Review PR: The Agentic Gate Before the Human

Input: $ARGUMENTS

The point of this skill is fresh eyes: it reviews the PR in a clean context, not the context that wrote the code, and can hand the deep analysis to the code-reviewer agent, which is the whole reason the review catches what the author's own context rationalizes away. It posts its verdict on the PR, then a human makes the final call.

Phase 1, Fetch the PR

Resolve the input to a PR number (a number, a URL, or a branch via gh pr list --head <branch> --json number -q '.[0].number'). Then:

gh pr view {N} --json number,title,body,author,headRefName,baseRefName,state,additions,deletions,changedFiles,files
gh pr diff {N}
gh pr checkout {N}

State guard: MERGED/CLOSED → stop ("nothing to review"); DRAFT → review direction, don't approve/block.

Phase 2, Load the context (so you review against the right bar)

• CLAUDE.md + any .claude/references/, the project's standards are the review rubric.
• The implementation report (if piv-implement wrote one, .claude/reports/*{branch}*) + its plan: read the documented deviations. A documented deviation is an intentional decision, not an issue, only flag undocumented divergences. (No report? Review normally and note its absence.)
• The PR's own intent (title/body): what problem it claims to solve.

Phase 3, Run validation

Run the project's real suite (the piv-validate skill, or the plan's validation commands), tests, type-check, lint, build. Capture pass/fail + counts. A red suite is a finding in itself.

Phase 4, Review the diff (dispatch the code-reviewer agent)