Skill Crossroads audit-skill
rubric v1.2 · deterministic
A 96.3/100 overall
Correctness & Structure 100 pass
Triggering & Discoverability 100 pass
Clarity & Instructions 100 pass
Token & Context Cost 100 pass
Safety & Security 89 1 warn
Verifiability & Maintainability 80 1 warn

Top fixes — ranked by score impact

⚠ SAFETY-03 No destructive auto-invocation
SKILL.md:3auto-invocable (no disable-model-invocation) → performs a destructive action ("publishing")
Skill appears to "publishing" but the model can auto-invoke it — a destructive action could fire without the user asking.
publishing
Fix If this action is destructive/irreversible, set `disable-model-invocation: true` so it only runs when explicitly invoked.
⚠ VERIFY-01 Evals or tests present
SKILL.md:47the skill can be verified → a prose verification step, but no runnable evals/ or tests/
Manual verification only — add eval prompts with expected outcomes to make it checkable.
## Verify
Fix Add an evals/ folder with 2–3 test prompts and the expected assertions.
★ scores higher than ≈71% of 214 public skills (deterministic rubric v1.2 sample, 2026-07)

Embed this badge

Skill Crossroads grade A Always-fresh — it re-scans and updates on its own. 
[![Skill Crossroads](https://skillcrossroads.com/api/badge/sgharlow/skillcrossroads/skill.svg)](https://skillcrossroads.com/s/sgharlow/skillcrossroads/skill)
Grade your own Claude Code skill — evidence-cited, file-and-line, free. Scan your own skill →