Enforces rigorous evidence-based verification before any code task is marked as complete or committed.
This skill establishes a mandatory 'Gate Function' that prevents AI agents and developers from claiming work is finished without providing fresh, empirical evidence. By requiring the execution of test suites, build commands, and linters immediately prior to any status report, it eliminates false positives and ensures that 'done' truly means 'verified.' It is designed to stop the use of speculative language and rationalizations, ensuring that every assertion of success is backed by verifiable command outputs and exit codes.
주요 기능
01Red-flag detection for speculative language like 'should' or 'seems to'
020 GitHub stars
03Comprehensive checklist for tests, builds, linters, and regression checks
04Mandatory fresh verification command execution before any success claim
05Evidence-based reporting requiring actual terminal output and exit codes
06Anti-rationalization framework to prevent shortcuts in the development cycle
사용 사례
01Ensuring unit and integration tests pass before opening a Pull Request
02Validating build success and linter cleanliness in pre-flight checks
03Verifying bug fixes through Red-Green cycles and regression testing
