Peer Review

Review a change the way a respected colleague would — design and craft lenses applied to the diff, every finding verified in the code, and the result written as kind, specific comments anchored to lines. Loads clean-code, fractal-architecture, responsibility-driven-design and domain-driven-design for the production code; unit-testing-principles (Khorikov's four pillars, managed vs unmanaged dependencies), art-of-unit-testing, xunit-test-patterns and test-data-patterns for the tests, including a map of every promised scenario to the test that pins it and a check that no guard can be removed wit

5 stars 2 forksTesting & QA Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add vnovakovits/claude-skills

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add vnovakovits/claude-skills --skill peer-review
Manual install
git clone --depth 1 https://github.com/vnovakovits/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/plugins/engineering-practices/skills/peer-review ~/.claude/skills/peer-review

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Peer Review

Review the change the user names — a pull request number, a branch, or nothing for the current branch against its base — and write the review they would want to receive from a colleague they respect.

**Local only.** Print the review. Never post, edit, approve or request changes on the hosting service unless the user asks for that in so many words; they paste what they agree with.

## 1. Get the change

- A number → `gh pr view <n>` for title and description, `gh pr diff <n>` for the diff.
- A branch or nothing → `git merge-base` with `master` (or `main`), then `git diff <base>...HEAD`.
- Read the surrounding code, not just the hunks. A finding that depends on context must be checked in the file.
- Skip `CLAUDE.md`, `AGENTS.md`, lockfiles and generated files.

## 2. Load the lenses

Load these skills before reading the diff:

- `clean-code` — names, function size, one level of abstraction, comments only for a why.
- `fractal-architecture` — does each unit fit in a head: ≤ ~7 chunks, cyclomatic complexity ≤ 7, no partial functions, invariants enforced.
- `responsibility-driven-design` — who knows, who does, who decides; Tell, Don't Ask; information expert; no god objects or middle men.
- `domain-driven-design` — ubiquitous language in names, value objects over primitives, aggregate boundaries, domain events as facts, layering.
- The unit-testing lenses, all four, for every test file in the diff:
Read the full skill on GitHub

Details

Skill name
peer-review
Path
plugins/engineering-practices/skills/peer-review/SKILL.md
License
MIT
Repo updated
16 November 2026

FAQ

What does the Peer Review skill do?

Review a change the way a respected colleague would — design and craft lenses applied to the diff, every finding verified in the code, and the result written as kind, specific comments anchored to lines. Loads clean-code, fractal-architecture, responsibility-driven-design and domain-driven-design for the production code; unit-testing-principles (Khorikov's four pillars, managed vs unmanaged dependencies), art-of-unit-testing, xunit-test-patterns and test-data-patterns for the tests, including a map of every promised scenario to the test that pins it and a check that no guard can be removed wit

How do I install the Peer Review skill?

Claude Code plugin: /plugin marketplace add vnovakovits/claude-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Peer Review popular?

It lives in vnovakovits/claude-skills, which has 5 GitHub stars and 2 forks.

Related skills

Accidental Cio

5

vnovakovits/claude-skills

Apply Scott Millett's "The Accidental CIO — A Lean and Agile Playbook for IT Leaders" (Wiley, 2024) when designing or reviewing how a technology organisation decides, funds, governs and delivers work. Covers the five components of an adaptive IT operating model (organised, work, govern, talent, lead) and its four themes (outcomes over output, intrinsic motivation, being not doing agile, manage flow not people); matching method and governance to context via Cynefin and Wardley evolution; governance as demand management + funding + measurement + decision rights, shifting from project funding to

Frontend & Design

Agent Retro

5

vnovakovits/claude-skills

Run a retrospective on a coding-agent session and improve the agent's environment, not the code. Combines Derby & Larsen's five-stage retrospective, Shigeo Shingo's poka-yoke (turn a mechanical mistake into a check that makes it impossible), and Matt Pocock's retro categories — navigation, automated checks, coding standards, steering files, tool economy, information access. Covers mining the session transcript for corrections, wrong turns and slow searches; deciding where each fix belongs (analyzer, hook, CI, reviewer standards, CLAUDE.md pointer, skill, doc or memory); the no-op test for stee

AI, LLMs & Agents

API Design

5

vnovakovits/claude-skills

Design APIs that are clear, evolvable, and idiomatic to their protocol — covering REST (Fielding, Richardson Maturity Model, Massé), GraphQL, gRPC/protobuf, versioning strategies, pagination, error responses (RFC 7807 Problem Details), idempotency, authentication, documentation (OpenAPI), and the pragmatic trade-offs between RESTful purity and developer ergonomics. Use when designing a new endpoint, choosing between REST/GraphQL/gRPC, defining versioning, structuring error responses, deciding pagination strategy, or evaluating an existing API's evolvability.

Software Development

Playwright

5

bolasblack/claude-skills

Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.

Testing & QA

Grill Me

5

bolasblack/claude-skills

Stress-test a plan, design, decision, or idea through a focused interview. Use when the user asks to be grilled, challenge their thinking, or resolve design choices before proceeding.

Testing & QA

Playwright Frontend Testing

8

Freddy-CHEN-ux/00_claude_skills

Use when testing frontend applications. AI-assisted browser testing with Playwright MCP. Fast, deterministic, no vision models needed.

Testing & QA

Browse the most popular Claude skills, all testing & qa skills, or write your own with the skills generator.