claude-code-skills / references
AGENTS.md1 starsChanged 47 days agoMITView on GitHub
Reference material for the skill-compliance-checklist skill, kept out of SKILL.md (progressive disclosure) and loaded only when recommending fixes. Holds the frontmatter/body template and a summary of the five official skill patterns and three use-case categories from Anthropic's Jan 2026 guide.
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/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
2 rules. About 0 are common, 0 are distinctive, and 2 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 23
When Anthropic revises the guide, update guide-patterns.md and bump the parent skill's metadata.version.
- Very specific: line 28
No automated tests. After editing, check that compliance-template.md still yields a SKILL.md that passes the parent skill's 12 criteria and …
≈ “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
<!-- Parent: ../AGENTS.md --><!-- Generated: 2026-06-30 | Updated: 2026-09-27 -->skills/skill-compliance-checklist/references/
Purpose
Reference material for the skill-compliance-checklist skill, kept out of SKILL.md (progressive disclosure) and loaded only when recommending fixes. Holds the frontmatter/body template and a summary of the five official skill patterns and three use-case categories from Anthropic's Jan 2026 guide.
Key Files
| File | Description |
compliance-template.md | Frontmatter template, description formula [WHAT] + [WHEN] + [CAPABILITIES] with good/bad examples, body template (Instructions / Error Handling / Examples / Important), progressive-disclosure checklist (Levels 1–3), trigger/functional/performance test checklists |
guide-patterns.md | Five patterns (sequential workflow orchestration, multi-MCP coordination, iterative refinement, context-aware tool selection, domain-specific intelligence) and three use-case categories (Document & Asset Creation, Workflow Automation, MCP Enhancement) — listed separately, not mapped to each other |
For AI Agents
Working In This Directory
SKILL.mdStep 5 cites both files by name — keep filenames stable or updateSKILL.mdin the same change.- The frontmatter template here omits
user-invocableandmetadata.based-on, which the rootCLAUDE.mdSkill Format includes; update both together if the convention changes. - When Anthropic revises the guide, update
guide-patterns.mdand bump the parent skill'smetadata.version. - CI does not validate these files.
Testing Requirements
- No automated tests. After editing, check that
compliance-template.mdstill yields aSKILL.mdthat passes the parent skill's 12 criteria and the local CI command in the rootAGENTS.md.
Common Patterns
- Progressive disclosure: Level 1 = frontmatter (when to load), Level 2 =
SKILL.mdbody (how to execute, < 5,000 words), Level 3 =references/(loaded on demand).
<!-- MANUAL: -->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.