{
  "markdown": "<p align=\"center\"><img src=\"logo.png\" width=\"120\" alt=\"logo\" /></p>\n\n# postgres-intelligence\n\nPostgreSQL intelligence skill for LLM coding agents.\n\nUse it with Claude Code, Codex, Cursor, Windsurf, or any local agent that needs to safely connect to PostgreSQL, inspect schemas, run read-first SQL, and reason about query performance without exposing credentials.\n\n## Why This Exists\n\nLLM agents are useful for database exploration, but they should not read or print secrets. `postgres-intelligence` keeps the contract clear:\n\n- humans configure `.env`\n- scripts load credentials at runtime\n- agents see only safe summaries, metadata, query results, and errors\n\n## Features\n\n- Multi-connection PostgreSQL config with `DB1_...DB10_...`\n- Safe connection testing without printing passwords or full DSNs\n- Schema metadata extraction from `information_schema` and `pg_catalog`\n- Read-only SQL by default: `SELECT`, `WITH`, `SHOW`, `EXPLAIN`\n- Write/DDL guards with explicit `--allow-write` and `--allow-ddl`\n- Structured JSON output for LLM agents\n- PostgreSQL guidance for `EXPLAIN`, indexes, JSONB, and maintenance\n\n## Install\n\n```bash\ngit clone https://github.com/cskwork/postgres-intelligence.git\ncd postgres-intelligence\npython3 -m venv .venv\n. .venv/bin/activate\npython -m pip install -r requirements.txt\ncp .env.example .env\n```\n\nEdit `.env` with your PostgreSQL connection details.\n\n## Quick Start\n\n```bash\n# Validate config without printing secrets\npython scripts/config.py\n\n# Test all configured connections\npython scripts/db_connector.py\n\n# Extract schema metadata\npython scripts/schema_extractor.py\n\n# Run read-only SQL\npython scripts/query_executor.py --json-only \"SELECT current_database(), current_schema();\"\n```\n\n## Agent Rule\n\nDo not open or print `.env` directly. Let scripts load credentials.\n\n## Layout\n\n```text\nSKILL.md\n.env.example\nrequirements.txt\nscripts/\n  config.py\n  db_connector.py\n  query_executor.py\n  schema_extractor.py\n  setup.py\nreferences/\n  postgres_best_practices.md\n```\n\n## License\n\nMIT\n\n",
  "bytes": 2021,
  "sha": "04eb9e1cb9637eb384d8b9e6368719b01b03bdcdab591dbf609f3a21aed35a12",
  "repo_slug": "cskwork/postgres-intelligence",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_cskwork_postgres_intelligence_a5889a68/readme"
}