Can I use this with any programming language?

Yes. The skill is command-agnostic and works with any testing framework, compiler, or linter including Jest, Pytest, Go test, and custom shell scripts.

When does this skill activate?

It is active whenever Claude is about to claim work is complete, express satisfaction with a result, or prepare a commit or pull request.

How does this skill prevent AI hallucinations?

It implements a strict protocol that forbids Claude from using words like 'done' or 'fixed' until it has physically executed a verification command and parsed the output for successful exit codes.

What is the Red-Green cycle requirement?

For bug fixes, the skill requires the AI to prove the test fails when the fix is removed (Red) and passes when restored (Green) to ensure the test is actually valid.

Verification Before Completion

Name: Verification Before Completion
Author: EricOo0

byEricOo0

•

Security & Testing

Enforces a rigorous evidence-based workflow that requires successful command output before any task is claimed as complete.

About

This skill establishes a non-negotiable protocol for Claude to prevent premature or false completion claims. By implementing an 'Iron Law' of verification, it forces the AI to identify, execute, and analyze fresh output from tests, linters, or build commands before reporting success. This eliminates speculative assertions, ensures TDD rigor through red-green cycles, and maintains high trust by providing concrete evidence for every fix or feature implemented.

Key Features

Strict prohibition of speculative language like 'should' or 'probably'
Line-by-line requirement checklist validation
5 GitHub stars
Mandatory gate function requiring fresh command execution before success claims
Systematic verification of bug fixes using TDD red-green cycles
Independent verification of agent-delegated task results and diffs

Use Cases

Verifying bug fixes by confirming the original symptom fails before the fix passes
Preventing the creation of Pull Requests before running full test suites
Ensuring complex build processes succeed after refactoring or dependency updates

About

Key Features

Strict prohibition of speculative language like 'should' or 'probably'
Line-by-line requirement checklist validation
5 GitHub stars
Mandatory gate function requiring fresh command execution before success claims
Systematic verification of bug fixes using TDD red-green cycles
Independent verification of agent-delegated task results and diffs

Use Cases

Verifying bug fixes by confirming the original symptom fails before the fix passes
Preventing the creation of Pull Requests before running full test suites
Ensuring complex build processes succeed after refactoring or dependency updates