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 Hyk260 in Hyk260/PureChat

Perform code reviews (CR) for changed files in the current repository.

MITAuto-check passedDevelopment

Install Code Review

skills CLI
$ npx skills add Hyk260/PureChat --skill code-review -a claude-code

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

GitHub CLI
$ gh skill install Hyk260/PureChat 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/Hyk260/PureChat.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/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
546
Token cost
~645 tokens
SKILL.md length
302 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

Perform code reviews (CR) for changed files in the current repository.

  • Works in 5 steps: Identify Changes → Review Focus Areas → Check Project-Specific Rules → …
  • The user asks to review code
  • SKILL.md covers Workflow and Review Principles
  • Calls pnpm

What it does

Code Review is an agent skill from Hyk260/PureChat. Perform code reviews (CR) for changed files in the current repository. Use when the user asks to review code, review changes, perform a code review, or mentions CR / code review.

Its SKILL.md is about 650 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Code review. It works with OpenAI, Ollama, Vercel and Vite. The repository describes itself as: PureChat 是一款全面的聊天应用程序，它将传统的即时消息与高级 AI 功能集成在一起。其模块化架构、可扩展的 AI 集成系统和灵活的配置选项使其成为强大的应用程序，也是 AI 增强通信应用程序的坚实基础。支持OpenAI，Ollama，DeepSeek等大语言模型，Markdown 渲染，聊天记录生成截图，主题切换，助力开发者快速掌握现代技术。 The licence is MIT.

When your agent uses it

  • The user asks to review code
  • Perform a code review
  • Mentions CR / code review

Example prompts

  • “/code-review”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Identify Changes
  2. Review Focus Areas
  3. Check Project-Specific Rules
  4. Present Results
  5. Optional — Apply Fixes

What it can do on your machine

Read from SKILL.md and the folder at commit abb2ec1. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • pnpm

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

  • Network

    No URLs in SKILL.md. Its commands use pnpm, which can reach the network depending on how they are called.

    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.

Context cost

Code Review loads about 645 tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 302 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~48
When it runs · the whole SKILL.md, loaded when a task matches
~645

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 Hyk260/PureChat at commit abb2ec1, republished under its MIT licence (© Hyk260). 302 words, ~645 tokens.

Download SKILL.mdSave it as .claude/skills/code-review/SKILL.md (or your agent's skills folder).
name
code-review
description
Perform code reviews (CR) for changed files in the current repository. Use when the user asks to review code, review changes, perform a code review, or mentions CR / code review.

Code Review

Perform code reviews for changed files in the current repository.

Workflow

Step 1: Identify Changes

Determine the scope of the code review:

  • Check the current working directory and project structure
  • Identify which files need review:
    • If the user specifies specific files, review those
    • If the user mentions a PR or branch, check the diff
    • If unspecified, check git status / diff for recently changed files
    • Search the codebase for recent changes if needed
Step 2: Review Focus Areas

For each file, systematically review:

  • Correctness: Does the code work as intended? Any logic errors or edge cases missed?
  • Type safety: Proper TypeScript types, avoid any, no unsafe assertions?
  • Code style: Follows project conventions (see AGENTS.md / CLAUDE.md)?
  • Consistency: Naming, imports, structure consistent with rest of codebase?
  • Performance: Any obvious performance concerns or unnecessary complexity?
  • Security: No hardcoded secrets, no unsafe patterns?
  • Maintainability: Clear, readable, properly commented where needed?
Step 3: Check Project-Specific Rules

Reference the project's AGENTS.md / CLAUDE.md for:

  • Code style requirements
  • TypeScript conventions
  • Lint / build / dev commands
  • Directory structure conventions
Step 4: Present Results

Summarize the review findings with:

  • File-by-file observations with specific line references
  • Issues categorized: 🔴 Critical / 🟡 Major / 🟢 Minor / 💡 Suggestion
  • Actionable recommendations for each issue
  • Positive highlights for good patterns or improvements

Format findings clearly using markdown with code references.

