Token导航 LogoToken导航TokenDH.com
研究检索敏感数据github未标认证来源可访问许可证需确认审计通过

readme-creatorREADME creator 控制

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

2,952

周安装

123

GitHub Stars

33

下载量

984
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:readme-creator(README creator 控制)
来源仓库:https://github.com/mblode/agent-skills
仓库路径:skills/readme-creator
安装命令:
npx skills add https://github.com/mblode/agent-skills --skill readme-creator
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/mblode/agent-skills --skill readme-creator

简介

用于辅助文档、README、Markdown、说明文和内容稿件的整理与改写。

  • 适合提炼结构、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。
  • 可结合原始 README 和仓库路径进一步核验具体用法和功能边界。

SKILL.md

README Creator

Write or rewrite a README.md tailored to the project type and audience.

Reference Files

FileRead When
references/section-templates.mdPhase 3: choosing structure and writing sections for a specific project type
references/quality-checklist.mdPhase 5: validating the finished README against quality standards
references/badges-and-shields.mdPhase 4: adding badges after the main content is written

README Workflow

Copy this checklist to track progress:

README progress:
- [ ] Phase 1: Discover project context
- [ ] Phase 2: Choose README structure
- [ ] Phase 3: Write sections
- [ ] Phase 4: Add badges and extras
- [ ] Phase 5: Validate quality

Phase 1: Discover project context

Read the project before asking questions. Explore files to detect the project type:

  • Read package.json, Cargo.toml, pyproject.toml, go.mod, or equivalent for name, description, license, dependencies, scripts, and bin field.
  • Read existing README.md (if rewriting).
  • Scan directory structure to understand architecture.

Classify into one of six project types:

TypeSignals
CLI toolbin field in package.json, src/cli.ts, commander/yargs dependency
Library / packagemain/exports in package.json, no bin field, src/index.ts
Web appnext.config.ts, vite.config.ts, framework dependency, no npm publish
FrameworkPlugin/middleware architecture, configuration API, extensibility points
Monorepoturbo.json, pnpm-workspace.yaml, apps/ + packages/ directories
Skill bundleskills/ directory with SKILL.md files

Ask the user only for what cannot be discovered from the code:

  • What problem does the project solve? (the "why")
  • Who is the target audience?
  • Any sections to include or exclude?

Phase 2: Choose README structure

Load references/section-templates.md.

Select sections based on the project type:

SectionCLILibraryAppFrameworkMonorepoSkills
Title + one-lineryesyesyesyesyesyes
Badgesyesyes--yesyes--
Features / highlightsyesyesyesyes--yes
Installyesyes--yesyes--
Quick start / usageyesyesyesyesyesyes
Options / API referenceyesyes--yes----
Configurationoptoptyesyesopt--
Environment variables----yes------
Packages table--------yes--
Skills table----------yes
Requirementsyesyesoptyesopt--
Contributingoptoptoptoptoptopt
Licenseyesyesyesyesyesopt

Phase 3: Write sections

Load references/section-templates.md. Write each section following the template for the detected project type.

Key principles:

  • Title is the project name. One-liner directly below, no heading.
  • Feature list above the fold (before Install) so readers see value before effort.
  • Install: single fastest path first. npm install -g for CLIs, npm install for libraries.
  • Usage: 3-5 runnable examples, simplest first. Real values, not foo or example.
  • Every code block must be copy-pasteable and runnable without modification.
  • A reader should be able to install and run something within 60 seconds.
  • Progressive disclosure: basic first, advanced later or in linked docs.

Phase 4: Add badges and extras

Load references/badges-and-shields.md. Add badges only if the project is published to a registry. Place directly below the title and one-liner. Maximum 4 badges.

Skip badges entirely for private apps, unpublished projects, and skill bundles.

Phase 5: Validate quality

Load references/quality-checklist.md. Run through every applicable check. Fix issues before finalizing.

After fixes, reread the README top to bottom to confirm it flows naturally.

Anti-patterns

  • Do not write a README longer than the codebase warrants
  • Do not include a table of contents for READMEs under 100 lines
  • Do not use "About" or "Introduction" as the first heading
  • Do not ship the default create-next-app or create-vite README
  • Do not include badges for unpublished projects
  • Do not include a "Features" section that restates the one-liner
  • Do not write "This project is..." or "This is a..." — describe what it does directly
  • Do not include empty Contributing or Acknowledgements sections
  • Do not use foo, bar, or test as example values

Skill Handoffs

WhenRun
After README is written, audit prose qualitydocs-writing
If project needs AGENTS.md / CLAUDE.mdagents-md

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

33.7%
按下载量换算332

Claude

30.02%
按下载量换算295

Cursor

17.98%
按下载量换算177

Gemini CLI

8.31%
按下载量换算82

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

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。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