生成面向 code review 任务的中文 prompt。用于审查代码、文档、配置、PR diff、指定 commit 或发布前风险;默认只生成审查任务 prompt,不直接 review,也不直接修改代码。

MITAuto-check passedDevelopment

Install Code Reviewer

skills CLI
$ npx skills add Philip-Cao-9527/code-note-helper --skill code-reviewer -a claude-code

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

GitHub CLI
$ gh skill install Philip-Cao-9527/code-note-helper code-reviewer --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/Philip-Cao-9527/code-note-helper.git skills-src && mkdir -p .claude/skills && cp -r skills-src/vibe-coding-template/skills/code-reviewer .claude/skills/code-reviewer && 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-reviewer
GitHub stars
273
Token cost
~599 tokens
SKILL.md length
168 words
Files
3 (incl. references)
Skills in repo
13
Repo updated
First seen
Licence
MIT

At a glance

生成面向 code review 任务的中文 prompt。用于审查代码、文档、配置、PR diff、指定 commit 或发布前风险;默认只生成审查任务 prompt,不直接 review,也不直接修改代码。

  • Works in 5 steps: 确认用户要的是生成 code review prompt,不是直接审查或直接改代码。 → 明确审查范围 → 读取目标项目 AGENTS.md、README、测试说明和与审查范围相关的规则。 → …
  • Tasks that involve Code review
  • SKILL.md covers 技能定位, Skill 交叉引用规则, 使用流程 and 审查重点生成规则, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Code Reviewer is an agent skill from Philip-Cao-9527/code-note-helper. 生成面向 code review 任务的中文 prompt。用于审查代码、文档、配置、PR diff、指定 commit 或发布前风险;默认只生成审查任务 prompt,不直接 review,也不直接修改代码。

Its SKILL.md is about 600 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `agents/openai.yaml` and `references/review-template.md`).

It sits in Development, covering Code review. The repository describes itself as: 一个专为算法刷题、深度学习和 AI 学习场景打造的浏览器扩展。拒绝机械的复制粘贴,帮你自动化生成高质量复盘笔记、内置遗忘曲线驱动的间隔复习、轻松驾驭超长对话,让刷过的每一道题都成为真正的技术资产!. The licence is MIT.

When your agent uses it

  • Tasks that involve Code review

Example prompts

  • “/code-reviewer”

Workflow steps

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

  1. 确认用户要的是生成 code review prompt,不是直接审查或直接改代码。
  2. 明确审查范围
  3. 读取目标项目 AGENTS.md、README、测试说明和与审查范围相关的规则。
  4. 读取 references/review-template.md,按项目类型和审查范围裁剪。
  5. 输出一个完整、连续、可复制的 code review prompt。

What it can do on your machine

Read from SKILL.md and the folder at commit 7421249. 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

    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.

Context cost

Code Reviewer loads about 599 tokens when it runs, and up to ~2.3k if it reads all its reference files. Until then it costs about 30 tokens; SKILL.md has 168 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~30
When it runs · the whole SKILL.md, loaded when a task matches
~599
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.3k

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 Philip-Cao-9527/code-note-helper at commit 7421249, republished under its MIT licence (© Philip-Cao-9527). 168 words, ~599 tokens.

Download SKILL.mdSave it as .claude/skills/code-reviewer/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
code-reviewer
description
生成面向 code review 任务的中文 prompt。用于审查代码、文档、配置、PR diff、指定 commit 或发布前风险;默认只生成审查任务 prompt,不直接 review,也不直接修改代码。

code-reviewer

技能定位

生成 code review prompt。这个 skill 不直接审查当前代码,也不默认修复问题;它的产物是一份可复制给 Codex/Agent 执行的审查 prompt。

如果用户明确要求“直接 review 当前改动”,可以改用普通审查流程而不是本 skill。若用户要求“审查并修复”,最终 prompt 中也要先要求 findings first,再由用户或任务边界决定是否进入修复。

Skill 交叉引用规则

如果生成的 code review prompt 需要指向其他 skill,必须使用 $skill-name 形式引用,例如 $project-prompt-creator 或 $plan-mode-planner。不要只写反引号包裹的 skill 名称,也不要把 skill 名称写成普通说明。

使用流程

  1. 确认用户要的是生成 code review prompt,不是直接审查或直接改代码。
  2. 明确审查范围:
    • 当前分支 diff、指定 commit、PR diff、用户指定文件或目录。
    • 审查目标:发布前风险、行为回归、接口契约、文档一致性、安全隐私、测试缺口等。
  3. 读取目标项目 AGENTS.md、README、测试说明和与审查范围相关的规则。
  4. 读取 references/review-template.md,按项目类型和审查范围裁剪。
  5. 输出一个完整、连续、可复制的 code review prompt。

审查重点生成规则

生成 code review prompt 时,不要提供一份固定风险清单让执行者照单审查。固定清单会把审查范围锁死,容易漏掉当前项目真正重要的风险。

最终 prompt 必须要求执行者先建立本轮“项目化风险地图”,再从风险地图生成审查重点。风险地图至少回答:

