verification-before-completion

Requires running verification commands and checking output before claiming work is complete.

Updated Sep 6, 2026
One-click install
npx skills add https://github.com/kangjuhyup/study --skill verification-before-completion-kangjuhyup
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: verification-before-completion
Source: https://github.com/kangjuhyup/study/tree/main/scoped-superpowers-ab/workflow-code-benchmark/fixture/workflows/full/skills/verification-before-completion
Command: npx skills add https://github.com/kangjuhyup/study --skill verification-before-completion-kangjuhyup

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI agents and developers often claim work is done, tests pass, or bugs are fixed without actually running the verification commands, leading to false success reports and broken commits. This Skill enforces an evidence-first discipline so no completion claim is made without fresh command output. ## Core Features & Use Cases - Verification Gate: Defines a five-step gate (identify, run, read, verify, claim) that must be completed before any success statement. - Failure Pattern Catalog: Maps common claims (tests pass, build succeeds, bug fixed) to the exact evidence required and what does not count as proof. - Rationalization Blocking: Lists red-flag phrases and excuses like "should work" or "linter passed" that signal unverified claims. - Use Case: Before committing a bug fix, run the test suite, confirm zero failures in the output, and only then state the fix is verified. ## Quick Start Before I commit these changes, apply the verification-before-completion rules and confirm the test and build output actually proves everything passes.

Frequently Asked Questions about verification-before-completion

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I verify work is complete before committing code?

Identify the command that proves your claim, run it fresh and in full, read the entire output including exit code, and confirm it matches the claim. Only state success after seeing concrete evidence such as zero test failures or a clean build exit code.

What counts as evidence that tests pass?

Evidence is the actual output of a freshly run test command showing zero failures. Previous runs, assumptions like "should pass", linter results, or partial checks do not qualify as verification of test success.

Why is a passing linter not enough to claim a build succeeds?

A linter checks style and static issues but does not compile the code. Claiming a build succeeds requires running the actual build command and confirming it exits with code 0.

How do I verify a regression test actually works?

Use a red-green cycle: write the test, run it to confirm it passes with the fix, revert the fix and confirm the test fails, then restore the fix and confirm it passes again. A test that never fails proves nothing.

Can I trust an agent's report that a task succeeded?

No. Agent success reports must be independently verified by checking the version control diff and confirming the actual changes match the claimed outcome before reporting completion.