jara-r-kjara-r-k/claude-code-skills/skills/skill-compliance-checklist/AGENTS.md

claude-code-skills / skill-compliance-checklist

AGENTS.md1 starsChanged 46 days agoMITView on GitHub

Meta-skill that audits SKILL.md files against Anthropic's "Complete Guide to Building Skills for Claude" (Jan 2026): structure, frontmatter, description quality, progressive disclosure, error handling, examples, word count, and hard-coded IDs. Produces a 12-row PASS/FAIL table per skill and fix recommendations drawn from references/. The repo's manual pre-publish gate; user-invocable: true (/skill-compliance-checklist).

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 31,700 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 repository16 other files it gives its agents.
- agents/AGENTS.mdAGENTS.md
- AGENTS.mdAGENTS.md
- examples/AGENTS.mdAGENTS.md
- .github/AGENTS.mdAGENTS.md
- .github/workflows/AGENTS.mdAGENTS.md
- scripts/AGENTS.mdAGENTS.md
- skills/AGENTS.mdAGENTS.md
- skills/figma-handoff/AGENTS.mdAGENTS.md
- skills/github-pr-review/AGENTS.mdAGENTS.md
- skills/gmail-workflow/AGENTS.mdAGENTS.md
- skills/skill-compliance-checklist/references/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- figma-handoffSkill
- github-pr-reviewSkill
- gmail-workflowSkill
- skill-compliance-checklistSkill

The file

We split this AGENTS.md into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Run the local CI command from the root AGENTS.md.
line 37

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

AGENTS.md

skills/skill-compliance-checklist/

Purpose

Meta-skill that audits SKILL.md files against Anthropic's "Complete Guide to Building Skills for Claude" (Jan 2026): structure, frontmatter, description quality, progressive disclosure, error handling, examples, word count, and hard-coded IDs. Produces a 12-row PASS/FAIL table per skill and fix recommendations drawn from references/. The repo's manual pre-publish gate; user-invocable: true (/skill-compliance-checklist).

Key Files

File	Description
`SKILL.md`	Five-step audit (identify → structural check → content check → report table → recommend fixes), troubleshooting for upload/trigger/instruction problems, three invocation examples. v1.1.0, ~580 words
`references/compliance-template.md`	Frontmatter and body templates, progressive-disclosure levels, trigger/functional/performance test checklists
`references/guide-patterns.md`	The guide's five skill patterns and three use-case categories

Subdirectories

Directory	Purpose
`references/`	Material loaded on demand when recommending fixes (see `references/AGENTS.md`)

For AI Agents

Working In This Directory

Step 1 scans only ~/.claude/skills/*/SKILL.md, ~/.claude/scheduled-tasks/*/SKILL.md, .claude/agents/*.md, and user-given paths. --all therefore never reaches this repo's skills/ or examples/ — pass explicit paths, e.g. /skill-compliance-checklist skills/gmail-workflow/SKILL.md.
The 12-row table in Step 4 is the canonical criteria list. Changing a criterion is a functional change: bump metadata.version (currently 1.1.0) and keep references/compliance-template.md consistent.
Its error-handling section is ## Troubleshooting, which satisfies the CI heading check.
Several criteria go beyond CI (no "claude"/"anthropic" in the name, no hard-coded IDs, ## Important/## Critical headers); CI enforces only the frontmatter, description, and word-count rows.

Testing Requirements

Self-audit: /skill-compliance-checklist skills/skill-compliance-checklist/SKILL.md should pass every row.
Negative check: a description > 1024 chars, </> in the description, no error-handling section, or > 5,000 words must each FAIL.
Run the local CI command from the root AGENTS.md.

Common Patterns

Output: one compliance table per skill, then fixes citing references/compliance-template.md and references/guide-patterns.md by filename.

Dependencies

Internal

Audits figma-handoff, github-pr-review, gmail-workflow, and examples/persona-audit-pattern

Download now (ZIP)

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

What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free