Evidence Verification
Verifies development tasks and code changes by collecting verifiable proof including test results, build outputs, and exit codes.
The Evidence Verification skill equips Claude with a rigorous protocol for validating task completion through tangible evidence. It ensures that every code change, deployment, or review is backed by executable proof—such as passing test suites, successful build logs, coverage metrics, and zero-exit codes—moving beyond verbal claims to production-grade verification. This skill is essential for maintaining high code quality, preventing AI hallucinations during the development cycle, and ensuring that implementations meet project standards before they are marked as complete.
Key Features
01Automated collection of test results, exit codes, and coverage metrics
02Multi-level verification standards from Minimum to Gold Standard
03Standardized evidence templates for builds, tests, and code quality
04Integration with language-specific toolchains like npm, pytest, and ruff
05Protocol for capturing deployment health checks and security scans
0629 GitHub stars
Use Cases
01Automating quality assurance checks and linter verification during code reviews
02Verifying that a new feature passes all unit and integration tests before handoff
03Ensuring a build is successful and produces required artifacts before deployment