verification-before-completion

Enforces running verification commands before claiming work is complete or passing.

Updated Sep 17, 2026
One-click install
npx skills add https://github.com/juanjaragavi/utilities-manager --skill verification-before-completion-juanjaragavi
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: verification-before-completion
Source: https://github.com/juanjaragavi/utilities-manager/tree/main/.agents/skills/verification-before-completion
Command: npx skills add https://github.com/juanjaragavi/utilities-manager --skill verification-before-completion-juanjaragavi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It prevents premature or false claims of task completion by requiring fresh verification evidence—such as test output, build exit codes, or linter results—before any success statement, commit, or pull request. ## Core Features & Use Cases - Evidence Gate: Defines a five-step gate (identify, run, read, verify, claim) that must be completed before asserting any status. - Failure Pattern Catalog: Maps common claims like "tests pass" or "bug fixed" to the exact command output required to substantiate them. - Rationalization Blocking: Lists red flags and excuses ("should work", "just this once") and counters each with the required verification action. - Use Case: Before committing a bug fix, run the original failing test, confirm it passes, then state the fix is verified with the actual output as evidence. ## Quick Start Before claiming any task is done, run the full verification command, read its complete output and exit code, and only then report the result with that evidence attached.

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 the exit code, and only then state the result with that evidence. Never commit based on assumptions or previous runs.

What counts as evidence that tests pass?▼

Only the fresh output of the test command showing zero failures counts as evidence. Previous runs, partial checks, or statements like "should pass" do not qualify as verification.

How do I verify a regression test actually works?▼

Use the 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.

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.

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

A linter does not check compilation. Claiming a build succeeds requires running the build command and confirming it exits with code 0, since linting and compilation are separate verification steps.