Read the current uncommitted diff, run three independent reviewers (safety + tests-coverage + style) in parallel, then arbitrate a single BLOCK / BLOCK_WITH_OVERRIDE / PASS_WITH_NOTES verdict. Use before commit when you want a multi-perspective second-opinion instead of a single-reviewer agent loop.
72
89%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
A combinator-style meta-skill that runs three independent reviewers in parallel over the currently-uncommitted diff, then arbitrates a single verdict with a strict priority rule.
This is the same combinator + arbitrate pattern as
meta-security-review-bundle, applied to a code-review domain. The
three reviewers each carry a tight, project-specific rubric — safety
focuses on injection / credentials / G1.6 contract; tests focuses on
the "new public surface ⇒ corresponding test" expectation; style
flags only a fixed list of antipatterns so it doesn't drift into
free-form opinions.
Fire by saying multi-reviewer diff, codereview my diff, or one of the
localized triggers listed in the frontmatter. The diff is read from the working
tree (git diff --cached HEAD, falling back to git diff HEAD if nothing is
staged).
If read_diff returns NO_DIFF, the downstream reviewers should
reply with their respective clean verdicts ("CLEAR" / "PASS" /
"CLEAN") and arbitrate emits PASS_WITH_NOTES: clean. If a reviewer
LLM step fails, the orchestrator's partial outputs are visible in
step_outputs; operator should manually re-run the failed reviewer.
94ac35e
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.