iuryszaiurysza/agent-skills/AGENTS.md

agent-skills

AGENTS.md5 starsChanged 11 days agoMITView on GitHub

Canonical source for Iury Souza's shareable Agent Skills. There are no versioned releases. This repo's skills live under skills/, not .agents/skills/ or .cursor/skills/. scripts/validate.sh, scripts/compat-test.sh, and scripts/smoke-test.sh exec that same script. Run it before committing. CI (.github/workflows/ci.yml): plus a Node 18 job for skills/skill-cleaner/scripts/skill-cleaner.mjs. Never include Cursor (or any Cursor agent/bot) as git author, committer, or in a Co-authored-by / similar trailer.

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 repository23 other files it gives its agents.
- architecture-knowledge-baseSkill
- audio-transcribeSkill
- better-uiSkill
- brainstormingSkill
- broSkill
- chatgpt-imagegenSkill
- coding-standardsSkill
- decision-roomSkill
- deslopifySkill
- domain-modelingSkill
- frontend-designSkill
- gemini-ttsSkill
- goalSkill
- readbackSkill
- rephraseSkill
- reply-broSkill
- setup-goalSkill
- skill-cleanerSkill
- strunk-writing-qualitySkill
- technical-writingSkill
- tech-specSkill
- tool-installSkill
- type-breakdownSkill

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
could be automatic: a setting could enforce it

Very specific:
Keep skills under skills/<name>/SKILL.md.
line 22
Distinctive:
Use only Agent Skills specification fields.
line 23
Very specific:
Use relative paths. Never commit personal state, secrets, caches, virtual environments, generated media, or node_modules.
line 24
Distinctive:
Keep bundled scripts self-contained.
line 25
Distinctive:
Never include Cursor (or any Cursor agent/bot) as git author, committer, or in a Co-authored-by / similar trailer.
line 51

≈ “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

Agent instructions

Canonical source for Iury Souza's shareable Agent Skills. There are no versioned releases.

Map

Path	Role
`skills/<name>/SKILL.md`	Catalog skills. Frontmatter `name` matches the directory.
`scripts/check.sh`	Default closed loop.
`scripts/bootstrap.sh`	Install the catalog into user-level skill folders.
`.github/workflows/ci.yml`	PR/`main` CI.
`ai-artifacts/_index.md`	How the catalog works. Keep current; grow design notes under `ai-artifacts/`.
`README.md`	Install and skill list.
`CONTRIBUTING.md`	Add a skill.
`THIRD_PARTY_NOTICES.md`, `LICENSE`	Attribution.

This repo's skills live under skills/, not .agents/skills/ or .cursor/skills/.

Rules

Keep skills under skills/<name>/SKILL.md. Match frontmatter name to the directory.
Use only Agent Skills specification fields.
Use relative paths. Never commit personal state, secrets, caches, virtual environments, generated media, or node_modules.
Keep bundled scripts self-contained; real CLIs belong in their own repositories.
Preserve upstream attribution in THIRD_PARTY_NOTICES.md and the root LICENSE.
How-the-catalog-works docs belong in ai-artifacts/ and must stay current.
main is a rolling catalog. Do not create version tags or GitHub releases.

Closed loop

./scripts/check.sh

scripts/validate.sh, scripts/compat-test.sh, and scripts/smoke-test.sh exec that same script. Run it before committing.

CI (.github/workflows/ci.yml):

./scripts/validate.sh
gh skill publish --dry-run
./scripts/compat-test.sh
./scripts/smoke-test.sh

plus a Node 18 job for skills/skill-cleaner/scripts/skill-cleaner.mjs.

Git commits

Never include Cursor (or any Cursor agent/bot) as git author, committer, or in a Co-authored-by / similar trailer.

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