skillektion
AGENTS.md1 starsChanged 3 months agoMITView on GitHub
Skillektion publishes a curated flat catalog of portable agent skills. - skills/<name>/ is the exact independently installable artifact. - sources.json records whether each skill is owned, mirror, or adapted. - Edit owned and adapted skills directly. Refresh mirrors only through npm run sync. - Preserve complete skill directories, including scripts and references. - Keep third-party attribution in LICENSE.upstream, outside SKILL.md, and document every adapted skill's changes in SOURCE.md. - Give owned and adapted skills Codex presentation metadata. Encode manual-only invocation…
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 repository45 other files it gives its agents.
- blast-radiusSkill
- broSkill
- codebase-designSkill
- code-reviewSkill
- confluence-workflowSkill
- creating-a-pr-mrSkill
- defuddleSkill
- diagram-designSkill
- docxSkill
- domain-modelingSkill
- engineering-principlesSkill
- forgejo-cliSkill
- frontend-designSkill
- gh-cliSkill
- git-conventional-commitsSkill
- git-working-agreementSkill
- glab-cliSkill
- grillingSkill
- grill-meSkill
- grill-with-docsSkill
- howSkill
- improve-codebase-architectureSkill
- jira-workflowSkill
- json-canvasSkill
- k8s-opsSkill
- obsidian-basesSkill
- obsidian-cliSkill
- obsidian-markdownSkill
- openspec-workflowSkill
- pdfSkill
- pptxSkill
- prototypeSkill
- researchSkill
- setup-matt-pocock-skillsSkill
- skill-minerSkill
- technical-writingSkill
- theme-factorySkill
- to-specSkill
- to-ticketsSkill
- triageSkill
- unslopSkill
- wayfinderSkill
- whySkill
- writing-for-agentsSkill
- xlsxSkill
The file
We split this AGENTS.md into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
Keep third-party attribution in LICENSE.upstream, outside SKILL.md, and document every adapted skill's changes in SOURCE.md.
- Very specific: line 16
Do not add the reserved agent-memory or nix-home-manager-expert names.
- Very specific: line 20
Run npm test and npm run sync:check.
≈ “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
Skillektion publishes a curated flat catalog of portable agent skills.
Contract
skills/<name>/is the exact independently installable artifact.sources.jsonrecords whether each skill isowned,mirror, oradapted.- Edit owned and adapted skills directly. Refresh mirrors only through
npm run sync. - Preserve complete skill directories, including scripts and references.
- Keep third-party attribution in
LICENSE.upstream, outsideSKILL.md, and document every adapted skill's changes inSOURCE.md. - Give owned and adapted skills Codex presentation metadata. Encode manual-only
invocation in both
disable-model-invocationandagents/openai.yaml. - Do not add the reserved
agent-memoryornix-home-manager-expertnames.
Validation
Run npm test and npm run sync:check. The latter requires network access to
verify mirrors against their pinned upstream commits.
See CONTRIBUTING.md for the update workflow.
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.