Runs a cheapest-first verification ladder (syntactic, then typecheck / build / lint, then execution) and reports an evidence receipt — confirms, contradicts, ambiguous, or null — never a score. Use when a claim or change needs executed proof; triggers on "verify this claim", "prove this behavior", "run this to confirm", "/verify-behavior".
81%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Passed
No findings from the security scan
Scanned
mthines/agent-skills
0ec47ca
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.