← 返回 Skills 市场
lnguyen1996

README Writer

作者 Lnguyen1996 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
106
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install auto-readme
功能描述
Generate a complete, production-quality README.md from code, description, or an existing README, tailored to the project type without any filler content.
使用说明 (SKILL.md)

readme-writer

Description

Generate a production-quality README.md from code, a short description, or an existing bad README. Adapts structure to the project type: library, CLI tool, web app, API, or data pipeline. No filler, no fluff — just the README a maintainer would actually want.

Use when

  • "write a README for this"
  • "my README is bad, rewrite it"
  • "generate docs for this project"
  • "I need a README"
  • Any project without a README, or with a placeholder/skeleton README

Input

Provide one or more of:

  • The project's source code (or key files)
  • A short description of what it does
  • The existing README (if rewriting)

Optionally specify:

  • Project type: library / CLI / web app / REST API / data pipeline / other
  • Primary language/framework
  • Target audience: end users / developers / both
  • License
  • Whether to include badges (CI, npm, PyPI, NuGet, etc.)

Output format

Outputs a complete, ready-to-paste README.md in this structure (sections omitted if not applicable):

# [Project Name]

[One-line description — what it is and what it does]

[Badges if requested: CI status, version, license, downloads]

## Features
[3–6 bullet points — concrete capabilities, not marketing copy]

## Quick Start
[Minimal working example — copy-paste runnable in under 60 seconds]

## Installation
[Package manager commands for all relevant platforms]

## Usage
[The most common use cases with code examples]

## API Reference
[For libraries: key classes, functions, parameters, return types]
[For CLIs: flags, subcommands, environment variables]

## Configuration
[Environment variables, config file format, defaults]

## Examples
[1–3 real-world examples beyond quick start]

## Contributing
[How to run locally, run tests, submit PRs]

## License
[License name and link]

Writing rules

  • First line after the title: one sentence, no jargon, a 10-year-old could understand
  • Quick Start must be runnable — no "replace with your actual values" placeholders unless unavoidable
  • API Reference uses the actual function/class names from the code
  • No phrases: "seamlessly", "powerful", "robust", "leveraging", "game-changer", "easy to use"
  • If something requires setup steps, number them — don't paragraph it
  • Code blocks have language tags (python, bash, ```json)
  • Never write "TODO" or leave blank sections — omit sections that don't apply

Project type adaptations

Library

Include: Features, Installation, Quick Start, API Reference, Examples, Contributing Skip: Deployment, Environment Variables (unless it's config)

CLI tool

Include: Installation, Usage (with all flags), Examples, Configuration Skip: API Reference

Web app / SaaS

Include: Features, Quick Start (local dev), Installation, Configuration (env vars), Deployment, Contributing Skip: API Reference (unless it exposes one)

REST API

Include: Base URL, Authentication, Endpoints (method, path, params, response), Examples Format: Use code blocks showing curl or example request/response JSON

Data pipeline

Include: What data flows in / out, How to run, Configuration, Output format Skip: Contributing (unless open source)

Self-improvement instructions

After each README generated, note what information was missing from the input that required assumptions. After 20 READMEs, surface the top 3 things developers forget to include.

安全使用建议
This skill appears to do what it says (produce high-quality README.md files) and doesn't request any credentials or installs — that's good. Before installing or using it: (1) Ask the publisher how the 'Self-improvement' tracking is implemented: where are per-README records stored, who can read them, and can you opt out? (2) Never feed repositories that contain secrets (API keys, private certs, credentials) — the skill's rule to use function/class names could cause accidental inclusion of sensitive strings in outputs. (3) If you want no persistent tracking, confirm the skill uses only in-session memory and does not write logs or analytics to external services. (4) Test with a non-sensitive sample project to validate output formatting and that no unexpected data is exfiltrated. If the publisher cannot explain how they implement the 20-README aggregation, consider this a red flag.
功能分析
Type: OpenClaw Skill Name: auto-readme Version: 1.0.0 The skill is a documentation generator designed to produce structured README.md files based on project source code or descriptions. It contains no executable code, network requests, or instructions to access sensitive system data, and its logic is entirely focused on formatting and content generation (SKILL.md).
能力评估
Purpose & Capability
Name, description, and declared requirements align: this is an instruction-only skill that generates README.md content from provided code or descriptions. It does not request extraneous binaries, environment variables, or credentials, which is appropriate for the stated purpose.
Instruction Scope
SKILL.md stays focused on README generation and outlines precise formatting rules and project-type adaptations. However, the 'Self-improvement instructions' ask the skill to record what was missing after each README and to 'after 20 READMEs, surface the top 3 things developers forget' — that requires accumulating state across runs. The skill provides no mechanism (install, storage path, environment, or external endpoint) for persistent tracking.
Install Mechanism
There is no install spec and no code files — lowest-risk delivery model. Nothing will be written to disk by the skill itself as described.
Credentials
The skill declares no environment variables, credentials, or config paths, which is proportionate to its stated function. Note: because it asks the agent to use actual function/class names from supplied code, giving the agent repository files may expose secrets embedded in code; the SKILL.md does not warn about excluding sensitive files.
Persistence & Privilege
Autonomous invocation is allowed (default) which is normal, but the self-improvement feature implies the skill will persist usage/metadata across sessions. Yet the skill doesn't declare how or where it will store that data (no install, no config path, no env). This mismatch could mean reliance on the host agent's memory/persistence features — clarify whether data will be stored and where, and whether it is shared or private.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install auto-readme
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /auto-readme 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release—auto-generates high-quality README.md files tailored to project type. - Writes production-ready READMEs from code, description, or an existing README. - Adapts sections for libraries, CLIs, web apps, APIs, and data pipelines. - Enforces clear, concise writing with concrete usage examples and coding standards. - Omits irrelevant sections and marketing jargon; focuses on maintainers’ real needs. - Supports configuration for project type, audience, language/framework, license, and badges.
元数据
Slug auto-readme
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

README Writer 是什么?

Generate a complete, production-quality README.md from code, description, or an existing README, tailored to the project type without any filler content. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 106 次。

如何安装 README Writer?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install auto-readme」即可一键安装,无需额外配置。

README Writer 是免费的吗?

是的,README Writer 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

README Writer 支持哪些平台?

README Writer 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 README Writer?

由 Lnguyen1996(@lnguyen1996)开发并维护,当前版本 v1.0.0。

💬 留言讨论