HomeRated skills › verification-before-completion
A

verification-before-completion

by obra/superpowers · view source ↗
Autonomous CodingMIT1,037 tok/call
Clean — safe and lean
Safety grade
A
88/100 · gate: pass
Token cost
1,037
leaner than median
Efficacy
Not yet measured

What it claims to do

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

What we found · 1

Conflicts with · 8

xlsxshadowoutput, fix
wranglershadowrunn, command
finishing-a-development-branchshadowcomplete, work
receiving-code-reviewshadowrequir, verification
frontend-designshadowmak
pptxshadowoutput
web-artifacts-buildershadowrequir
cloudflare-oneshadowwork

If you have both installed, they compete for the same triggers — the top cause of an agent picking the wrong skill.

Have you installed verification-before-completion? Scan everything you run.

One command grades every skill in your Claude Code / Codex — safety, token bloat, and conflicts, 100% locally.

npx skillmoo scan

Browse all rated skills

Grade computed 2026-07-13 · rubric static-v1. Efficacy shown only when measured on a labeled model + task suite — never invented.

Show the badge

Add this independent grade to the skill's README — the badge links back to this rating and updates when we re-grade.

SkillMOO grade A

[![SkillMOO](https://skillmoo.com/badge/verification-before-completion)](https://skillmoo.com/skill/verification-before-completion/)

Does this rating match your experience with verification-before-completion?
Anonymous & aggregate. We watch these as a trend and re-check flagged skills — a single click never moves a grade on its own.
Independent static analysis by SkillMOO — the Consumer Reports for agent skills. Safety, token, and conflict grades are computed, not opinions. Efficacy is only ever claimed when measured. We rate & link to the source; we do not rehost skill content.