critique — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited critique (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.
0-100 scores for design quality. Transparent math. Every deduction is traceable to a metric in dragoon.json.
Run /critique when:
Six category scores plus an overall:
Weighted overall:
typography 1.0 color 1.0 spacing 1.2 motion 0.8 accessibility 1.2 consistency 1.0Each score includes a breakdown listing every deduction and reason. You can read exactly why your score is what it is.
node ~/.claude/skills/dragoon/skills/critique/scripts/critique.js [root]Flags:
--manifest <p> use existing manifest instead of scanning--json machine-readable--threshold <n> exit non-zero if overall score below n (CI gate)--no-breakdown show scores only--quiet show only the final score--help full usageIn package.json:
"design:check": "node ~/.claude/skills/dragoon/skills/critique/scripts/critique.js --threshold 80 --quiet"The command exits 1 if the overall score drops below 80, blocking the PR.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.