New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Code Review

by johnku2011 in johnku2011/boilerplates-with-ai-skills

A skill your agent uses when reviewing a diff or pull request — check correctness, tests, readability, security, and server/client boundaries before approving.

MITAuto-check passedDevelopment

Install Code Review

skills CLI
$ npx skills add johnku2011/boilerplates-with-ai-skills --skill code-review -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install johnku2011/boilerplates-with-ai-skills code-review --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/johnku2011/boilerplates-with-ai-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/shared/skills/code-review .claude/skills/code-review && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
code-review
GitHub stars
240
Token cost
~708 tokens
SKILL.md length
319 words
Files
1
Skills in repo
18
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when reviewing a diff or pull request — check correctness, tests, readability, security, and server/client boundaries before approving.

  • Works in 7 steps: Read the change description and confirm… → Identify scope: which files, routes, or… → Check correctness: edge cases, error… → …
  • Reviewing a diff
  • SKILL.md covers Overview, When to Review, Process and Review Checklist, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Code Review is an agent skill from johnku2011/boilerplates-with-ai-skills. Use when reviewing a diff or pull request — check correctness, tests, readability, security, and server/client boundaries before approving.

Its SKILL.md is about 710 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: Git working tree or PR diff available

It sits in Development, covering Plain language and style rules, Code review and Pull requests. The licence is MIT.

When your agent uses it

  • Reviewing a diff
  • Pull request — check correctness
  • Server/client boundaries before approving

Example prompts

  • “/code-review”

Requirements

  • Compatibility (from SKILL.md): Git working tree or PR diff available
  • Pre-approved tools (allowed-tools): Read, Grep

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Read the change description and confirm it matches the diff.
  2. Identify scope: which files, routes, or modules changed and why.
  3. Check correctness: edge cases, error handling, and inputs that could break.
  4. Check tests: is new behavior covered? Do existing tests still pass?
  5. Check readability: clear names, small functions, no dead code.
  6. Check boundaries: server-only code must not leak to client bundles or logs.
  7. Note security concerns as blocking (see project-security skill).

What it can do on your machine

Read from SKILL.md and the folder at commit 475dc6a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Grep

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Git working tree or PR diff available

    From compatibility in the SKILL.md frontmatter.

Context cost

Code Review loads about 708 tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 319 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~38
When it runs · the whole SKILL.md, loaded when a task matches
~708

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from johnku2011/boilerplates-with-ai-skills at commit 475dc6a, republished under its MIT licence (© johnku2011). 319 words, ~708 tokens.

Download SKILL.mdSave it as .claude/skills/code-review/SKILL.md (or your agent's skills folder).
name
code-review
description
Use when reviewing a diff or pull request — check correctness, tests, readability, security, and server/client boundaries before approving.
allowed-tools
Read, Grep
compatibility
Git working tree or PR diff available
license
MIT
metadata.suite
quality

Code Review

Overview

Give a focused, constructive review of a change. Separate blocking issues from optional suggestions. Review the work product (diff + tests), not the author's process.

Core principle: Review early, review often — before merge, not after production.

When to Review

Mandatory:

  • Before merging to the main branch
  • After completing a major feature or multi-file change
  • When security-sensitive paths change (auth, payments, user data)

Valuable:

  • After fixing a non-trivial bug (regression check)
  • Before a large refactor (baseline sanity check)

Process

  1. Read the change description and confirm it matches the diff.
  2. Identify scope: which files, routes, or modules changed and why.
  3. Check correctness: edge cases, error handling, and inputs that could break.
  4. Check tests: is new behavior covered? Do existing tests still pass?
  5. Check readability: clear names, small functions, no dead code.
  6. Check boundaries: server-only code must not leak to client bundles or logs.
  7. Note security concerns as blocking (see project-security skill).

Review Checklist

AreaBlocking if…
CorrectnessWrong logic, missing error handling, race conditions
TestsNew behavior untested; tests deleted without replacement
SecurityUnvalidated input, secrets in code/logs, missing auth
API shapeBreaking changes without migration or docs
PerformanceObvious N+1, unbounded loops, sync I/O on hot paths

Output Format

Use this structure every time:

## Blocking
- [file:line] Issue — concrete fix

## Suggestions
- [file:line] Optional improvement

## Verdict
approve | approve-with-nits | request-changes
  • List blocking issues first, each with a concrete fix.
  • Then non-blocking suggestions.
  • End with an explicit verdict.

Integration with TDD

If the change adds behavior without a failing test first, that is a blocking issue unless the author documents why (e.g. config-only change). Ask for tests that prove the behavior.

Anti-patterns

  • Approving without checking tests or security-sensitive paths.
  • Nitpicking style while missing error handling.
  • Vague feedback ("this feels wrong") without a concrete fix.
  • Reviewing the conversation instead of the diff.
  • Rubber-stamping because "it's small."

When You Disagree

Push back with technical reasoning. Cite failing tests, spec requirements, or security impact. Request clarification when the intent is unclear.

© johnku2011, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in shared/skills/code-review of johnku2011/boilerplates-with-ai-skills.

