agentsclimarketplace

Audit router

Skill Data-Wise/craft/skills/code/audit-router

This skill should be used when the user asks to "audit commands", "check command frontmatter", "audit skills", "check skill standards", "validate command/skill health", or invokes `/craft:code:command-audit` or `/craft:code:skill-standards`. Shared vocabulary + reference bodies for craft's two schema-audit commands — both validate craft's own frontmatter (commands/skills/agents vs `_schema.json`, or `skills/**/SKILL.md` vs Anthropic's authoring standards) and share the same `--format`/`--fix` semantics. Not for dependency or docs-site checks — see `/craft:code:deps-audit`, `/craft:code:deps-check`, `/craft:code:docs-check` instead, which are unrelated generic cross-project tools despite living in the same `commands/code/` directory.From its SKILL.md

Install
npx -y skills add Data-Wise/craft --skill audit-router

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.1 KB, as published. Nobody here has run it

Audit Router — Shared Vocabulary for craft's Schema-Audit Commands

Two commands audit craft's own frontmatter against a schema and share one vocabulary:

CommandValidatesAgainst
/craft:code:command-auditcommands/, skills/, agents/ frontmatter_schema.json
/craft:code:skill-standardsskills/**/SKILL.mdvendored Anthropic authoring standards (docs/reference/SKILL-STANDARDS.md)

Both commands stay independently slash-invocable — this skill holds the shared vocabulary and each command's full reference body, not a replacement entry point.

Shared Flag Vocabulary

Both commands accept the same two flags with the same meaning:

  • --format terminal|json|markdown — output rendering only, default terminal. Never changes what is checked.
  • --fix — auto-fixes safe mechanical issues only, never prose or descriptions:
    • command-audit --fix: removes invalid frontmatter fields, renames args → arguments.
    • skill-standards --fix: strips rot-prone version tags from reference headers, normalizes frontmatter key casing/order, inserts TOC stubs in oversized reference files.

Both share the same health-score formula (100 − errors×5 − warnings×2, floored at 0) and the same exit-code convention (0 clean, 1 warnings-only, 2 errors — command-audit --strict also treats warnings as errors, matching skill-standards' own error-severity checks).

skill-standards carries one extra flag (--refresh-standards) with no command-audit equivalent — documented in its own reference only, not promoted to the shared set.

Full Reference Bodies

Not This Skill

deps-audit, deps-check, docs-check are not schema-audit-shaped — they're generic cross-project tools (dependency security/freshness for any project, or a full docs/site preflight+deploy pipeline) with incompatible flag surfaces. They stay independent commands with their own bodies, not references under this skill.

Keep looking

Skills are one crate of 627,801. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.