Verification Before Completion

What it does

This skill helps the agent separate implementation progress from a demonstrated outcome. It frames completion as an evidence question: identify what observation would support the claim, obtain that observation, inspect the result and report the limits. That makes it useful at the end of a task when a successful edit or intermediate command could otherwise be mistaken for end-to-end success.

Best for

Repository changes, release preparation, deployment work and other tasks where a user needs a reliable statement of what actually works. It is also useful during handoffs because evidence can distinguish a completed stage from a stage that is merely prepared or waiting for access.

Tradeoffs and requirements

Verification is only as strong as the selected check. A passing unit test does not prove a public deployment, and a successful build does not prove hardware behavior. Repeating unrelated tests adds little confidence. Choose observations that cover the requested outcome and explicitly retain any boundaries that require a real user, device or external account.

Unknown; inspect source requirements and supporting scripts.

Install from the source

Inspect the pinned source snapshot and its supporting files first. The command selects this skill through the open-source skills CLI. Node.js and agent-specific setup may be required. Installation can download code. Catalog ingestion never executes skill instructions or install scripts.

npx skills add https://github.com/obra/superpowers/tree/2ce8aa15d05bd57213e6f746f953aafb7ded7a8b/skills/verification-before-completion --skill verification-before-completion

Review pinned skill folder ↗ · CLI documentation ↗

After source review, use npx skills check and npx skills update to inspect and apply upstream updates. Re-check changed instructions before running them.

Safety & review signals

Static review only. This is not a security audit or a guarantee of safety.

SKILL.md text only; scripts, dependencies and runtime behavior not audited.

No configured text patterns matched. Unmatched or concealed behavior can still exist.

Allowed tools declaration: Unknown. Runtime permissions and network behavior: Unknown.

AI Craft Pad Skill Score

88/100 · Metadata coverage 100% · Model 1.0

Scores summarize observable discovery signals. Popularity and repository activity apply to the whole repository. Unknown runtime safety earns no certification.

Documentation

100/100

100

Maintenance

100/100

100

License Clarity

100/100

100

Repository Health

100/100

100

Compatibility Evidence

80/100

80

Popularity

99/100

99

Originality

80/100

80

Static Safety

60/100

60

Suggested workflow

Write the completion claim in concrete terms, choose the narrowest meaningful check, run it against the final state, and inspect both success markers and the actual output. For a website, combine deployment evidence with a fresh public interaction check.

How to judge the result

The final report should name the observed outcome and its evidence, and identify material unverified conditions without turning them into a success claim.