Stats
Actions
Tags
From superpowers
Enforces rigorous task verification via /need-vet: clarify if needed, fully execute and test (code runs, app interactions, edge cases), append verified tag only after checks.
How this skill is triggered — by the user, by Claude, or both
Slash command
/superpowers:need-vetThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Enable work verification for the current task. The stop hook will block session exit until the work is verified.
Enable work verification for the current task. The stop hook will block session exit until the work is verified.
Evaluate task clarity. If the request is vague, lacks explicit success criteria, or has key ambiguities, use the AskUserQuestion tool to resolve them before doing any work. If clear, define a done checklist and start working immediately — no "I will..." preamble.
Execute the task. The final deliverable must be finished and working, not a draft. If something fails or looks wrong, fix it before reporting back — do not hand problems back to the user.
Verify the work.
Mark as verified. Once the work is genuinely verified, append <verified>Fully Vetted.</verified> at the end of the response. Only output this tag when you have genuinely verified the work — do not lie to exit.
npx claudepluginhub fradser/dotclaude --plugin superpowersEnforces running verification commands (tests, linters, builds) before claiming completion, success, or satisfaction. Activates on any positive work state claims.
Enforces evidence-before-claims discipline: requires fresh verification (test, build, lint) before any completion claim. Prevents premature sign-offs.
Enforces evidence-based completion discipline: run verification commands (tests, lints, type checks, builds) before claiming work is done. Prevents false completion by requiring captured output.