skills.rest
afonsoft
afonsoftCOMMUNITY
Explore all skills by this author →
Website𝕏@afonsoftGitHub

verification-before-completion

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

Updated Jul 21, 2026
Search Tags:#code quality#testing#verification#evidence#ci#build validation#completion claims
One-click install
npx skills add https://github.com/afonsoft/gamehub --skill verification-before-completion-afonsoft
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: verification-before-completion
Source: https://github.com/afonsoft/gamehub/tree/main/.claude/skills/verification-before-completion
Command: npx skills add https://github.com/afonsoft/gamehub --skill verification-before-completion-afonsoft

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 lost trust. This Skill enforces an evidence-first discipline so no success claim is made without fresh command output. ## Core Features & Use Cases - Verification Gate: Defines a mandatory gate function (identify, run, read, verify, then claim) that must be executed before any completion statement. - Failure Pattern Catalog: Maps common claims (tests pass, build succeeds, bug fixed) to the exact evidence required, and lists red-flag rationalizations to stop. - Use Case: Before committing a bug fix or opening a PR, the agent runs the full test suite, confirms zero failures in the output, and only then reports the fix as verified. ## Quick Start Before you say the task is done, run the relevant test or build command and report the actual output as evidence.

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 the claim, such as the test suite or build command, run it fresh and in full, then read the output and exit code. Only state the work is complete after the output confirms zero failures.

What counts as evidence that tests pass?▼

Evidence is the fresh output of the actual test command showing zero failures in the current session. Previous runs, partial checks, linter results, or assumptions like "should pass" do not qualify as verification.

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 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.

Can I trust a sub-agent's report that a task succeeded?▼

No. Agent success reports must be independently verified by checking the version control diff and confirming the changes exist and work before reporting the actual state.

Related Skills

Explore More Software Engineering Skills→
yuichi176yuichi176

code-change-verification

Install dependencies, build, lint, typecheck, and test code changes.

Community
Intermediate
caitengweicaitengwei
6

verification-before-completion

Require fresh command execution and evidence before reporting completion status.

Community
Basic
519lab519lab
2

requesting-code-review

Run automated code review with security scans and static analysis before commit.

Official
Advanced
northguildnorthguild
6

tdd

Guides test-driven development through red-green cycles with seam-based test design.

Official
Intermediate