What problem does it solve? AI agents and developers often claim work is complete, tests pass, or code is ready to commit without actually running verification commands, leading to broken builds, false handoffs, and lost trust. This Skill eliminates unverified success claims by requiring fresh command output as evidence before any completion statement. ## Core Features & Use Cases - Verification Gate: Blocks any completion, fix, or passing claim until the relevant command has been run fresh in the current session and its output inspected. - Scope Matching: Requires broad claims like "task complete" or "ready to commit" to be backed by the full verification pipeline (format, lint, tests, build), not partial checks. - Pre-Commit and Pre-PR Gate: Mandates a full pipeline run, diff review, and a structured Verification Report with a PASS verdict before any git commit or pull request. - Failure Protocol: Provides a disciplined loop for diagnosing failures, fixing root causes, and re-verifying from scratch without workarounds. - Use Case: Before an agent reports "all tests pass" and commits a bug fix, it runs the full test suite, cites the exit code and output in a Verification Report, and only then proceeds with the commit. ## Quick Start Before claiming this task is done, run the full verification pipeline and show me the verification report with the actual command output.
