skills.rest
HarmAalbers
HarmAalbersCOMMUNITY
Explore all skills by this author →
GitHub

verification-before-completion

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

1|Updated Dec 11, 2025
Search Tags:#code quality#testing#verification#test evidence#git push#ci discipline#completion claims
One-click install
npx skills add https://github.com/HarmAalbers/claude-requirements-framework --skill verification-before-completion-harmaalbers
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: verification-before-completion
Source: https://github.com/HarmAalbers/claude-requirements-framework/tree/main/plugins/requirements-framework/skills/verification-before-completion
Command: npx skills add https://github.com/HarmAalbers/claude-requirements-framework --skill verification-before-completion-harmaalbers

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI-assisted development often produces premature completion claims — saying tests pass, builds succeed, or bugs are fixed without actually running the verification command. This Skill enforces an evidence-first discipline so every status claim is backed by fresh command output. ## Core Features & Use Cases - Gate Function: A five-step protocol (identify, run, read, verify, claim) that must be completed before any success statement. - Failure Pattern Tables: Concrete mappings of claims (tests pass, linter clean, bug fixed) to the exact evidence required, plus rationalization and red-flag lists. - Workflow Integration: Auto-satisfies the verified gate in the requirements framework, re-arming after every git push so verification runs before each push. - Use Case: Before committing a bug fix, run the test suite, confirm zero failures in the output, and only then state that the fix works — instead of assuming the code change resolved it. ## Quick Start Ask the assistant to verify the fix by running the full test suite and reporting the actual output before claiming the work is done.

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 actually pass before committing code?▼

Run the full test command such as pytest tests/ -v and read the complete output, confirming zero failures and a clean exit code. Only then state that tests pass, citing the actual counts from the output rather than assuming success.

How to verify a bug fix works before creating a pull request?▼

Reproduce the original symptom with a test, confirm it fails before the fix and passes after, then run the full suite. A code change alone is not evidence; the red-green cycle must be observed in actual command output.

Does a passing linter mean the build succeeds?▼

No, a linter passing does not prove the build succeeds. Run the actual build or compilation command, such as python -m py_compile, and confirm exit code 0 before claiming the build passes.

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

No, agent success reports must be verified independently. Inspect the git diff to confirm the claimed changes exist and run relevant tests before reporting the actual state of the work.

When should verification run in a git push workflow?▼

Verification should run before every push, not just once per session. In the requirements framework the verified gate is single_use and re-arms after each git push, so fresh evidence is required each time.

Related Skills

Explore More Software Engineering Skills→
jacexhjacexh

verification-before-completion

Run full verification commands and report exit code evidence before completion claims.

Community
Intermediate
amotion-aiamotion-ai

close

Verify tests, commit changes, push branch, and create a pull request.

Official
Intermediate
youssefKadaouiAbbassiyoussefKadaouiAbbassi

pre-review-checklist

Run tests, type checks, and lint checks on a codebase before submission.

Community
Intermediate
shin0720shin0720

auto-canary

Automate pre-deployment verification including builds, E2E tests, and browser checks.

Community
Intermediate