agent-skills
AGENTS.md9 starsChanged 29 days agoMITView on GitHub
Collection of Codex / multi-agent skills published to skills.sh. npx is aliased to nvm in this shell — use the full binary path: See references/building-skills-guide.md for the complete guide to building skills (frontmatter, progressive disclosure, composability, testing, distribution). Skills appear on skills.sh after push + install (install count tracks discoverability).
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 repository13 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- agent-sessionsSkill
- apple-books-mcpSkill
- blender-mcpSkill
- cinema4d-mcpSkill
- figma-bridgeSkill
- figma-context-mcpSkill
- fluid-interfacesSkill
- pdf-look-scannedSkill
- reverse-engineer-jsSkill
- threejs-perf-loadingSkill
- time-lensSkill
- visual-feedback-loopSkill
The file
We split this AGENTS.md into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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 35
Create skills/<name>/SKILL.md with name and description frontmatter
- Very specific: line 36
Add scripts/references/assets as needed
- Distinctive: line 37
Update README.md with the new skill entry
≈ “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
agent-skills repo
Collection of Codex / multi-agent skills published to skills.sh.
Installing skills via npx skills
npx is aliased to nvm in this shell — use the full binary path:
~/.nvm/versions/node/v22.21.1/bin/npx skills <command>Install this repo's skills globally to Codex
~/.nvm/versions/node/v22.21.1/bin/npx skills add vladmdgolam/agent-skills -g -a Codex -yInstall a specific skill
~/.nvm/versions/node/v22.21.1/bin/npx skills add vladmdgolam/agent-skills --skill time-lens -g -a Codex -yList installed skills
~/.nvm/versions/node/v22.21.1/bin/npx skills listAdding a new skill
See references/building-skills-guide.md for the complete guide to building skills (frontmatter, progressive disclosure, composability, testing, distribution).
- Create
skills/<name>/SKILL.mdwithnameanddescriptionfrontmatter - Add scripts/references/assets as needed
- Update
README.mdwith the new skill entry - Commit and push
- Install globally:
~/.nvm/versions/node/v22.21.1/bin/npx skills add vladmdgolam/agent-skills --skill <name> -g -a Codex -y
Skills appear on skills.sh after push + install (install count tracks discoverability).
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
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.