ai-component-metadata
Skill2 starsChanged 46 days agoApache-2.0View on GitHub
Audit and enrich Agentica component metadata to verify a component is "agent-ready" — has the structured intent, variants, rules, accessibility, behavior, dependencies, anti-patterns, owner, approval level, and version an agent needs to analyze, validate, and use it correctly. Use when asked to audit component metadata, check if a component is agent-ready, or score component completeness.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- thedesignproject/agent-skillstheir own version, first seen Jun 4, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- thedesignproject/agent-skills★ 101same 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 repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ai-ds-composerSkill
- codebase-indexSkill
- documentSkill
- post-change-pipelineSkill
- quality-gateSkill
- ux-pattern-reviewSkill
- ai-component-metadataSkill
- ai-ds-composerSkill
- codebase-indexSkill
- documentSkill
- post-change-pipelineSkill
- quality-gateSkill
- ux-pattern-reviewSkill
- design-system-builderSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Ensure every component has the structured metadata an agent needs to analyze, validate, and use it correctly.
- Very specific: line 40
Read the .md file
- Very specific: line 41
Read the matching token in tokens/component.json
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill 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
Skill: ai-component-metadata
Cross-tool port of
.claude/skills/ai-component-metadata/SKILL.md(Claude Code's native implementation) — seegovernance/ai-skills-reference.mdfor the full picture of what Agentica's skills automate. This file follows the open Agent Skills format (agentskills.io) so Codex CLI and GitHub Copilot CLI load it automatically from.agents/skills/; content is identical in substance to the Claude Code version.
Objective
Ensure every component has the structured metadata an agent needs to analyze, validate, and use it correctly.
Required metadata — checklist
For each component, verify the presence of:
✅ intent — Why this component exists
✅ variants — List of allowed variants
✅ rules — Usage rules (when to use, when not to use)
✅ accessibility — WCAG requirements (contrast, focus, ARIA)
✅ behavior — States, animations, special interactions
✅ dependencies — Tokens and components it depends on
✅ antiPatterns — What must never be done with this component
✅ owner — Who is responsible
✅ approvalLevel — What approval level is required to modify it
✅ version — Current contract versionMetadata audit process
Step 1 — Inventory
For each component in guidelines/components/:
- Read the
.mdfile - Read the matching token in
tokens/component.json - Compare the two to detect gaps
Step 2 — Scoring
Compute a completeness score:
- 10 required fields × 10 points = 100 points possible
- Score < 70: component not agent-ready → flag it
- Score 70–89: partially agent-ready → improvement recommended
- Score ≥ 90: agent-ready ✅
Step 3 — Report
Produce a structured report:
## Metadata report — [DATE]
| Component | Score | Missing | Priority |
|-----------|-------|---------|----------|
| button | 100% | — | ✅ |
| input | 70% | antiPatterns, approvalLevel | 🟡 |
| modal | 40% | rules, accessibility, behavior, dependencies | 🔴 |
### Recommendations
[List of actions to take, in priority order]Step 4 — Do not modify without approval
This skill only produces reports and suggestions. Never modify files directly.
Enriched metadata format (JSON example)
{
"component": {
"button": {
"$metadata": {
"intent": "Trigger an action in the interface",
"variants": ["primary", "secondary", "critical", "ghost"],
"rules": [
"Maximum 1 primary button per section",
"The critical button requires confirmation"
],
"accessibility": {
"minimumContrast": "4.5:1",
"requiresFocusVisible": true,
"ariaAttributes": ["aria-label if no visible text", "aria-disabled"]
},
"antiPatterns": [
"Two primary buttons side by side",
"Generic label ('OK' or 'Confirm') alone for a critical button"
],
"owner": "design-system-team",
"approvalLevel": "principal-designer",
"version": "2.1.0"
}
}
}
}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.