  • 本次改动可能改变了哪些对用户、调用方、维护者或发布流程的承诺。
  • 哪些项目不变量、数据状态、交互边界、运行假设或文档承诺可能被破坏。
  • 哪些失败模式最难被发现、最难恢复,或者影响面最大。
  • 哪些证据足以证明本轮改动没有破坏关键路径。
  • 哪些风险来自 {{项目类型}}、{{审查范围}}、{{高风险领域}}、{{发布审核约束}}、{{用户可见文案要求}} 或用户明确边界。

可以给执行者提供“风险维度示例”,但必须明确它们只是启发,不是完整清单,也不能限制审查范围。生成最终 review prompt 时,应把不适用的示例删除,并要求执行者根据真实仓库补充项目专属风险。

输出要求

  • 最终 prompt 必须要求审查输出 findings first。
  • 默认 code review 只输出审查报告和建议,不直接修改代码。
  • 每条 finding 必须包含:严重级别、可跳转 Markdown 相对路径位置、证据、影响、可能的解决方案、验证建议;带行号时统一使用 [文件名](相对路径#L行号),不要把 :行号 写进链接目标。
  • 每个定位到的问题都要给出可能的解决方案,不能只写“建议修复”。解决方案要说明可行方向、涉及文件、预期影响和需要补充的验证;如果存在多种方案,可以给 1 到 3 个方向,但不要在证据不足时强行拍板。
  • 生成的 code review prompt 必须要求审查报告保存为单独 Markdown 文档。用户指定路径时使用用户路径;未指定路径时,要求执行者先根据项目习惯选择合理的 {{报告目录}},例如项目已有 docs/、reports/ 或类似目录,并在执行前说明路径。报告文件名应体现任务主题和日期,但不能写死当前仓库命名。
  • 审查报告至少包含:问题清单、严重程度、可跳转 Markdown 相对路径位置、证据摘要、影响说明、可能的解决方案、建议验证方式、是否阻塞合并 / 发布 / 交付、未覆盖风险或测试缺口;文件链接能定位到行号时必须使用 #L{行号} 锚点。
  • 问题按严重程度排序。
  • 如果没有发现问题,也要生成报告,明确说明未发现阻塞项、已检查范围、剩余风险和测试缺口。
  • 不要把 review prompt 写成实现 prompt;除非用户明确要求修复,否则只要求审查报告和建议。

输出包裹规则

  • 最终 code review prompt 必须整体放入一个 Markdown 文本块。
  • 如果 prompt 内部包含三反引号,外层使用四反引号或更长围栏。
  • 输出代码块前最多写一句中文引导;输出代码块后不要追加额外正文。

自检

输出前逐条检查:

  1. 是否明确本 skill 生成的是 review prompt,不是直接 review。
  2. 是否写清审查目标、范围、对比基准和不直接修改代码边界。
  3. 是否把审查重点按项目类型和风险域模板化。
  4. 是否要求 findings first、严重程度排序和证据链接。
  5. 是否包含没有发现问题时的输出规则和测试缺口说明。
  6. 如果 prompt 中交叉引用其他 skill,是否统一使用 $skill-name 形式。
  7. 是否没有把旧项目的权限、发布、版本或测试约束硬写进通用 prompt。

© Philip-Cao-9527, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in vibe-coding-template/skills/code-reviewer of Philip-Cao-9527/code-note-helper.

  • SKILL.md
  • agents/openai.yaml
  • references/review-template.md

Open the folder on GitHubat commit 7421249

Compare with similar skills

Code Reviewer 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 Reviewer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Code Reviewer this skillPhilip-Cao-9527/code-note-helper273—~599Automated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k4 repos~1.1kAutomated safety check: PassMIT
Backend Code Reviewlangflow-ai/langflow155k—~3.5kAutomated safety check: NotesMIT
Mole Bug Patternstw93/Mole70k—~2kAutomated safety check: PassGPL-3.0
Backend Code Reviewlanggenius/dify158k—~676Automated safety check: PassCustom licence

Similar skills

  • 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
  • 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 4 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Backend Code Review

    langflow-ai/langflow

    Review backend code for quality, security, maintainability, and best practices based on established checklist rules.

    155k GitHub stars~3.5k tokensUpdated today
    DevelopmentAuto-check: notes
  • A catalog of recurring bug shapes in the Mole Mac cleaner, used to review safety-sensitive diffs for deletion safety, unbounded commands, shell traps and weak tests.

    70k GitHub stars~2k tokensUpdated today
    DevelopmentAuto-check passed
  • Backend Code Review

    langgenius/dify

    Reviews backend code under api/ for concrete, reproducible defects, routes to rule packs for architecture, schema, repositories and SQLAlchemy, and ranks findings from P0 to P3.

