audit-skill — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited audit-skill (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
| Reference | When to load |
|---|---|
../../references/rubric.md | The scoring rubric (shared) |
../../references/write-protocol.md | Write discipline |
templates/scorecard-skeleton.md | Output file shape |
Score one skill against the 7-dimension rubric. The skill is the input; a scorecard Markdown file is the output.
{{ skill }} to an absolute path. Accept either a directory path (skills/research) or a bare skill name (research) — glob for the matching SKILL.md.${CLAUDE_PLUGIN_ROOT}/references/rubric.md.references/, every file under templates/. The scorecard is grounded in what's in the files, not in the description alone. Reading is the primary work./gardener audit exists at plugin-gardener/audit/, read its latest collisions.csv and clusters.csv for cross-reference context. Collisions involving this skill inform Dimension 1 (description quality) and Dimension 5 (proactive-label discipline) — check whether the description carries the right negative-keyword discriminators. For every collision row, open the sibling SKILL.md and verify by reading, not from the cosine alone.plugin-gardener/audit/ad-hoc/<skill-name>-<YYYY-MM-DD>.md using templates/scorecard-skeleton.md.Apply the rubric dimension by dimension. Record a short rationale (1–2 sentences with a file:line citation from the files you read) for every criterion scoring under 3 points. The rationale is the value; the number is the aggregate.
On the role of embedding data: collisions and clusters from a prior /gardener run are binoculars, not the photograph. They point you at the right cross-references to open. Verify every flagged collision by reading both SKILL.md files — a high cosine is an invitation to investigate, not a verdict.
/gardener run flags a skill — re-score to confirm the issue.The scorecard is the deliverable. Changes are the user's to apply.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.