination]\n    \n  - name: error_count\n    type: counter\n    labels: [pipeline_name, error_type]\n    \n  - name: data_freshness\n    type: gauge\n    labels: [table_name]\n```\n\n### Alert Configuration\n\n```yaml\nalerts:\n  - name: pipeline_failed\n    condition: status == 'failed'\n    channels: [pagerduty, slack]\n    \n  - name: high_error_rate\n    condition: error_rate > 0.05\n    channels: [slack]\n    \n  - name: slow_pipeline\n    condition: duration > 2 * avg_duration\n    channels: [slack]\n    \n  - name: data_freshness\n    condition: freshness_hours > 24\n    channels: [email]\n```\n\n## Best Practices\n\n1. **Incremental Loading**: Use incremental extraction when possible\n2. **Idempotency**: Ensure pipelines can be re-run safely\n3. **Partitioning**: Partition large tables by date\n4. **Monitoring**: Track pipeline health metrics\n5. **Documentation**: Document all transformations\n6. **Testing**: Test with sample data before production\n7. **Version Control**: Track pipeline changes in git\n",{"mcp":24,"name":5,"tags":32,"input":38,"author":43,"models":44,"output":48,"version":53,"category":54,"languages":55,"department":57,"description":7,"capabilities":58,"related_skills":63},{"tools":25,"server":31},[26,27,28,29,30],"postgres_query","mysql_query","mongodb_aggregate","bigquery_load","snowflake_api","data-mcp",[33,34,35,36,37],"etl","data-pipeline","integration","analytics","automation",[39,40,41,42],"Source database connections","Transformation rules","Target schema definitions","Schedule configurations","Claude Office Skills",[45,46,47],"claude-3-opus","claude-3-sonnet","gpt-4",[49,50,51,52],"Transformed datasets","Pipeline status reports","Data quality metrics","Error logs","1.0.0","data",[56],"en","engineering",[59,60,61,62],"Data extraction from multiple sources","Data transformation and cleaning","Automated data loading","Pipeline orchestration",[64,65,66],"sheets-automation","database-sync","api-integration","main","9c4c7d5cd2813a8936bf2c9fdb174ea883b85a11","etl-pipeline",101,"https:\u002F\u002Fgithub.com\u002Fclaude-office-skills\u002Fskills","https:\u002F\u002Fgithub.com\u002Fclaude-office-skills","2026-01-31 22:03:56",{"source":8,"skillName":5,"commands":75,"prompt":85,"zipAvailable":86},[76,79,82],{"tool":77,"command":78},"npx","npx skills add claude-office-skills\u002Fskills --skill \"ETL Pipeline\"",{"tool":80,"command":81},"bunx","bunx skills add claude-office-skills\u002Fskills --skill \"ETL Pipeline\"",{"tool":83,"command":84},"pnpm","pnpm dlx skills add claude-office-skills\u002Fskills --skill \"ETL Pipeline\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fclaude-office-skills\u002Fskills\u002Fblob\u002Fmain\u002Fetl-pipeline\u002FSKILL.md",true,[],[89,96,103,110,117,124],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M72A0X7X4TWS4ZWTEK8TJEC8","devops-automation","DevOps and IT Ops automation - CI\u002FCD, monitoring, incident management, and infrastructure workflows","https:\u002F\u002Fgithub.com\u002Fclaude-office-skills\u002Fskills\u002Fblob\u002Fmain\u002Fdevops-automation\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":19},"01M72A0VPXF4Q5F48TPDG6S10Q","dev-slides",">","https:\u002F\u002Fgithub.com\u002Fclaude-office-skills\u002Fskills\u002Fblob\u002Fmain\u002Fdev-slides\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":19},"01M72A0Q1T0KN60CR3PAD93J6T","deep-research","Conduct comprehensive research on any topic. Synthesize information from multiple angles, provide structured analysis, and generate detailed research reports.","https:\u002F\u002Fgithub.com\u002Fclaude-office-skills\u002Fskills\u002Fblob\u002Fmain\u002Fdeep-research\u002FSKILL.md",[],[],{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":19},"01M72A0KWAYEWQJMDRGC0WTT7V","dcf-valuation","Build Discounted Cash Flow (DCF) valuation models. Calculate intrinsic value with customizable assumptions. Generate professional valuation reports.","https:\u002F\u002Fgithub.com\u002Fclaude-office-skills\u002Fskills\u002Fblob\u002Fmain\u002Fdcf-valuation\u002FSKILL.md",[],[],{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":19},"01M72A0GVWRZ3HZNXMW3RB5CF9","Database Sync","Automate database synchronization, replication, migration, and cross-platform data integration","https:\u002F\u002Fgithub.com\u002Fclaude-office-skills\u002Fskills\u002Fblob\u002Fmain\u002Fdatabase-sync\u002FSKILL.md",[],[],{"skillNo":125,"name":34,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":129,"publishedAt":19},"01M72A0E16K862EDP0QYEAC9HJ","Data pipeline and ETL automation - extract, transform, load workflows for data integration and analytics","https:\u002F\u002Fgithub.com\u002Fclaude-office-skills\u002Fskills\u002Fblob\u002Fmain\u002Fdata-pipeline\u002FSKILL.md",[],[]]