open-skills
AGENTS.md15 starsChanged 12 days agoApache-2.0View on GitHub
These instructions apply to this repository. Read scope and CONTRIBUTING.md before changing skills or documentation. Glossary · Guides · Workflow recipes
In this repository95 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- agent-mailboxSkill
- agent-outputSkill
- ask-gateSkill
- ask-meSkill
- audit-coupled-constantSkill
- budget-checkSkill
- build-prototypeSkill
- caller-optionsSkill
- cold-reviewSkill
- debug-taskSkill
- define-termsSkill
- defuddleSkill
- design-an-interfaceSkill
- diff-recapSkill
- directives-auditSkill
- domain-checkSkill
- double-checkSkill
- extract-signalSkill
- freshness-contractSkill
- github-syncSkill
- handoff-executeSkill
- handoffSkill
- headless-claudeSkill
- headless-codexSkill
- headless-geminiSkill
- headless-grokSkill
- headless-modelsSkill
- headless-update-modelsSkill
- headless-usageSkill
- human-drawSkill
- human-mergeSkill
- human-outputSkill
- human-rewriteSkill
- implement-taskSkill
- improve-codebase-architectureSkill
- insight-adversarialSkill
- insight-anglesSkill
- insight-assessSkill
- insight-critiqueSkill
- insight-cross-examineSkill
- insight-exploreSkill
- insight-premortemSkill
- insight-reference-classSkill
- insight-retroSkill
- insight-root-causeSkill
- insight-skill-gapSkill
- insight-test-assumptionSkill
- insight-value-of-informationSkill
- investigateSkill
- json-canvasSkill
- map-checkSkill
- map-initSkill
- map-maintainSkill
- map-rulesSkill
- map-thisSkill
- monorepo-depsSkill
- multi-agent-modeSkill
- next-skillsSkill
- The first 60 shown.
The file
Files
Working on open-skills
These instructions apply to this repository. Read scope and CONTRIBUTING.md before changing skills or documentation.
- [open-skills.source] SKILL.md and its selected resources own skill behavior. Keep any protocol.yon aligned with that behavior; structural validity does not establish runtime obedience.
- [open-skills.scope] Make the smallest complete selected change. Preserve invocation policy, safeguards, dependencies and unrelated work; a recipe or conditional route can be enough without another skill.
- [open-skills.docs] Every public skill needs a source-grounded guide. Edit docs/skill-guides.json after reading its cited sources; tools/skill-docs.mjs defines the editorial model. Explain the reader's situation, mechanism, role, practical questions and recognizable result without inventing experience or behavior.
- [open-skills.generated] tools/spine.mjs owns catalogs, taxonomy projections, SKILLS.md, skills.sh.json and generated guides. tools/conformance.mjs owns CONFORMANCE.md. Do not hand-edit emitted files or refresh a source fingerprint without reconciling its guide.
- [open-skills.discovery] Add, rename or retire a skill together with its taxonomy assignment, guide disposition, README entry points and changelog. Counts and release versions move through their existing owners.
- [open-skills.installation] docs/installation.md owns shared installation/update wording. Keep source checks, installed bytes, runtime pickup and directory visibility as separate evidence claims. Existing links, editable copies and managed installs have different update owners.
- [open-skills.verification] Inspect command effects, then use proportionate checks for the actual candidate. Preserve recovery material outside public/discovery output and report failed or unrun checks. Do not turn optional examples or review into hidden dependencies.
- [open-skills.release] Follow the maintainer closeout in CONTRIBUTING.md. Record the exact intended scope and DCO identity before a commit. Editing does not itself authorize installation, deletion, Git publication or outreach.
Glossary · Guides · Workflow recipes
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.

