Does this work with any programming language?

Yes, it is language-agnostic and applies to any environment where you can run verification commands like npm test, pytest, go test, or make.

Why is this skill necessary for AI coding?

AI assistants can occasionally assume a code change works without executing it; this skill forces the AI to provide fresh evidence from command output before claiming success.

Can it prevent broken builds?

Yes, by making a successful build command (exit code 0) a mandatory prerequisite for any completion claim.

What 'red flags' does this skill monitor?

It identifies and stops the use of non-committal language like 'should work,' 'seems to,' or 'looks correct,' requiring hard evidence instead.

How does it handle Red-Green testing?

It requires the AI to prove a test fails by reverting a fix, then prove it passes by restoring the fix, ensuring the test is actually measuring the intended behavior.

Verification Before Completion

Name: Verification Before Completion
Author: timequity

bytimequity

安全与测试

Enforces a rigorous evidence-based workflow that requires successful command execution before any task is marked as finished.

关于

This skill acts as a cognitive gatekeeper for Claude, preventing premature completion claims by mandating the 'Iron Law' of verification: no task is considered done until fresh, successful command output is produced and analyzed. It eliminates 'should-work' statements and assumptions, ensuring that bug fixes, test suites, and builds are validated through actual execution. By requiring the AI to identify, run, and read verification commands before making any success claims, it significantly improves the reliability of AI-generated code and the overall integrity of the development cycle.

主要功能

Mandatory execution of verification commands before any status update
Detection and prevention of 'red flag' language like 'should' or 'probably'
Step-by-step checklist verification for complex project requirements
Enforced TDD Red-Green cycle for verified regression testing
Systematic validation of exit codes and failure counts for tests and linters
0 GitHub stars

使用场景

Preventing false positives when resolving complex software bugs
Ensuring local builds pass before committing or creating pull requests
Standardizing quality control during automated refactoring sessions

关于

主要功能

Mandatory execution of verification commands before any status update
Detection and prevention of 'red flag' language like 'should' or 'probably'
Step-by-step checklist verification for complex project requirements
Enforced TDD Red-Green cycle for verified regression testing
Systematic validation of exit codes and failure counts for tests and linters
0 GitHub stars

使用场景

Preventing false positives when resolving complex software bugs
Ensuring local builds pass before committing or creating pull requests
Standardizing quality control during automated refactoring sessions