verification-before-completion

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

Updated Jul 23, 2025
One-click install
npx skills add https://github.com/derrik-fleming/dotfiles --skill verification-before-completion-derrik-fleming
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: verification-before-completion
Source: https://github.com/derrik-fleming/dotfiles/tree/main/private_dot_agents/skills/verification-before-completion
Command: npx skills add https://github.com/derrik-fleming/dotfiles --skill verification-before-completion-derrik-fleming

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI agents and developers often claim work is complete, fixed, or passing without actually running the verification commands, leading to broken builds, shipped bugs, and broken trust. This Skill enforces an evidence-first discipline so no success claim is made without fresh command output. ## Core Features & Use Cases - Verification Gate: A five-step gate function (identify, run, read, verify, claim) that must be completed before any completion statement. - Claim-to-Evidence Mapping: A table defining what proof each claim requires, such as test output showing zero failures or a build exiting with code 0. - Rationalization Blocking: Explicit counterarguments for common excuses like "should work now", "linter passed", or "agent reported success". - Use Case: Before committing a bug fix, run the test suite, confirm zero failures in the output, verify the regression test fails without the fix, and only then state the fix works with the evidence attached. ## Quick Start Before claiming any task is done, run the full verification command, read the complete output and exit code, and only state success 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 code changes before committing?▼

Identify the command that proves your claim, run it fresh and in full, read the complete output including the exit code, and only then state the result with that evidence. Never commit based on a previous run or assumption.

How to 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. A test that never fails proves nothing.

Does a passing linter mean the build succeeds?▼

No, a linter passing does not prove compilation or build success. Linters check style and static issues but do not compile code, so you must run the actual build command and confirm it exits with code 0.

Can I trust an agent's success report without checking?▼

No, agent success reports must be verified independently. Check the version control diff to confirm the claimed changes actually exist and run the relevant verification commands yourself before reporting completion.

When should verification run before claiming completion?▼

Always, before any success claim, expression of satisfaction, commit, pull request, or task handoff. The rule applies to exact phrases, paraphrases, and any wording implying success, with no exceptions for confidence or fatigue.