| name | source-analyzer |
| description | Analyze data source characteristics including update frequency, volume patterns, and schema stability. |
| allowed-tools | Read Grep Glob Bash |
Source Analyzer
Audience: Data engineers planning ETL pipelines.
Goal: Characterize data sources for extraction planning by analyzing volume, update patterns, schema, and quality baselines.
Analysis Dimensions
Volume Analysis
- Current row count
- Historical growth rate (if multiple snapshots available)
- Projected growth
- Peak vs average volume
- Seasonality patterns
Update Patterns
- Full refresh vs incremental
- Update frequency (hourly, daily, weekly)
- Batch arrival times
- Late-arriving data windows
Schema Characteristics
- Column count and types
- Nullable patterns
- Primary key candidates
- Foreign key relationships
- Schema change history
Data Quality Baseline
- Typical null rates per column
- Expected value ranges
- Cardinality expectations
- Known data issues
Workflow
- Inventory the source - File location/database connection, access patterns (API, file drop, DB query), authentication requirements
- Sample multiple time periods - Analyze data from different dates, identify temporal patterns
- Profile the schema - Document all columns, identify stable vs volatile columns, note computed/derived columns
