Skip to main content
affpapa.org
RU EN
skill CX Codex

review-pr · neolabhq — Claude Code skill: what it does, how to install

Reviews an open GitHub pull request and leaves inline comments on the diff. Handy when the work sits in a PR, not in your local tree.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add NeoLabHQ/context-engineering-kit --skill review-pr -a claude-code
Open on GitHub

What review-pr does

The skill runs a multi-agent pass over a pull request. It starts by reading git status and diff statistics to size up the change, then hands chunks of files to as many as six agents working in parallel. Each one checks a different angle: vulnerabilities, bugs, code quality, type and API contracts, test coverage, and file history through git blame.

Every issue then gets a confidence score and an impact score. The --min-impact flag sets the cutoff, with critical, high, medium, medium-low and low as accepted values; high is the default. Any free text in the arguments names review aspects, such as “security, performance”. Only inline comments on code get published — the skill is explicit that it posts no overall review report. Folders spec/ and reports/ stay out unless you ask for them.

You need GitHub access and a local clone with history, because the diff comes from commands like git diff origin/master...HEAD. On a repo whose default branch is main, edit that command yourself — otherwise the diff comes back empty.

What it helps with

  • check an open pull request before merging
  • attach a comment to the exact changed line
  • filter noise with an impact threshold
  • match findings against rules in CLAUDE.md
  • trace who touched each modified file

Example prompts for the agent

  • Review pull request 128, focus on security and error handling
  • Check the PR on my current branch with --min-impact medium
  • Review the changes under src/api/ and comment inline

How to install review-pr

1Skills CLI (Vercel)

npx skills add NeoLabHQ/context-engineering-kit --skill review-pr -a claude-code

2Manually: put the files in place

~/.claude/skills/review-pr/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/review-pr/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about review-pr

How do I install review-pr in Claude Code?

Run npx skills add NeoLabHQ/context-engineering-kit --skill review-pr -a claude-code, then check that ~/.claude/skills/review-pr/SKILL.md exists.

What does review-pr do?

It reviews an open pull request with several agents and posts comments on the diff inline. No overall report is produced.

What does --min-impact control?

The lowest importance level an issue needs to be published as a comment. Default is high; levels run from critical down to low.

Similar skills

All skills for Code review and refactoring →

review-pr by other authors comes first.

review-pr tirth8205 This skill reviews a PR or branch through a code knowledge graph, showing risk, affected flows, and test gaps. Use it when a diff needs structural context. CX Codex +1 1,200installs improve-codebase-architecture Matt Pocock This skill scans a codebase for architectural friction, then builds a visual HTML report with refactoring candidates. Use it before a deeper architecture review. 1,163,035installs tdd Matt Pocock Guides the red-green TDD loop: ensures tests are written first, keep them at public interfaces, and avoid coupling to implementation details. 1,141,062installs triage Matt Pocock This skill moves issues and external PRs through triage states, verification, and agent briefs. It fits maintainers managing an issue queue. 990,453installs codebase-design Matt Pocock This skill helps design modules with small interfaces and hidden complexity. Use it when refactoring code, choosing a seam, or making tests easier to write. 850,344installs code-review Matt Pocock Reviews changes from a chosen reference point against repository standards and the originating spec. Use it for a branch, PR, or work in progress. 789,521installs implement Matt Pocock Implements work from a specification or tickets, following a test-driven flow and ending with review and a commit. Use it when a coding task needs a defined delivery routine. 774,700installs

From the same set64

tree-of-thoughts Runs a hard task through three parallel agents, a pruning vote and a synthesis pass. Useful when the right approach isn't obvious up front. CX Codex +1 1,200installs create-rule A skill that walks you through writing a rule file in .claude/rules/ so your agent stops repeating the same mistake. CX Codex +1 1,200installs launch-sub-agent Dispatches a focused sub-agent with isolated context, automated model routing, and mandatory self-critique verification. CX Codex +1 1,200installs do-and-judge This skill sends a task to an implementation sub-agent, checks the result with an independent judge, and retries with feedback when needed. CX Codex +1 1,200installs analyse Selects a Kaizen technique for your target, running code exploration via Gemba Walk, workflow reviews with VSM, or waste audits using Muda. CX Codex +1 1,200installs judge The skill runs a two-stage review of work from the current conversation: one sub-agent sets the criteria, another scores the result with evidence. CX Codex +1 1,200installs add-task Turns your request into a task file under .specs/tasks/draft/, with a verb-first title, a type and your original wording. The first step of a spec-driven workflow. CX Codex +1 1,200installs do-in-parallel Runs isolated tasks across separate files concurrently via sub-agents and validates work with automated judges. Fits batch refactoring and doc generation. CX Codex +1 1,200installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor