--- title: "Superpowers Verification Before Completion: review, setup & limitations · Undominated.ai" canonical: https://undominated.ai/skills/obra-verification-before-completion/ description: "Requires a fresh command result or direct check for each completion claim and distinguishes passing tests from fulfilling requirements." --- # Superpowers Verification Before Completion: review, setup & limitations · Undominated.ai > Requires a fresh command result or direct check for each completion claim and distinguishes passing tests from fulfilling requirements. [← Explore all skills](/skills/) TESTING AND RELIABILITY / Jesse Vincent / Superpowers # Superpowers Verification Before Completion Requires a fresh command result or direct check for each completion claim and distinguishes passing tests from fulfilling requirements. See setup guidance ↓Original source ↗ SOURCE REVIEW Reviewed 2026-09-21 Evidence 5 linked sources Publisher Jesse Vincent / Superpowers Licence MIT ↗ Revision 5bf4e7801107 Read what was—and wasn’t—checked ↓ “Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before” Jesse Vincent / Superpowers · upstream description ↗ Our analysis follows below. 01 / THE REASONING ## Why this made the selection. - Maps common claims to appropriate evidence, including compiler/build status, original bug reproduction and requirements checks. - Explicitly asks reviewers to inspect delegated changes instead of treating another agent's success message as proof. ### A good fit for - Checking a coding agent's final handoff - Preventing a successful lint run from being reported as a successful build ### Weigh up before choosing - This is a behavioral checklist, not an automatic enforcement mechanism or runtime test harness. - Strict fresh-command requirements can repeat expensive work; teams still need to define checks appropriate to each claim. 02 / THE REVIEW RECORD ## What we actually inspected. Source review has boundaries. A clear record is more useful than a “safe” badge. ### Material inspected - skills/verification-before-completion/SKILL.md - LICENSE ### Our findings - The gate requires identifying a proving command, reading complete output and its exit status, then qualifying the claim. - The examples distinguish a test that merely passes from a demonstrated regression test. - The source has no bundled executables; the consuming agent chooses and runs project-specific checks. ### Not established by this review - No agent-adherence evaluation was run. - No project tests, builds or deployments were performed by this review. The review applies to the material and revision named here. A newer upstream release can change its behavior. 03 / PUT IT TO WORK ## Add a skill to your workflow. Upstream setup instructions ↗ DOCUMENTED COMMAND npx skills add https://github.com/obra/superpowers/tree/5bf4e78011075bcfc0dc295f0724994cd123ee71/skills/verification-before-completion Copy command ↗ Copying does not execute this command. It may retrieve a newer version than the reviewed source. - Install the complete skill directory with its references and helpers; a copied SKILL.md alone may be incomplete. - Choose the intended agent and project scope in the installer, then review its permissions before using the skill. ### Before you start - Node.js/npm for this installer - An agent that supports the Agent Skills format - Access to relevant test/build commands and their complete output ### Compatibility Superpowers-supported coding agents ### Project checks and result inspection - Read changed files and version-control diffs - Run the commands required to substantiate the requested status ### Cost model The MIT-licensed instructions have no separate service fee; verification can consume agent, compute or external CI resources. 04 / FOLLOW THE EVIDENCE ## The source trail. Our notes are separate from the original resource. Check upstream before adopting a new version. - Skill definition at reviewed revision ↗ Checked 2026-09-21 https://github.com/obra/superpowers/blob/5bf4e78011075bcfc0dc295f0724994cd123ee71/skills/verification-before-completion/SKILL.md Supports: summary, upstreamDescription, whySelected, bestFor, limitations, review, compatibility, access - Upstream license or licensing declaration ↗ Checked 2026-09-21 https://github.com/obra/superpowers/blob/5bf4e78011075bcfc0dc295f0724994cd123ee71/LICENSE Supports: license - Publisher installation and project documentation ↗ Checked 2026-09-21 https://github.com/obra/superpowers/blob/5bf4e78011075bcfc0dc295f0724994cd123ee71/README.md Supports: install, compatibility, access - Skills installer source formats and selective installation ↗ Checked 2026-09-21 https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md Supports: install - Installer implementation: full commit SHA fallback ↗ Checked 2026-09-21 https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/src/git.ts Supports: install KEEP COMPARING ## Other approaches to consider. Related by category or shared topics. These are alternatives to inspect, not a measured quality order. [### Bug Receipt ↗ Creates an evidence-bearing defect or incident handoff that distinguishes verified, partial and blocked outcomes.](/skills/github-bug-receipt/)[### Superpowers Receiving Code Review ↗ Checks review feedback against the code and project constraints before making and testing each requested change.](/skills/obra-receiving-code-review/)[### Diagnosing Bugs ↗ A debugging procedure that establishes a reproducible symptom, tests competing explanations and preserves a regression check.](/skills/mattpocock-diagnosing-bugs/) [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)