agentleFS
manastalukdarmanastalukdar/ai-devstudio/skills/database-connect/SKILL.md

database-connect

Skill1 starsChanged 7 months agoMITView on GitHub

Database MCP server integration for PostgreSQL, MySQL, MongoDB

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Database Connection & Management

I'll help you connect to and manage databases through MCP servers for data exploration, schema inspection, and queries.

Arguments: $ARGUMENTS - database type (postgres, mysql, mongodb), connection details, or query

Database Capabilities

Supported Databases:

  • PostgreSQL (via MCP or native psql)
  • MySQL/MariaDB (via MCP or native mysql)
  • MongoDB (via MCP or native mongo)
  • SQLite (local database files)

Operations:

  • Schema inspection and exploration
  • Safe query execution
  • Data exploration and analysis
  • Migration support

Token Optimization

Expected range: 1,500–2,500 tokens (initial), 400 tokens (cache hit)

Caching: Caches database connection config in .claude/cache/database/ for 7 days. Invalidated when connection strings change.

Early exit: Returns immediately if MCP server for the target database is already connected.

Patterns used: Grep-before-Read, early exit, template-based generation, caching

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.