skills.rest
marcmarti9
marcmarti9COMMUNITY
Explore all skills by this author →
GitHub

verification-before-completion

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

3|Updated Jul 28, 2026
Search Tags:#code quality#testing#tdd#verification#evidence#build validation#completion claims
One-click install
npx skills add https://github.com/marcmarti9/agentit --skill verification-before-completion-marcmarti9
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: verification-before-completion
Source: https://github.com/marcmarti9/agentit/tree/main/skills/verification-before-completion
Command: npx skills add https://github.com/marcmarti9/agentit --skill verification-before-completion-marcmarti9

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI agents and developers often claim work is done, tests pass, or bugs are fixed based on assumptions, partial checks, or stale results rather than fresh evidence. This Skill eliminates premature success claims by requiring actual command output before any completion statement. ## Core Features & Use Cases - Evidence Gate: A five-step gate function (identify, run, read, verify, claim) that must be completed before any success assertion. - Claim-to-Evidence Mapping: A table defining what proof each common claim requires, such as test output for "tests pass" or exit code 0 for "build succeeds". - Rationalization Prevention: Counters common excuses like "should work now" or "linter passed" with the requirement to run the actual verification. - Use Case: Before committing a bug fix, the agent runs the test suite fresh, confirms zero failures in the output, and only then reports the fix as verified with the evidence attached. ## Quick Start Before claiming any task is complete or creating a pull request, run the full verification command and confirm its output proves the claim.

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 completely, read the full output including exit codes, and only then state the result with evidence. Never commit based on previous runs or assumptions.

How to confirm a bug fix actually works?▼

Run a test that reproduces the original symptom and confirm it passes. Changed code alone is not proof; you must observe the failing behavior resolved through fresh test output.

Does a passing linter mean the build succeeds?▼

No, a linter does not check compilation. Build success requires running the actual build command and confirming exit code 0, since linting and compilation are separate verification steps.

How do I verify a regression test with red-green TDD?▼

Write the test, run it to confirm it passes, revert the fix and confirm the test fails, then restore the fix and confirm it passes again. A test that only passes once is not verified.

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

No, agent success reports require independent verification. Check the version control diff to confirm actual changes were made and run verification commands yourself before reporting the real state.

Related Skills

Explore More Software Engineering Skills→
g2i-aig2i-ai
51

tdd

Guide test-driven development with red-green-refactor cycles and quality checks.

Official
Intermediate
basicmachines-cobasicmachines-co
4.0k

pr-create

Creates or updates Basic Memory pull requests and runs the Codex review loop.

Official
Intermediate
SigmacodeatSigmacodeat

cross-modal-review

Route work products to an independent AI model for contract-based review.

Community
Advanced
mikkeymoomikkeymoo
1

mm-quality

Automate dependency audits, accessibility checks, migration planning, API route validation, and mechanical verification gates.

Community
Advanced