← ClaudeAtlas

reviewlisted

Fan out parallel read-only reviewers over a diff and consolidate into one severity-ranked verdict. Use for a full pre-ship review, "review/validate this PR", or "spawn agents to review". Don't use for a single-lens PR review (/code-review), one audit, or triaging existing comments (/triage-review).
helderberto/agent-skills · ★ 16 · Code & Development · score 81
Install: claude install-skill helderberto/agent-skills
# Review Phase Resolve the diff, fan out **parallel read-only reviewers** — each in its own subagent so a11y and security reasoning don't bleed into each other — and consolidate into one severity-ranked verdict. Findings two reviewers reach independently are the highest signal — surface that convergence. Reviewers come from two sources: **audit skills** selected by file type in the diff (`a11y-audit`, `i18n`, `perf-audit`, `deps-audit`, `harden`, `safe-repo`) and **agent lenses** applied to the whole diff (correctness, test effectiveness, type safety, architecture friction). ## Workflow ### 1. Resolve the diff PR number → `gh pr view` + `gh pr diff` (fails → current-branch diff, warn). Branch → `git diff <base>...<branch>`. Nothing → `git merge-base HEAD main` (fall back `master`, `origin/HEAD`, then `HEAD~10` with a warning), then `git diff <base>...HEAD`. Empty diff → "Nothing to review", stop. State the scope: "Reviewing branch `X` vs `main` — 6 files, 224 insertions." ### 2. Select reviewers Always: correctness (`code-review`), sensitive data (`safe-repo` diff-only), test effectiveness. Add the rest from the diff. Default 3–5 total; honor an explicit count from `$ARGUMENTS` (2–5). Never spawn `e2e` or `visual-validate` — those are VERIFY phase, not REVIEW. | Reviewer | When | Agent type | |----------|------|------------| | Correctness (`code-review`) | always | `general-purpose` | | Sensitive data (`safe-repo` diff-only) | always | `general-purpose` | | Test effec