agentleFS
sinediedsinedied/agent-skills/AGENTS.md

agent-skills

AGENTS.md4 starsChanged 5 months agoMITView on GitHub

Instructions for AI coding agents working in this repository. This repo is a personal collection of Agent Skills located under .agents/skills/. Each subfolder is a self-contained skill with a SKILL.md entry point, an LICENSE.md, and optional references/ and scripts/ folders. [!IMPORTANT] For anything related to the skill format itself — frontmatter fields, folder layout, progressive disclosure, naming conventions, etc. — refer to the official spec at <https://agentskills.io/>. Fetch <https://agentskills.io/llms.txt> first to discover the full documentation index before diving deeper. Whenever…

  • 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 32,671 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 repository8 other files it gives its agents.

The file

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

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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
  1. Distinctive:

    Add, remove, or update the row in the Skills table (keep entries in alphabetical order by skill name).

    line 18
  2. Very specific:

    Update the Skills-N badge count in the header to reflect the current number of skills.

    line 19
  3. Distinctive:

    If the skill changes what it does, refresh its one-liner description in the table (and any matching example in the Usage section if …

    line 20
  4. Distinctive:

    When adding or reviewing a skill, ensure that:

    line 24
  5. Very specific:

    If a license file exists under a different name or extension (e.g.

    line 27

≈ “Common” is an estimate: at least 1 in 5 of the 41,581 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

Instructions for AI coding agents working in this repository.

Repository purpose

This repo is a personal collection of Agent Skills located under .agents/skills/. Each subfolder is a self-contained skill with a SKILL.md entry point, an LICENSE.md, and optional references/ and scripts/ folders.

[!IMPORTANT] For anything related to the skill format itself — frontmatter fields, folder layout, progressive disclosure, naming conventions, etc. — refer to the official spec at https://agentskills.io/. Fetch https://agentskills.io/llms.txt first to discover the full documentation index before diving deeper.

Rules

Keep README.md in sync with the skills

Whenever a skill is added, renamed, removed, or has its purpose changed, you must update the root README.md accordingly:

  • Add, remove, or update the row in the Skills table (keep entries in alphabetical order by skill name).
  • Update the Skills-N badge count in the header to reflect the current number of skills.
  • If the skill changes what it does, refresh its one-liner description in the table (and any matching example in the Usage section if relevant).

Every skill must have an MIT LICENSE.md

When adding or reviewing a skill, ensure that:

  • The skill folder contains a LICENSE.md file with the MIT License, copyright Yohan Lasorsa, matching the root LICENSE.md.
  • If a license file exists under a different name or extension (e.g. LICENSE, LICENSE.txt), rename it to LICENSE.md (use git mv to preserve history).
  • The skill's SKILL.md frontmatter includes the line:
    license: Complete terms in LICENSE.md

Skill structure

A skill folder follows this layout:

.agents/skills/<skill-name>/
├── SKILL.md          # required — entry point with YAML frontmatter
├── LICENSE.md        # required — MIT, copyright Yohan Lasorsa
├── scripts/          # optional — executable helpers
├── references/       # optional — additional docs the skill can load
├── assets/           # optional — templates and other resources
└── ...               # any additional files or directories

The SKILL.md frontmatter must include at least name and description (per the agentskills.io spec), plus license: Complete terms in LICENSE.md for this repo.

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.