Skill Crossroads data-cleanup
rubric v1.2 · deterministic
A+ 98.3/100 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 100 pass

Top fixes — ranked by score impact

⚠ SAFETY-03 No destructive auto-invocation
SKILL.md:24auto-invocable (no disable-model-invocation) → performs a destructive action ("delete")
Skill appears to "delete" but the model can auto-invoke it — a destructive action could fire without the user asking.
delete
Fix If this action is destructive/irreversible, set `disable-model-invocation: true` so it only runs when explicitly invoked.
★ scores higher than ≈87% 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/claude-code-recipes/skills/data-cleanup.svg)](https://skillcrossroads.com/s/sgharlow/claude-code-recipes/skills/data-cleanup)
Grade your own Claude Code skill — evidence-cited, file-and-line, free. Scan your own skill →