Step 5: Optional — Apply Fixes

If the user requests fixes or you determine changes are necessary:

  • Create a todo list for the planned fixes
  • Apply fixes incrementally, keeping each change focused
  • Run project validation commands after changes:
    • pnpm lint
    • pnpm build
    • pnpm dev (when relevant)

Review Principles

  • Be constructive and specific — avoid vague feedback
  • Cite file paths and line numbers when referencing issues
  • Prioritize: correctness > safety > maintainability > style
  • Follow the project's existing patterns over personal preferences
  • Do not modify test files to make tests pass (see Bug Fixing strategy in AGENTS.md)

© Hyk260, 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 .agents/skills/code-review of Hyk260/PureChat.

Open the folder on GitHubat commit abb2ec1

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 skillHyk260/PureChat546—~645Automated safety check: PassMIT
Deep Reviewdyad-sh/dyad22k—~1.4kAutomated safety check: PassCustom licence
Remember Learningsdyad-sh/dyad22k—~1.1kAutomated safety check: PassCustom licence
Test Coveragescott-fryxell/brayness124—~1.6kAutomated safety check: PassMIT
Page AgentTommy-yw/RunbookHermes5463 repos~2.3kAutomated safety check: NotesMIT
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • Deep Review

    dyad-sh/dyad

    Deep multi-agent code review run locally — a fleet of parallel finder agents reviews the diff from independent angles, then adversarial verifier agents reproduce each finding before it is reported.

    22k GitHub stars~1.4k tokensUpdated today
    DevelopmentAuto-check passed

  • Remember Learnings

    dyad-sh/dyad

    Review the current session for errors, issues, snags, and hard-won knowledge, then update the rules/ files (or AGENTS.md if no suitable rule file exists) with actionable learnings.

    22k GitHub stars~1.1k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Test Coverage

    scott-fryxell/brayness

    Write Vitest specs for Vue 3 JavaScript (Vite Plus, happy-dom, @vue/test-utils) and analyze V8 coverage + Fallow health to prioritize test-first refactors.

    124 GitHub stars~1.6k tokensUpdated 9 days ago
    Testing & QAAuto-check passed

  • Page Agent

    Tommy-yw/RunbookHermes

    Embed alibaba/page-agent into your own web application — a pure-JavaScript in-page GUI agent that ships as a single <script tag or npm package and lets end-users of your site drive the UI with…

    546 GitHub starsUsed in 3 repos~2.3k tokens
    Productivity & AutomationAuto-check: notes

  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed

  • Open Code Review CLI

    alibaba/open-code-review

    Runs the ocr command-line tool to review Git changes, a commit or a branch comparison with an AI model, returning line-level comments and optionally applying fixes.

    44k GitHub stars~3.1k tokensUpdated 2 days ago
    DevelopmentAuto-check passed

More from Hyk260/PureChat

  • Create Skill

    Hyk260/PureChat

    Create a new skill in the current repository. An agent skill from Hyk260/PureChat.

    546 GitHub starsUsed in 1 repo~823 tokens
    Auto-check passed

  • Check Deps Sync

    Hyk260/PureChat

    Check if package.json files are in sync with pnpm-lock.yaml.

    546 GitHub stars~594 tokensUpdated 20 days ago
    Auto-check passed

Works with

Categories

Questions about Code Review

What does Code Review do?

Perform code reviews (CR) for changed files in the current repository. Code Review is an agent skill from Hyk260/PureChat. Perform code reviews (CR) for changed files in the current repository.

When should I use Code Review?

Code Review fits situations like: the user asks to review code; perform a code review; mentions CR / code review.

How do I install Code Review in Claude Code?

Run `npx skills add Hyk260/PureChat --skill code-review -a claude-code`. Or copy the skill folder (.agents/skills/code-review in Hyk260/PureChat) 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 Hyk260/PureChat --skill code-review -a codex`. Or copy the skill folder (.agents/skills/code-review in Hyk260/PureChat) 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 Hyk260/PureChat --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?

Going by SKILL.md and its folder, Code Review needs the command-line tools its instructions call (pnpm).

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 (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Code Review use?

About 645 tokens (SKILL.md is roughly 2.6k 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: Deep Review (dyad-sh/dyad, 22k stars), Remember Learnings (dyad-sh/dyad, 22k stars), Test Coverage (scott-fryxell/brayness, 124 stars) and Page Agent (Tommy-yw/RunbookHermes, 546 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Code Review?

Hyk260 (a GitHub user) maintains it in Hyk260/PureChat, which has 546 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on September 17, 2026.

Source: Hyk260/PureChat on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.