agentleFS
alex-voloshin-devalex-voloshin-dev/ai-skills/.agents/skills/asset-validation/SKILL.md

asset-validation

Skill2 starsChanged 6 months agoMITView on GitHub

Validate Codex AI assets for size limits, frontmatter correctness, cross-reference integrity, runtime readiness, and parity safety after structural changes.

1 other project uses a version of this.

Adopted by

Most recently taken up by

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
  1. Very specific:

    Use this skill after modifying .agents/skills/ or .codex/ assets and before accepting a parity-impacting change.

    line 9
  2. Distinctive:

    no installer-specific or machine-specific commands remain

    line 47
  3. Very specific:

    Use validation-checklist.md for the detailed checklist.

    line 65

≈ “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.

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

Asset Validation

Use this skill after modifying .agents/skills/ or .codex/ assets and before accepting a parity-impacting change.

Validation Layers

1. Structure

Confirm the expected runtime layout exists:

  • .agents/skills/<name>/SKILL.md
  • .codex/roles/*.md
  • .codex/rules/*.md
  • .codex/operations/*.md
  • .codex/templates/*.md and .codex/checklists/*.md when applicable

2. Frontmatter and Format

Check:

  • SKILL.md contains at least name and description
  • optional codex-roles values resolve to both role and overlay files
  • AGENTS.md stays plain Markdown
  • markdown assets stay within repository size guidance where required

3. Cross-References

Verify:

  • skill references resolve to existing folders under .agents/skills/
  • role references resolve to existing files under .codex/roles/
  • overlay references resolve under .codex/rules/role-overlays/
  • operation docs point to existing Codex files and not stale Claude runtime paths

4. Runtime Readiness

Confirm:

  • assets assume the Codex runtime layout under .agents/skills/ and .codex/
  • Claude hook and settings behavior is translated into visible operation docs, not implied hidden automation
  • no installer-specific or machine-specific commands remain

5. Naming

  • role files use kebab-case.md
  • overlay files use the same role id as the matching role file
  • skill folders use kebab-case/
  • template files use consistent Codex naming

Report Format

Return:

  • Summary
  • Passed checks
  • Findings
  • Required follow-up

Use validation-checklist.md for the detailed checklist.

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.