← ClaudeAtlas

pr-reviewlisted

Run a rigorous, multi-dimensional review checklist on any pull request before opening, merging, or after receiving review comments. Use this skill ALWAYS before opening a PR, when asked to "review this PR/branch/diff", "check my changes", "is this ready to merge", or before promoting a branch from dev to staging or staging to main. Goes beyond style — checks security, performance, testing rigor, supply chain, and Definition of Done coverage.
Xipher-Labs/walter-os · ★ 5 · AI & Automation · score 67
Install: claude install-skill Xipher-Labs/walter-os
# Pull Request Review This is the rubric. Apply it to every PR before opening and again before merging. The reviewer subagent uses this checklist with read-only tools (`Read`, `Grep`, `Glob`). ## Model Routing When a PR needs a cross-model second opinion, resolve the backend/security review model through: ```bash source "$WALTER_OS_HOME/scripts/walter/lib/model-router.sh" review_model="" walter_model_resolve backend_review review_model ``` Default preference is Codex for backend, security, infrastructure, and edge-case review. Frontend-heavy PRs may additionally use `walter_model_resolve frontend review_model`. PHI/medical diffs must use `walter_model_resolve phi review_model` and stay local. ## Required before opening a PR - [ ] **PR title validated**: run `./hooks/pr-title-validator.sh "$TITLE"` before calling `gh pr create`. If exit != 0, fix the title — do not proceed. Format: `[TYPE] -CATEGORY- title` (see CONTRIBUTING.md -> "Title convention"). - [ ] Spec exists at `docs/specs/<slug>.md` and is current - [ ] Plan exists at `docs/specs/<slug>.plan.md` and matches the diff - [ ] All acceptance criteria in spec map to ≥1 test - [ ] Tests pass locally on the latest commit: unit, integration, e2e - [ ] Lint passes: language formatter + linter - [ ] Typecheck passes (TS strict, mypy strict, cargo check, etc.) - [ ] No `.only`, `.skip`, `xit`, `xdescribe`, `#[ignore]` left - [ ] No `console.log`, `println!()`, `print()`, `dbg!()` debugging artifacts - [ ] No