What problem does it solve? AI agents and developers often claim work is complete, tests pass, or bugs are fixed without actually running the verification commands, leading to broken builds, shipped defects, and lost trust. This Skill enforces an evidence-first discipline so no success claim is made without fresh command output. ## Core Features & Use Cases - Verification Gate: Defines a mandatory five-step gate (identify command, run it, read output, verify result, then claim) before any completion statement. - Failure Pattern Catalog: Maps common claims (tests pass, build succeeds, bug fixed, agent completed) to the exact evidence required and what does not count as proof. - Rationalization Blocking: Lists red-flag phrases and excuses ("should work", "just this once", "linter passed") that signal an unverified claim is about to be made. - Use Case: Before committing a bug fix, the agent runs the test suite, confirms zero failures in the output, and only then reports the fix as verified, including for regression tests via a red-green cycle check. ## Quick Start Before claiming any task is done or tests pass, run the relevant verification command, read the full output, and only then state the result with the evidence.
