template — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited template (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.
Replace this template. KeepSKILL.mdunder ~500 lines / 5k tokens. Push long detail intoreferences/, deterministic steps intoscripts/, and templates intoassets/. Claude reads those only when needed (progressive disclosure).
Two or three sentences on the capability and the outcome it produces.
The description frontmatter is what Claude actually reads to decide whether to load this skill — make it specific and include the triggering situation. Write it in the third person ("Generates…", "Audits…"), never first person.
python scripts/example.py <args>.
What the user/agent must provide.
What the skill produces, and where it goes.
Edge cases, things to avoid, required tools. Use forward-slash paths. Fully qualify any MCP tools as Server:tool. Don't assume packages are installed.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.