RiccardoGrinRiccardoGrin/skills/AGENTS.md

skills

AGENTS.md5 starsChanged 8 months agoMITView on GitHub

CLAUDE.md is a symlink to this file. Edit AGENTS.md only — CLAUDE.md will stay in sync automatically. Content-only repository of reusable agent skills. Skills installed via npx skills add <username>/skills or manual copy to ~/.claude/skills/. The CLI scans for SKILL.md files inside skills/ directories.

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 31,542 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 repository15 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- being-carefulSkill
- creating-skillsSkill
- creating-spritesSkill
- designing-frontendSkill
- enforcing-architectureSkill
- freezing-editsSkill
- generating-game-changelogsSkill
- initializing-projectsSkill
- listing-docsSkill
- looping-tasksSkill
- planning-loopSkill
- planningSkill
- reviewing-codeSkill
- transcribing-youtubeSkill

The file

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

8 rules. About 0 are common, 3 are distinctive, and 5 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.
5
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
Do: use gerund-form kebab-case for skill names (creating-skills, not skill-creator)
line 13
Very specific:
Do: use /creating-skills when authoring or modifying a skill — it covers the full workflow, format spec, and validation
line 14
Distinctive:
Do: one sentence per line in markdown body text (for clean diffs)
line 15
Distinctive:
Do: one skill per PR; include a real-usage test result in the PR description
line 16
Very specific:
Do: update the Available Skills table in README.md when adding or removing a skill
line 17
Very specific:
Don't: add external Python dependencies unless declared in SKILL.md with a requirements.txt in scripts/
line 18
Distinctive:
Don't: use backslash paths — always forward slashes
line 19
Very specific:
When renaming folders or reference files, grep all SKILL.md files for stale paths
line 25

≈ “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

CLAUDE.md is a symlink to this file. Edit AGENTS.md only — CLAUDE.md will stay in sync automatically.

Overview

Content-only repository of reusable agent skills. Skills installed via npx skills add <username>/skills or manual copy to ~/.claude/skills/. The CLI scans for SKILL.md files inside skills/ directories.

Do / Don't

Do: use gerund-form kebab-case for skill names (creating-skills, not skill-creator)
Do: use /creating-skills when authoring or modifying a skill — it covers the full workflow, format spec, and validation
Do: one sentence per line in markdown body text (for clean diffs)
Do: one skill per PR; include a real-usage test result in the PR description
Do: update the Available Skills table in README.md when adding or removing a skill
Don't: add external Python dependencies unless declared in SKILL.md with a requirements.txt in scripts/
Don't: use backslash paths — always forward slashes

Gotchas

Frontmatter (name, description) is required — skills without it won't be indexed
Reference files must be linked from SKILL.md body or they won't be discovered
When renaming folders or reference files, grep all SKILL.md files for stale paths

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