awesome-skills
AGENTS.md1 starsChanged 44 days agoMITView on GitHub
Guidance for AI agents (Hermes, Claude, Codex, Cursor, Windsurf, Roo/Cline, OpenCode, AGY, …) that work in this repository. Read this before editing. awesome-skills is a public, community-maintained catalog of reusable Skills, Agents, and Plugins for AI agents. Every entry is procedural memory that must work across multiple runtimes from a single canonical SKILL.md. 1. One canonical SKILL.md per skill (Hermes format). Adaptors (CLAUDE.md, manifest.json) must only reference or translate — never duplicate logic. 2. No secrets — tokens, keys, passwords…
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 repository125 other files it gives its agents.
- skill-authoringSkill
- apple-notesSkill
- apple-remindersSkill
- findmySkill
- imessageSkill
- agy-customizationsSkill
- antigravity-guideSkill
- awesome-skills-masterSkill
- claude-codeSkill
- codexSkill
- computer-useSkill
- context-modeSkill
- dogfoodSkill
- hermes-agentSkill
- opencodeSkill
- rag-local-lancedbSkill
- skills-sh-registrySkill
- watermarks-removerSkill
- yuanbaoSkill
- libretranslate-markdown-i18nSkill
- mt-markup-preserving-translationSkill
- architecture-diagramSkill
- ascii-artSkill
- ascii-videoSkill
- baoyu-infographicSkill
- claude-designSkill
- comfyuiSkill
- design-mdSkill
- excalidrawSkill
- humanizerSkill
- manim-videoSkill
- p5jsSkill
- popular-web-designsSkill
- portfolio-github-pagesSkill
- pretextSkill
- sketchSkill
- songwriting-and-ai-musicSkill
- touchdesigner-mcpSkill
- jupyter-live-kernelSkill
- suap-iff-apiSkill
- desktop-themingSkill
- hermes-desktop-pluginsSkill
- docker-single-port-multi-instanceSkill
- hybrid-desktop-server-opsSkill
- himalayaSkill
- codebase-inspectionSkill
- git-conventional-commitsSkill
- github-authSkill
- github-code-reviewSkill
- github-issue-pr-attribsSkill
- github-issuesSkill
- github-profile-readmeSkill
- github-pr-workflowSkill
- github-repo-managementSkill
- github-starred-kbSkill
- hermes-installed-catalogSkill
- readme-templateSkill
- cv-latex-multilingualSkill
- latex-cv-maintenanceSkill
- gif-searchSkill
- The first 60 shown.
The file
We split this AGENTS.md into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
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
- Very specific: line 20
pure: no leaked credentials (keys/tokens/secrets) and no proprietary or closed-source code.
- Distinctive: line 22
Never embed a real token, signed request, or internal endpoint.
- Very specific: line 42
Follow templates/ for new skills/agents/plugins.
- Distinctive: line 45
Verify locally (below). No verification → no merge.
≈ “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.
Files
AGENTS.md — awesome-skills
Guidance for AI agents (Hermes, Claude, Codex, Cursor, Windsurf, Roo/Cline, OpenCode, AGY, …) that work in this repository. Read this before editing.
Purpose
awesome-skills is a public, community-maintained catalog of reusable
Skills, Agents, and Plugins for AI agents. Every entry is procedural memory
that must work across multiple runtimes from a single canonical SKILL.md.
Hard rules
- One canonical
SKILL.mdper skill (Hermes format). Adaptors (CLAUDE.md,manifest.json) must only reference or translate — never duplicate logic. - No secrets — tokens, keys, passwords never in body or scripts. Use env / secret store. Fail closed (non-zero exit) on error.
- API purity — anything touching
*API*(specs, wrappers, clients) must be pure: no leaked credentials (keys/tokens/secrets) and no proprietary or closed-source code. Use only public specs, fictional examples, and stubs. Never embed a real token, signed request, or internal endpoint. - Multi-tool compatible — if it only works in one runtime, it does not belong here.
- Idempotent scripts — safe to run more than once.
- Verifiable — ship a check, or state the blocker explicitly.
- KISS/DRY — concise instructions, concrete examples, no noise.
Structure
skills/<category>/<name>/ # SKILL.md + references/ + scripts/ + templates/
templates/ # starter kits: skill / agent / plugin
docs/CODE_REVIEW.md # review standard
tools/gen_index.py # regenerates README.md from SKILL.md
.github/ # ISSUE_TEMPLATE + PULL_REQUEST_TEMPLATEWorkflow (every change)
- Branch from
main:feat/...,fix/...,docs/...,chore/.... - Follow
templates/for new skills/agents/plugins. - Never hand-edit the README above the Index/Contributing sections —
run
python3 tools/gen_index.pyinstead. - Verify locally (below). No verification → no merge.
- Open a PR with the seven standard assignment fields (see
CONTRIBUTING.md): Assignee, Reviewer, Labels, Project, Milestone, Development, Relationship. - Review per
docs/CODE_REVIEW.md(severity table + rubrics). - Merge
--rebase; delete the branch.
Verification (run before committing)
python3 tools/gen_index.py
python3 -c "import yaml; yaml.safe_load(open('skills/<cat>/<name>/SKILL.md').read().split('---')[1]); print('SKILL_OK')"
python3 -c "import json; json.load(open('templates/.../manifest.json')); print('MANIFEST_OK')"The CI workflow (.github/workflows/ci.yml) runs the same checks on every PR.
Conventions
- Frontmatter:
name,description,version,author,license,platforms,metadata.hermes.tags— all present. descriptionis imperative and states when to use the skill.- Tags drive discoverability; pick 3–6 accurate ones.
- Releases are semver tags (
vMAJOR.MINOR.PATCH);Backlogis the default milestone for unscheduled work.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

