verification-before-completion

Enforces running verification commands before claiming task completion or success.

Updated Jan 2, 2025

Search Tags:#code quality #testing #verification #evidence #regression testing #build validation #completion claims

Ready to run

npx skills add https://github.com/mcinnisd/gymbro --skill verification-before-completion-mcinnisd

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: verification-before-completion
Source: https://github.com/mcinnisd/gymbro/tree/main/.agents/skills/verification-before-completion
Command: npx skills add https://github.com/mcinnisd/gymbro --skill verification-before-completion-mcinnisd

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI agents and developers often claim work is complete, tests pass, or bugs are fixed without actually running fresh verification, leading to false status reports and broken deliverables. ## Core Features & Use Cases - Evidence Gate: Requires running the full verification command and reading its output before any completion claim. - Failure Pattern Catalog: Maps common claims (tests pass, build succeeds, bug fixed) to the exact evidence required versus insufficient proxies. - Rationalization Defense: Lists common excuses like "should work now" or "linter passed" and counters each with the required verification action. - Use Case: Before committing code or reporting a task done, the agent runs the test suite, confirms zero failures in the output, and only then states the result with evidence. ## Quick Start Ask the agent to verify all tests pass with fresh command output before reporting the task as complete.

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 tests pass before claiming completion?▼

Run the full test command fresh in the current session, read the complete output, and confirm zero failures before stating tests pass. Previous runs, partial checks, or assumptions like "should pass" do not count as evidence.

What counts as valid verification evidence for a bug fix?▼

Valid evidence means reproducing the original symptom and confirming it no longer occurs after the fix. Simply changing code or assuming the fix works is insufficient without running the failing scenario.

Does a passing linter prove the build succeeds?▼

No, a linter passing does not prove compilation or build success. Linters check style and syntax patterns but do not verify compilation; you must run the actual build command and confirm exit code 0.

How do I verify a regression test actually works?▼

Use the red-green cycle: write the test, 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 success report without checking?▼

No, agent success reports must be independently verified by checking the version control diff and confirming the actual changes exist. Trusting a report without inspecting the evidence violates the verification rule.