    158k GitHub stars~676 tokensUpdated today
    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 Philip-Cao-9527/code-note-helper

All 13 skills in this repo
  • Agents Md Creator

    Philip-Cao-9527/code-note-helper

    基于项目真实背景、用户长期偏好和现有文档生成或更新项目级 AGENTS.md。用于新项目初始化、迁移协作规则、整理语言编码测试版本文档约束、沉淀长期协作底线和交付格式时使用。

    273 GitHub stars~581 tokensUpdated 2 mo ago
    Auto-check passed
  • Codenote Fix Prompt

    Philip-Cao-9527/code-note-helper

    为 CodeNote Helper 生成普通开发、修复、验证、治理、文档和审核友好类中文执行 prompt。用于把一次具体任务整理成可直接交给 Codex 或 Agent 执行的 prompt;不承载 Plan mode prompt、code review prompt 或项目 skill creator 的完整职责。

    273 GitHub stars~931 tokensUpdated 2 mo ago
    Auto-check passed
  • Codenote Skill Creator

    Philip-Cao-9527/code-note-helper

    创建或更新 CodeNote Helper 项目本地 .agents/skills 下的 Codex skills。用于把高频协作流程、prompt 生成流程、审查流程或项目专项流程沉淀为可复用 skill;不替代一次性任务 prompt、普通开发实现或万能规则汇总。

    273 GitHub stars~948 tokensUpdated 2 mo ago
    Auto-check passed
  • Project Prompt Creator

    Philip-Cao-9527/code-note-helper

    在项目 AGENTS.md 约束下生成可直接交给 Codex 或 Agent 执行的中文任务 prompt。用于开发、修复、文档、验证、审计、治理或交接任务的 prompt 化,但不承载 Plan mode 和 code review 的完整模式规则。

    273 GitHub stars~693 tokensUpdated 2 mo ago
    Auto-check passed
  • Project Skill Creator

    Philip-Cao-9527/code-note-helper

    基于用户需求和项目真实上下文创建或更新项目本地 skill。用于把高频协作流程、领域任务、项目规范、prompt 生成流程或审查流程沉淀为可复用 skill,并避免把一次性任务误做成长期 skill。

    273 GitHub stars~820 tokensUpdated 2 mo ago
    Auto-check passed
  • Knowledge Explainer

    Philip-Cao-9527/code-note-helper

    当用户要求技术原理讲解、八股讲解、从零教学、面试口述、项目追问回答、领域补课、把项目实现转成可复习表达,或在缺少领域背景时需要先理解概念再推进项目时使用;覆盖后端、前端、数据库、分布式、系统设计、编译构建、DevOps、安全、产品业务、数据分析、Agent、LLM、科研方法等可迁移领域。若涉及最新论文、官方文档、benchmark、争议结论或现代 API,先调用 $web-search。

    273 GitHub stars~899 tokensUpdated 2 mo ago
    Auto-check passed

Categories

Questions about Code Reviewer

What does Code Reviewer do?

生成面向 code review 任务的中文 prompt。用于审查代码、文档、配置、PR diff、指定 commit 或发布前风险;默认只生成审查任务 prompt,不直接 review,也不直接修改代码。. Code Reviewer is an agent skill from Philip-Cao-9527/code-note-helper.

When should I use Code Reviewer?

Code Reviewer fits situations like: tasks that involve Code review.

How do I install Code Reviewer in Claude Code?

Run `npx skills add Philip-Cao-9527/code-note-helper --skill code-reviewer -a claude-code`. Or copy the skill folder (vibe-coding-template/skills/code-reviewer in Philip-Cao-9527/code-note-helper) into .claude/skills/code-reviewer in your project. Claude Code loads it when a task matches its description.

How do I install Code Reviewer in Codex?

Run `npx skills add Philip-Cao-9527/code-note-helper --skill code-reviewer -a codex`. Or copy the skill folder (vibe-coding-template/skills/code-reviewer in Philip-Cao-9527/code-note-helper) into .agents/skills/code-reviewer in your project. Codex loads it when a task matches its description.

Can I use Code Reviewer 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 Philip-Cao-9527/code-note-helper --skill code-reviewer -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-reviewer, .gemini/skills/code-reviewer, .github/skills/code-reviewer and .opencode/skills/code-reviewer in your project.

What does Code Reviewer need to run?

SKILL.md names no scripts, command-line tools or credentials: Code Reviewer is instructions for the agent only.

Does Code Reviewer 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 Reviewer 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 Reviewer use?

Code Reviewer 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 Reviewer use?

About 599 tokens (SKILL.md is roughly 2.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.7k tokens, read only when the agent opens those files.

What are the alternatives to Code Reviewer?

Skills that share tags, products or a category with Code Reviewer: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Code Review Checklist (shareAI-lab/learn-claude-code, 78k stars), Backend Code Review (langflow-ai/langflow, 155k stars) and Mole Bug Patterns (tw93/Mole, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Code Reviewer?

Philip-Cao-9527 (a GitHub user) maintains it in Philip-Cao-9527/code-note-helper, which has 273 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on July 15, 2026.

Source: Philip-Cao-9527/code-note-helper on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.