Playbook for reviewing pull requests — verdict format, verification-not-trust, severity-ranked findings with concrete fixes, risk acceptance on the record. The reviewer-side counterpart of pr-authoring.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# PR Review — playbook
A review is not an opinion; it is a verification with a verdict. The author
owed you an evidence-backed PR (per `pr-authoring`); you owe back a review
that says what you checked, what you found, and exactly what it takes to
get to APPROVE.
## 1. Review output format (in order)
1. **Verdict** — one of:
- **APPROVE** — mergeable as-is.
- **APPROVE-WITH-NITS** — mergeable; nits listed, author's call.
- **REQUEST-CHANGES** — not mergeable; the exact path to APPROVE is
listed. A REQUEST-CHANGES without that path is a stall, not a review.
- **BLOCKED** — a question outside this PR must be answered first
(file it as a ticket / open decision; link it).
2. **What I verified** — table: Claim in PR | How I checked | Result.
Re-run at least the highest-risk verification the author claims, and
spot-check at least two checklist boxes. Trust is not a review method.
3. **Findings** — table: Severity | Location | Issue | Concrete fix.
Severity levels:
- **Blocker** — merging causes harm (bug, security, data, broken
contract). Ship-stoppers only.
- **Major** — wrong but not dangerous; fix before or immediately after
…
The line at the top of this page pins the label git:20260722.05296a5, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_3ml5rrbcjk4ucom7
GET https://markdownregistry.com/api/v1/resolve?ref=vandanaajaydubey111/great-pm/pr-review
GET https://markdownregistry.com/api/v1/blob/f6af97b14de6b3e039b39f1db4f8763eb74f9872d720f76e6734738cffd4c45b
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
vandanaajaydubey111/great-pm · codex/source-skills/great-pm-runtime/SKILL.md · Use when a GreatPM workflow needs to select, spawn, coordinate, or collect results from its specialist…
vandanaajaydubey111/great-pm · plugins/great-pm/skills/accessibility/SKILL.md · Playbook for product accessibility — WCAG 2.2 AA, ADA Title III (US public accommodations), Section 508 (US federal)…
vandanaajaydubey111/great-pm · plugins/great-pm/skills/activation-aha-moment/SKILL.md · The statistical method for finding a product's activation/aha moment — the action that, taken early, separates retained…
vandanaajaydubey111/great-pm · plugins/great-pm/skills/ai-regulation/SKILL.md · Playbook for AI-specific regulation — EU AI Act (high-risk + GPAI obligations), NIST AI RMF (US voluntary), Biden EO +…
vandanaajaydubey111/great-pm · plugins/great-pm/skills/ai-unit-economics/SKILL.md · The unit-economics model that governs whether an AI product is viable. Forces explicit cost-per-action (token +…
vandanaajaydubey111/great-pm · plugins/great-pm/skills/ai-use-case-scoping/SKILL.md · The should-this-even-be-AI gate — decide where an LLM belongs versus deterministic rules, frame error tolerance as a…
vandanaajaydubey111/great-pm · plugins/great-pm/skills/beachhead-segment/SKILL.md · Identify the first beachhead market segment for a product launch. Evaluates segments against burning pain, willingness…
vandanaajaydubey111/great-pm · plugins/great-pm/skills/blue-ocean-strategy/SKILL.md · Create uncontested market space using value innovation instead of competing head-to-head. Use when the user mentions…
agentic-community/mcp-gateway-registry · .claude/skills/pr-review/SKILL.md · Review a GitHub pull request using multiple expert personas. Takes a PR URL as input, analyzes the changes, and…
athola/claude-night-market · plugins/sanctum/skills/pr-review/SKILL.md · Reviews pull requests with scope validation, requirements compliance, and line comments. Use when reviewing GitHub or…
mathews-tom/armory · evals/skillsbench/source-snapshots/pr-review-776a618c/SKILL.md · Diff-based PR review across code quality, test coverage, silent failures, type design, and comment quality with…
mathews-tom/armory · skills/pr-review/SKILL.md · Diff-based PR review across code quality, test coverage, silent failures, type design, and comment quality with…