What problem does it solve? AI agents and developers often claim work is complete, fixed, or passing without actually running the verification command, leading to broken builds, shipped bugs, and lost trust. This Skill enforces an evidence-first discipline so no completion claim is made without fresh verification output. ## Core Features & Use Cases - The Iron Law gate: Blocks any completion, success, or satisfaction claim until a verification command has been run and its output read in the current session. - Claim-to-evidence mapping: Defines what proof each claim requires, such as test output showing zero failures, build exit code 0, or a RunVerification gameplay probe pressing input and reading state back. - Rationalization prevention: Lists common excuses ("should work", "linter passed", "agent said success") and the correct evidence-based response to each. - Use Case: Before committing a bug fix, the agent runs the test suite, confirms 0 failures in the output, and only then reports the fix as verified, instead of assuming the code change worked. ## Quick Start Before you claim any task is done, fixed, or passing, run the full verification command, read its complete output and exit code, and only then state the result with that evidence.
