skill.md:1the skill works → no evals/, tests/, or verification section found
No way to prove the skill does what it claims.
Fix Add an evals/ folder (test prompts + expected outcomes) and a '## Verify' step in the body.
overall
Correctness & Structure
100
pass
Triggering & Discoverability
100
pass
Clarity & Instructions
100
pass
Token & Context Cost
91
1 warn
Safety & Security
89
1 warn
Verifiability & Maintainability
53
1 fail
Top fixes — ranked by score impact
skill.md:17auto-invocable (no disable-model-invocation) → performs a destructive action ("Deploying")
Skill appears to "Deploying" but the model can auto-invoke it — a destructive action could fire without the user asking.
Deploying
Fix If this action is destructive/irreversible, set `disable-model-invocation: true` so it only runs when explicitly invoked.
skill.mdeverything inlined in SKILL.md → 373 body lines, 0 supporting files
Large SKILL.md (373 lines) with no supporting files — all of it loads every time the skill fires.
Fix Move heavy reference material into supporting files and link to them, so the model loads it only when needed.
★ scores higher than ≈41% of 208 public skills (deterministic rubric v1.2 sample, 2026-09)
Embed this badge
Always-fresh — it re-scans and updates on its own.
Grade your own Claude Code skill — evidence-cited, file-and-line, free.
Scan your own skill →