agentleFS
FrankieeWFrankieeW/agent-skills/AGENTS.md

agent-skills

AGENTS.md0 starsChanged 8 months agoMITView on GitHub

Guidelines for working with this skill repository. This repository stores AI coding agent skills — markdown files with YAML frontmatter. Not a traditional app codebase. Use pr-worktree-workflow skill for changes to this repo: Before committing code-rules or any skill: 1. Add something new → Is it documented? 2. Remove/rename → Old refs cleaned? 3. Change behavior → Docs updated? 4. Add dependencies → Recorded? 5. Add code needing docstring → Written?

  • Commits and pushes

The file

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

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use pr-worktree-workflow skill for changes to this repo:

    line 56
  2. Distinctive:

    Before committing code-rules or any skill:

    line 64
  3. Distinctive:

    Add something new → Is it documented?

    line 65
  4. Distinctive:

    Remove/rename → Old refs cleaned?

    line 66
  5. Distinctive:

    Add code needing docstring → Written?

    line 69
  6. Distinctive:

    All skill directories are self-contained

    line 74
  7. Distinctive:

    No build step — skills are markdown files discovered by the agent

    line 75

≈ “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

Guidelines for working with this skill repository.

Overview

This repository stores AI coding agent skills — markdown files with YAML frontmatter. Not a traditional app codebase.

Structure

./
├── README.md                      # Skill catalog
├── AGENTS.md                      # This file
├── CLAUDE.md                      # Claude Code config
├── code-rules/                    # Universal coding rules
│   ├── SKILL.md
│   └── languages/
├── pre-init/                      # Project scaffolding
│   ├── SKILL.md
│   ├── init.sh
│   └── templates/{python,lean4}/
├── mathlib-style/                 # Lean style guide
├── mathlib-workflow/              # Lean contribution
├── tmux/, ssh/, lmfdb-cli/        # Utility skills
└── openclaw-rss/

Where to Look

TaskLocation
New skill developmentCreate */SKILL.md with frontmatter
Lean 4 workmathlib-style/, mathlib-workflow/
Python project setuppre-init/templates/python/
Git worktree + PRpr-worktree-workflow/SKILL.md
Coding standardscode-rules/SKILL.md

Conventions

  • Skill names: kebab-case
  • SKILL.md frontmatter: name + description fields required
  • Descriptions: English, concise, include "Use when:" triggers
  • Examples: Practical, runnable

Anti-Patterns

  • ❌ Killing tmux sessions outside current project
  • ❌ Using $ instead of <| in Lean
  • ❌ fun x ↦ x instead of fun x => x in Lean
  • ❌ Empty lines inside Lean declarations
  • ❌ Committing without checking if docs need updating

Git Workflow

Use pr-worktree-workflow skill for changes to this repo:

gh pr create --fill

Pre-Commit Check

Before committing code-rules or any skill:

  1. Add something new → Is it documented?
  2. Remove/rename → Old refs cleaned?
  3. Change behavior → Docs updated?
  4. Add dependencies → Recorded?
  5. Add code needing docstring → Written?

Notes

  • Templates in pre-init/templates/ are defaults; users override via ~/.config/pre-init/
  • All skill directories are self-contained
  • No build step — skills are markdown files discovered by the agent

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.