Token导航 LogoToken导航TokenDH.com
开发需要联网github未标认证来源可访问clear审计通过

writing-documentation编写文档

Agent Skill

用于辅助文档、README、Markdown、说明文和内容稿件的整理与改写。它适合让 Agent 提炼结构、补齐章节、统一术语、检查链接或把零散材料整理成可读文档。使用时应保留项目已有事实、命令和路径,不要把未确认的信息写成确定结论;涉及对外文案时,还需要控制语气,避免过度营销或夸大能力。

总安装

950

周安装

40

GitHub Stars

35

下载量

333
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

3

许可证

MIT

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:writing-documentation(编写文档)
来源仓库:https://github.com/ratacat/claude-skills
仓库路径:skills/writing-documentation
安装命令:
npx skills add https://github.com/ratacat/claude-skills --skill writing-documentation
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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/ratacat/claude-skills --skill writing-documentation

简介

writing-documentation 用于辅助文档、README、Markdown 和内容稿件的整理与改写。

  • 适合让 Agent 提炼结构、补齐章节、统一术语或检查链接,提升文档可读性。
  • 使用时应保留项目已有事实和路径,避免将未确认信息写成确定结论。
  • 安装前需确认权限范围和维护状态,注意是否触发联网、命令执行或文件读写操作。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Writing Documentation Skill

Apply Strunk & White's *Elements of Style* principles to produce concise, clear technical documentation.

When to Use This Skill

Use this skill when:

  • Writing new documentation (README, API docs, guides, tutorials, architecture docs)
  • Improving existing documentation
  • Reviewing documentation for quality
  • User asks to "make this more concise" or "improve clarity"
  • User mentions: documentation, docs, README, guide, tutorial, API docs

Do NOT use this skill for:

  • Code comments (different context, separate skill needed)
  • Marketing copy (requires persuasive voice, not neutral clarity)
  • Personal blog posts (requires individual voice)

Workflows

Workflow 1: Write New Documentation

Steps:

  1. Understand the purpose

- What is the primary goal of this documentation? - Who is the target audience? - What do readers need to accomplish after reading?

  1. Load writing principles

- Read reference/strunk-white-principles.md to internalize core principles

  1. Determine documentation type

- Read reference/doc-types.md to select appropriate type - Identify essential sections based on guidelines

  1. Draft the documentation

- Apply Strunk & White principles while writing

  1. Validate quality

- Run through Quality Checklist (below) - Verify all essential information is present - Confirm document achieves its purpose

Workflow 2: Improve Existing Documentation

Steps:

  1. Read the current documentation

- Understand its purpose and audience - Note specific problems (verbosity, unclear sections, missing info)

  1. Load writing principles

- Read reference/strunk-white-principles.md - Review reference/examples.md for before/after patterns

  1. Apply improvements

- Remove needless words - Convert passive to active voice - Strengthen vague statements - Eliminate redundancy - Improve organization if needed

  1. Validate improvements

- Run through Quality Checklist - Verify no information was lost - Confirm clarity improved

Workflow 3: Review Documentation

Steps:

  1. Load writing principles

- Read reference/strunk-white-principles.md - Review relevant guidelines in reference/doc-types.md

  1. Assess against quality criteria

- Run through Quality Checklist (below) - Note specific violations with examples

  1. Provide feedback

- List specific issues found - Reference violated principles - Suggest concrete improvements

Decision Framework

When to Write vs Improve

Write new documentation when:

  • No documentation exists
  • Existing documentation is fundamentally wrong or outdated
  • Complete restructuring needed (cheaper to rewrite)

Improve existing documentation when:

  • Core structure and information are sound
  • Style or clarity issues can be fixed incrementally
  • Specific sections need enhancement

Choosing Documentation Type

See reference/doc-types.md for detailed guidelines. Quick reference:

  • README: Project overview, quick start, primary entry point
  • API Documentation: Reference for function/endpoint signatures and behavior
  • Tutorial/Guide: Step-by-step learning path for accomplishing specific goals
  • Architecture/Design Doc: Explain system structure, decisions, and tradeoffs
  • CLI Tool Documentation: Command reference with options and examples

Prioritizing Conciseness vs Comprehensiveness

Prioritize conciseness when:

  • Documentation type is reference (README, API docs, CLI docs)
  • Readers need to scan quickly
  • Getting started / quick start sections

Prioritize comprehensiveness when:

  • Documentation type is learning-focused (tutorials, guides)
  • Complex concepts require detailed explanation
  • Architecture decisions need thorough justification

Balance both:

  • Use concise overview sections with detailed subsections
  • Link to comprehensive resources rather than embedding everything
  • Apply progressive disclosure pattern

Quality Checklist

Content

  • Purpose is clear
  • Essential information is present
  • No unnecessary information
  • Correct and accurate

Writing (Core Principles)

  • Active voice predominates
  • Definite statements (not hedging)
  • Positive form
  • Specific, concrete language
  • Concise (no needless words)

Structure

  • Logical organization
  • Clear headings
  • Scannable
  • Examples where helpful

Technical Documentation

  • Code examples are executable
  • Commands include full context
  • Prerequisites are stated
  • Error cases are covered

Reference Files

When to Load Each Reference

Load reference/strunk-white-principles.md:

  • At the start of EVERY documentation writing/improvement task
  • When reviewing documentation

Load reference/doc-types.md:

  • When choosing what type of documentation to write
  • When unsure about essential sections for a doc type
  • When reviewing documentation structure

Load reference/examples.md:

  • When improving existing documentation (see patterns)
  • When you want concrete before/after examples

Common Pitfalls

Skipping Principle Loading: ALWAYS load reference/strunk-white-principles.md before writing.

Following Guidelines Rigidly: Adapt to the specific project's needs. Some projects don't need all sections; some need additional ones.

Over-Editing: "Omit needless words" means remove words that add no value. Keep all information that serves the reader's purpose.

Sacrificing Accuracy for Brevity: Accuracy always wins. Express explanations concisely, but never misleadingly.

Inconsistent Terminology: Choose one term for each concept and use it consistently.

Notes

  • This skill works iteratively - you can run it multiple times on the same document without degrading quality (idempotent)
  • Quality over quantity - a short, clear document is better than a comprehensive, confusing one

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

04

需要参考平台分布和安装热度时

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

补充不同宿主或平台的使用分布数据

能力 5

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

Claude Code

29.48%
按下载量换算98

Antigravity

25.39%
按下载量换算85

Gemini CLI

18.52%
按下载量换算62

Codex

13.89%
按下载量换算46

trae

7.41%
按下载量换算25

windsurf

3.26%
按下载量换算11

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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。

来源信息

继续浏览同类 Skills