agentleFS
Sign inStart free
kinged007kinged007/agent-skill-search/AGENTS.md

agent-skill-search

AGENTS.md0 starsChanged 28 days agoMITView on GitHub

Portable skill catalog search for AI agents. CLI (skill-search) + MCP server (skill-search-mcp, tools: skill_search, skill_view, skill_list). Skills are stored as SKILL.md files in a catalog indexed with SQLite FTS5. Prefer the skill-search MCP tools or CLI over reading every SKILL.md into context. Example: The catalog dir defaults to ~/.agents/skills-catalog; add local skills with skill-search add <dir>. Use kinged007 <599286+kinged007@users.noreply.github.com> for commits.

  • Reads credentials
  • Installs packages
  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repositoryOne other file it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

5 rules. About 1 is common, 2 are distinctive, and 2 are very specific to this project.

  • ≈1

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    Prefer the skill-search MCP tools or CLI over reading every SKILL.md into context.

    line 22
  2. Distinctive:

    Do not push directly to main.

    line 33
  3. Distinctive:

    Create a feature branch, commit, push, and open a PR against main.

    line 34
  4. Common:

    Do not commit secrets (API keys, tokens, .env).

    line 39
  5. Very specific:

    Use kinged007 <599286+kinged007@users.noreply.github.com> for commits.

    line 44

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

AGENTS.md — agent-skill-search

Purpose

Portable skill catalog search for AI agents. CLI (skill-search) + MCP server (skill-search-mcp, tools: skill_search, skill_view, skill_list). Skills are stored as SKILL.md files in a catalog indexed with SQLite FTS5.

How to work in this repo

  • Python 3.10+, package agent-skill-search, entry points skill_search.cli:main and skill_search.server:run.
  • Install dev deps: pip install ".[dev]" ruff mypy.
  • Checks (same as CI):
    pytest -q
ruff check .
mypy skill_search --ignore-missing-imports
  • Catalog for tests is test-catalog/; set SKILL_CATALOG_DIRS to point at it when exercising CLI/server locally.
  • skill_search/engine.py owns indexing/search, cli.py the CLI, server.py the MCP server, install.py/clients.py per-client install adapters.

Using skills in this repo

Prefer the skill-search MCP tools or CLI over reading every SKILL.md into context. Example:

skill-search search "mcp|install"
skill-search view "skill-search"

The catalog dir defaults to ~/.agents/skills-catalog; add local skills with skill-search add <dir>.

Branch / PR workflow

  • Do not push directly to main.
  • Create a feature branch, commit, push, and open a PR against main.
  • CI (ci.yml) runs pytest + ruff + mypy on Python 3.10 and 3.12 for every push/PR to main.

Permissions

  • Do not commit secrets (API keys, tokens, .env). Only .env.example belongs in the repo.
  • This repo is self-contained. Do not add network calls in tests; mock external services.

Commit authorship

Use kinged007 <599286+kinged007@users.noreply.github.com> for commits.

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.

Check your setup, free