Open the folder on GitHubat commit 475dc6a

Compare with similar skills

Code Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Code Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Code Review this skilljohnku2011/boilerplates-with-ai-skills240—~708Automated safety check: PassMIT
Code Reviewhardness1020/Leeway115—~301Automated safety check: PassMIT
Code Reviewgetsentry/warden414—~1.9kAutomated safety check: PassCustom licence
Code Walkthroughtestdouble/han279—~4.4kAutomated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Understand Diff AnalysisEgonex-AI/Understand-Anything85k1 repos~1.4kAutomated safety check: PassMIT

Similar skills

  • Code Review

    hardness1020/Leeway

    Code quality review — identify patterns, anti-patterns, and improvements.

    115 GitHub stars~301 tokensUpdated 4 mo ago
    DevelopmentAuto-check passed

  • Code Review

    getsentry/warden

    Official

    Finds real correctness bugs in code changes. An agent skill from getsentry/warden.

    414 GitHub stars~1.9k tokensUpdated 7 days ago
    DevelopmentAuto-check passed

  • Code Walkthrough

    testdouble/han

    Walks a person through code changes one step at a time in conversation, starting at the entry point and following the flow that changes, showing a small chunk per step and explaining it in plain…

    279 GitHub stars~4.4k tokensUpdated 6 days ago
    DevelopmentAuto-check passed

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed

  • Understand Diff Analysis

    Egonex-AI/Understand-Anything

    Reads your git changes or a pull request against a prebuilt knowledge graph of the project to explain what changed, which components are affected and what is risky.

    85k GitHub starsUsed in 1 repo~1.4k tokens
    DevelopmentAuto-check passed

  • WooCommerce Code Review

    woocommerce/woocommerce

    Reviews WooCommerce code changes against the project's standards, flagging backend PHP architecture, naming, documentation, data integrity and testing violations.

    11k GitHub starsUsed in 3 repos~1.1k tokens
    DevelopmentAuto-check passed

More from johnku2011/boilerplates-with-ai-skills

All 18 skills in this repo

  • Project Security

    johnku2011/boilerplates-with-ai-skills

    A skill your agent uses when reviewing security-sensitive code paths — check auth, secrets, input validation, dependency risk, and data exposure before shipping.

    240 GitHub stars~650 tokensUpdated 1 mo ago
    Auto-check passed

  • Python API Design

    johnku2011/boilerplates-with-ai-skills

    A skill your agent uses when adding or changing FastAPI routes, dependencies, or tests in this Python service — keep endpoints typed, validated, and covered by pytest.

    240 GitHub stars~449 tokensUpdated 1 mo ago
    Auto-check passed

  • Bwai Advisor

    johnku2011/boilerplates-with-ai-skills

    Use before scaffolding a bwai project — runs the full startup-goal workflow then recommends the right boilerplate and outputs the exact bwai new command to run.

    240 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed

  • Deploy Vercel

    johnku2011/boilerplates-with-ai-skills

    A skill your agent uses when deploying or configuring this project on Vercel — env vars, build settings, serverless limits, and production checks for Next.js or Express.

    240 GitHub stars~660 tokensUpdated 1 mo ago
    Auto-check: notes

  • Express API Design

    johnku2011/boilerplates-with-ai-skills

    A skill your agent uses when adding or changing routes, middleware, or error handling in this Express.js API, to keep endpoints consistent, validated, and testable.

    240 GitHub stars~575 tokensUpdated 1 mo ago
    Auto-check passed

  • Nextjs App Router

    johnku2011/boilerplates-with-ai-skills

    A skill your agent uses when adding pages, layouts, route handlers, or data fetching in this Next.js App Router project, to follow server-first conventions correctly.

    240 GitHub stars~587 tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Code Review

What does Code Review do?

A skill your agent uses when reviewing a diff or pull request — check correctness, tests, readability, security, and server/client boundaries before approving. Code Review is an agent skill from johnku2011/boilerplates-with-ai-skills. Use when reviewing a diff or pull request — check correctness, tests, readability, security, and server/client boundaries before approving.

When should I use Code Review?

Code Review fits situations like: reviewing a diff; pull request — check correctness; server/client boundaries before approving.

How do I install Code Review in Claude Code?

Run `npx skills add johnku2011/boilerplates-with-ai-skills --skill code-review -a claude-code`. Or copy the skill folder (shared/skills/code-review in johnku2011/boilerplates-with-ai-skills) into .claude/skills/code-review in your project. Claude Code loads it when a task matches its description.

How do I install Code Review in Codex?

Run `npx skills add johnku2011/boilerplates-with-ai-skills --skill code-review -a codex`. Or copy the skill folder (shared/skills/code-review in johnku2011/boilerplates-with-ai-skills) into .agents/skills/code-review in your project. Codex loads it when a task matches its description.

Can I use Code Review in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add johnku2011/boilerplates-with-ai-skills --skill code-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/code-review, .gemini/skills/code-review, .github/skills/code-review and .opencode/skills/code-review in your project.

What does Code Review need to run?

SKILL.md names no scripts, command-line tools or credentials: Code Review is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Grep. Compatibility (from SKILL.md): Git working tree or PR diff available.

Does Code Review access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Code Review safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Code Review use?

Code Review is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Code Review use?

About 708 tokens (SKILL.md is roughly 2.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Code Review?

Skills that share tags, products or a category with Code Review: Code Review (hardness1020/Leeway, 115 stars), Code Review (getsentry/warden, 414 stars), Code Walkthrough (testdouble/han, 279 stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Code Review?

johnku2011 (a GitHub user) maintains it in johnku2011/boilerplates-with-ai-skills, which has 240 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on August 24, 2026.

Source: johnku2011/boilerplates-with-ai-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.