lmiranda
2d51df7a42
Phase 1b: Rename all ~94 commands across 12 plugins to /<noun> <action> sub-command pattern. Git-flow consolidated from 8→5 commands (commit variants absorbed into --push/--merge/--sync flags). Dispatch files, name: frontmatter, and cross-reference updates for all plugins. Phase 2: Design documents for 8 new plugins in docs/designs/. Phase 3: Scaffold 8 new plugins — saas-api-platform, saas-db-migrate, saas-react-platform, saas-test-pilot, data-seed, ops-release-manager, ops-deploy-pipeline, debug-mcp. Each with plugin.json, commands, agents, skills, README, and claude-md-integration. Marketplace grows from 12→20. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
958 B
958 B
name
| name |
|---|
| data ingest |
/data ingest - Data Ingestion
Skills to Load
- skills/mcp-tools-reference.md
- skills/visual-header.md
Visual Output
Display header: DATA-PLATFORM - Ingest
Usage
/data ingest [source]
Workflow
-
Identify source:
- File path: determine format (CSV, Parquet, JSON)
- SQL query or table name: query PostgreSQL
-
Load data:
- Files:
read_csv,read_parquet,read_json - Database:
pg_query
- Files:
-
Validate: Check row count against 100k limit
-
Report: data_ref, row count, columns, memory usage, preview
Examples
/data ingest data/sales.csv
/data ingest data/customers.parquet
/data ingest "SELECT * FROM orders WHERE created_at > '2024-01-01'"
Required MCP Tools
read_csv- Load CSV filesread_parquet- Load Parquet filesread_json- Load JSON/JSONL filespg_query- Query PostgreSQL databaselist_data- List loaded DataFrames