authoring-skills
Skill1 starsChanged 5 months agoMITView on GitHub
Guide for authoring new skills that integrate with the Vibe Coding OS skill system. Covers frontmatter (name, version, introduced_in, last_reviewed, category, tags, status), required sections (Purpose, When to use, Inputs, Workflow, Outputs, Failure modes, Verification checklist, Examples), and the per-skill example convention (see templates/skill-example-template.md). When you are about to create a new skill file in skills/<category>/<skill-name>/SKILL.md. Read this guide first to ensure your skill passes validate:skill-quality and validate:traceability on the first try.
10 other projects use a version of this.
Adopted by
Most recently taken up by
- PuntoyComaTech/hermes-agent-squadstheir own version, first seen Nov 1, 2026
- LucasDevKid9/collab-chartertheir own version, first seen Nov 1, 2026
- mohmaedeslam00116/waypowertheir own version, first seen Oct 15, 2026
- syntropic137/software-leverage-pointstheir own version, first seen Oct 14, 2026
- flutter/devtoolstheir own version, first seen Oct 9, 2026
- louisbrillet/cor-skillstheir own version, first seen Sep 18, 2026
Other versions10 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 10
- vercel/next.js★ 143ksame name
- flutter/devtools★ 1.7ksame name
- andrueandersoncs/claude-skill-authoring-skill★ 11same name
- louisbrillet/cor-skills★ 4same name
- PuntoyComaTech/hermes-agent-squads★ 3same name
- LucasDevKid9/collab-charter★ 1same name
- forsonny/DG-Anvil★ 0same name
- larsch/skills★ 0same name
- mohmaedeslam00116/waypower★ 0same name
- syntropic137/software-leverage-points★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository117 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- advanced-orchestrationSkill
- architect-agentSkill
- implementer-agentSkill
- quality-councilSkill
- reviewer-agentSkill
- tester-agentSkill
- writer-critic-pairSkill
- api-endpoint-qualitySkill
- async-job-qualitySkill
- auth-qualitySkill
- db-migration-qualitySkill
- frontend-state-qualitySkill
- acceptance-criteriaSkill
- adaptive-flowSkill
- adaptive-prompt-selectionSkill
- adversarial-code-reviewSkill
- architecture-decision-recordsSkill
- brainstormingSkill
- brownfield-spec-enhancementSkill
- bug-fix-lifecycleSkill
- checkpoint-validationSkill
- cicd-integrationSkill
- clarify-before-codeSkill
- claude-code-hooks-packSkill
- code-context-packSkill
- code-intelligence-reviewSkill
- context-policySkill
- context-rich-implementationSkill
- crash-proof-planningSkill
- critique-pass-protocolSkill
- dependency-aware-task-orderingSkill
- deprecation-migrationSkill
- disciplined-diagnosisSkill
- docs-authorSkill
- executing-plansSkill
- external-skillSkill
- finishing-a-development-branchSkill
- git-guardrailsSkill
- goal-driven-executionSkill
- grill-user-before-buildingSkill
- guard-bypass-protocolSkill
- improve-codebase-architectureSkill
- incremental-reviewSkill
- issue-slicingSkill
- lessons-learned-dbSkill
- loop-engineeringSkill
- model-aware-configSkill
- model-weakness-memorySkill
- multi-repo-learningSkill
- orchestration-workflowsSkill
- plan-driven-executionSkill
- plan-from-specSkill
- prd-from-contextSkill
- project-constitutionSkill
- prompt-architectureSkill
- prototype-before-commitmentSkill
- quality-engineSkill
- quality-execution-contractSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
3
Distinctive
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 19
When you are about to create a new skill file in skills/<category>/<skill-name>/SKILL.md.
- Distinctive: line 25
Use case (3-5 trigger phrases)
- Distinctive: line 32
Add YAML frontmatter with all required fields.
- Distinctive: line 33
Write the body in this order: Purpose → When to use → Inputs → Workflow → Outputs → Failure modes → Verification checklist → Examples.
- Very specific: line 34
Run npm run validate:skill-quality to confirm compliance.
- Very specific: line 35
If a regression test is needed, follow templates/skill-test-template.md.
“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Skill: Authoring Skills
Purpose
Guide for authoring new skills that integrate with the Vibe Coding OS skill system. Covers frontmatter (name, version, introduced_in, last_reviewed, category, tags, status), required sections (Purpose, When to use, Inputs, Workflow, Outputs, Failure modes, Verification checklist, Examples), and the per-skill example convention (see templates/skill-example-template.md).
When to use
When you are about to create a new skill file in skills/<category>/<skill-name>/SKILL.md. Read this guide first to ensure your skill passes validate:skill-quality and validate:traceability on the first try.
Inputs
- Skill purpose (one sentence)
- Target category (core, prompts, agents, meta, quality, security, memory, etc.)
- Use case (3-5 trigger phrases)
- Failure modes (what could go wrong)
Workflow
- Draft the skill's purpose in 1-2 sentences.
- List 3-5 "When to use" trigger phrases.
- Add YAML frontmatter with all required fields.
- Write the body in this order: Purpose → When to use → Inputs → Workflow → Outputs → Failure modes → Verification checklist → Examples.
- Run
npm run validate:skill-qualityto confirm compliance. - If a regression test is needed, follow
templates/skill-test-template.md.
Outputs
- A new SKILL.md file in the appropriate
skills/<category>/<skill-name>/directory. - A passing
validate:skill-qualityrun.
Failure modes
- Missing frontmatter — gate FAIL on
validate:skill-quality. Add all required fields. - Missing required sections — gate FAIL. Use the section order above.
- No examples — convention recommends 3 (trivial/standard/advanced). Use
templates/skill-example-template.md. - Stale skill —
last_reviewedis too old. Update when the skill changes. - No test file — convention recommends 1 test per top-20 priority skill. See Wave B Deliverable 4.
Verification checklist
- YAML frontmatter is valid (parse with
js-yaml) - All required sections present in the correct order
- At least 1 example included
last_revieweddate is currentvalidate:skill-qualityexits 0- Linked from at least one adapter or command (no orphan skills)
- Optional: test file at
tests/skills/<skill-name>.test.mjs
Related files
- See
skills/SKILL.mdfor the canonical template.
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.

