agentleFS
hiltayhiltay/agent-skills/skills/readme-gen/SKILL.md

readme-gen

Skill4 starsChanged 9 months agoMITView on GitHub

为 Python 和 Rust 项目生成中文 README.md 文档。包含项目概述、安装指南、使用方法、配置说明和示例代码等标准章节。当用户要求生成 README、编写项目文档、创建项目说明,或提到 README.md 时使用此 skill。

  • Installs packages

4 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions4 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 4

    1. normieg/Readme-gen★ 2same name
    2. hacxy/skills★ 1same name
    3. sreedhargs89/claude-code-guide★ 1same name
    4. sissc0731/claude-code-skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repositoryOne other file it gives its agents.

The file

Files
SKILL.md

README 文档生成

为 Python / Rust 项目生成结构清晰、内容完整的中文 README.md。

工作流程

Task Progress:
- [ ] Step 1: 分析项目结构和代码
- [ ] Step 2: 确定文档章节
- [ ] Step 3: 生成 README 内容
- [ ] Step 4: 检查和完善

Step 1: 分析项目

在生成文档前,先收集项目信息:

  1. 读取项目根目录结构(ls / tree)
  2. 读取已有的配置文件:
    • Python: pyproject.toml > setup.py > setup.cfg > requirements.txt
    • Rust: Cargo.toml
  3. 浏览核心源码入口(main.py、lib.rs、main.rs 等)
  4. 检查是否有已有的 README(有则作为参考进行改写)

Step 2: 确定章节

根据项目规模选择章节:

小型项目(单文件/脚本)→ 精简版:

  • 项目简介、安装、使用方法

标准项目 → 完整版(默认):

  • 项目简介、安装指南、快速开始、配置说明、示例代码

大型项目(多模块/库)→ 扩展版:

  • 项目简介、目录、功能特性、安装指南、快速开始、配置说明、示例代码、项目结构、API 参考

当文档超过 150 行时,在项目简介后添加「目录」章节。

Step 3: 生成 README

使用下方模板,参考 templates.md 获取完整模板。

核心规则

  1. 语言:全部使用中文,技术术语保留英文(如 API、CLI、Docker)
  2. 代码块:标注语言(python、rust、bash、toml 等)
  3. 命令示例:同时给出注释说明
  4. 表格:用于对比信息、参数列表、环境变量等结构化数据
  5. 不加徽章:除非用户明确要求

行文风格

  • 简洁直接,不要废话
  • 用「你」称呼读者
  • 步骤编号用阿拉伯数字
  • 重要提示用 > 引用块或 **粗体**

Step 4: 检查

生成后逐项检查:

  • 所有代码块都能正确运行
  • 安装命令与实际依赖文件一致
  • 没有占位符文本(<your-xxx> 等需提醒用户修改)
  • 目录链接正确(如有)
  • Markdown 语法正确,无渲染问题

语言特定指南

Python 项目

安装章节优先使用以下方式(按优先级排序):

# 1. uv(推荐)
uv pip install <package>

# 2. pip
pip install <package>

# 3. 从源码安装
git clone <repo>
cd <project>
pip install -e .

虚拟环境建议:

# uv
uv venv && source .venv/bin/activate

# 标准方式
python -m venv .venv && source .venv/bin/activate

Rust 项目

安装章节标准格式:

# 作为依赖添加
cargo add <crate-name>

# 从源码构建
git clone <repo>
cd <project>
cargo build --release

运行示例:

cargo run --example <example-name>

额外资源

  • 完整模板和章节示例,参见 templates.md

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.