Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问许可证需确认审计异常

python-code-reviewerPython 代码 reviewer

Agent Skill

用于辅助 Python 项目开发、测试、依赖管理和常见框架工作流。它适合让 Agent 阅读 Python 代码、定位测试问题、整理运行命令、生成脚本或分析数据处理逻辑。使用时需要确认项目虚拟环境、依赖版本和测试入口;涉及执行脚本、读写文件、访问数据库或调用外部 API 时,应先明确运行目录和输入输出范围,避免误改生产数据。

总安装

599

周安装

24

GitHub Stars

3

下载量

194
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:python-code-reviewer(Python 代码 reviewer)
来源仓库:https://github.com/yennanliu/ai_experiment
仓库路径:skills/python-code-reviewer
安装命令:
npx skills add https://github.com/yennanliu/ai_experiment --skill python-code-reviewer
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/yennanliu/ai_experiment --skill python-code-reviewer

简介

作为专业 Python 代码评审助手提供持续反馈。

  • 支持多文件关联分析和上下文感知建议。python-code-reviewer 属于研究检索类 Skill,可作为该场景下的辅助能力补充。
  • 强调可读性、一致性和维护性最佳实践。
  • 安装方式:从 ai_experiment 项目获取 reviewer 技能包。
  • 可与 Git 工作流结合实现 PR 自动化评审。

SKILL.md

Python Code Reviewer

Instructions

When reviewing Python code, follow this comprehensive review format:

1. Strengths Section (✅)

Identify and highlight what's working well:

  • Good code organization and structure
  • Proper use of Python idioms and patterns
  • Clear documentation (docstrings, comments)
  • Appropriate error handling
  • Good naming conventions
  • Proper use of language features

2. Issues & Concerns Section (⚠️)

Categorize issues by severity:

Critical Bugs:

  • Runtime errors (ZeroDivisionError, IndexError, etc.)
  • Logic errors that break functionality
  • Security vulnerabilities (injection, XSS, etc.)
  • Reference specific line numbers using format: filename:line_number

Recommendations:

  • Code quality improvements
  • Better error handling
  • Edge case handling
  • Performance optimizations
  • Code maintainability issues

3. Code Examples

For each issue or recommendation:

  • Provide concrete code examples showing the fix
  • Use proper Python formatting
  • Show both the problem and solution
  • Explain why the change improves the code

4. Additional Considerations

Review for:

  • Edge cases: Empty inputs, boundary conditions, null/None values
  • Type safety: Consider suggesting type hints
  • Code style: PEP 8 compliance, consistent formatting
  • Testing: Are there testable concerns or missing validations?
  • Documentation: Are docstrings clear and complete?
  • Performance: Any obvious performance bottlenecks?
  • Security: Input validation, SQL injection, command injection, etc.

5. Overall Rating

Provide a score out of 10 with brief justification:

  • 9-10: Production-ready, minimal issues
  • 7-8: Good quality, minor improvements needed
  • 5-6: Functional but needs refactoring
  • 3-4: Significant issues, requires major work
  • 1-2: Critical problems, needs rewrite

6. Summary

End with a concise 1-2 sentence summary of the code quality and main concerns.

Review Checklist

Always check for:

  • Division by zero or similar runtime errors
  • Empty collection handling (lists, dicts, etc.)
  • Input validation and sanitization
  • Exception handling completeness
  • Resource management (file handles, connections)
  • Security vulnerabilities (OWASP Top 10)
  • Type correctness and potential type errors
  • Function side effects and purity
  • Code duplication and DRY principle
  • Naming clarity and consistency

Best Practices

  1. Be specific: Always reference line numbers using filename:line_number format
  2. Be constructive: Frame issues as opportunities for improvement
  3. Provide context: Explain WHY something is an issue, not just WHAT
  4. Show examples: Demonstrate better approaches with code snippets
  5. Prioritize: Critical bugs first, then recommendations
  6. Consider scope: Don't over-engineer simple scripts, don't under-engineer production code

Response Format Template

## Code Review: `path/to/file.py`

[Brief description of what the code does]

### ✅ Strengths

1. [Strength 1]
2. [Strength 2]
...

### ⚠️ Issues & Concerns

**Critical Bug (filename:line_number):**
[Description and code reference]

**Recommendations:**
1. [Recommendation with code example]
2. [Recommendation with code example]
...

### 📊 Overall Rating: X/10

**Summary:** [1-2 sentence summary]

Tool Usage

  • Use Read to examine the code file
  • Use Grep if you need to search for patterns across multiple files
  • Use Glob to find related files if reviewing a module
  • Do NOT use Edit or Write unless explicitly asked to fix issues

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

33.49%
按下载量换算65

Claude

27.69%
按下载量换算54

Cursor

20.88%
按下载量换算41

Gemini CLI

8.47%
按下载量换算16

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

未通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills