From cc-harness
Run a read-only verification pass after implementation to check whether completion claims are real, validation actually ran, and obvious edge cases or regressions were missed.
How this skill is triggered — by the user, by Claude, or both
Slash command
/cc-harness:verification-gateThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill when the implementation should not be accepted without a separate challenge pass.
Use this skill when the implementation should not be accepted without a separate challenge pass.
Collect a verification context from a git repo:
python3 {baseDir}/scripts/verification_context.py --repo /path/to/repo
Then run the portable verifier prompt from references/prompt-template.md.
python3 {baseDir}/scripts/verification_context.py ...npx claudepluginhub learnprompt/cc-harness-skills --plugin cc-harnessEnforces running verification commands like tests, lints, builds before claiming code complete, fixed, or passing, prior to commits/PRs.
Enforces fresh verification evidence before any completion claim, fix, or commit. Run the full verification pipeline before reporting success or handing off work.
Enforces evidence-based verification by running fresh tests, builds, linters, reviewing outputs before claiming work done, committing, or PRing.