rewrite-descriptions — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited rewrite-descriptions (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/write-protocol.md | Write discipline for the proposal file |
references/rewriting-patterns.md | Patterns specific to description fixes |
templates/proposal-skeleton.md | Output file shape |
Given a collision pair, produce a concrete description rewrite proposal for each side. The output is a Markdown file with before/after blocks the user copies into the SKILL.md files manually.
{{ pair }} — either skill-a,skill-b or a single skill name. If single, read plugin-gardener/audit/ for the latest collisions.md and pick the top unresolved collision involving that skill.description + optional when_to_use.references/rewriting-patterns.md. Every rewrite must:description + when_to_use under 1,536 characters (skill listing cap).Do NOT use when the user mentions [sibling-domain-term].Use when the user asks to … clause structure if it was already there.plugin-gardener/audit/ad-hoc/rewrite-<skill-a>-vs-<skill-b>-<YYYY-MM-DD>.md using templates/proposal-skeleton.md.The user applies the rewrite manually. After applying, invoke /audit-skill <name> on both sides to confirm the collision is resolved.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.