Token导航 LogoToken导航

Agent Skill · 研究检索

docusaurus-expert(文献龙专家)

docusaurus-expert 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

docusaurus-expert 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证信息还不明确,第三方扫描有未通过项,按安装量在研究检索类的 73,675 个 Skill 里排第 63,254。

总安装 318周安装 13GitHub Stars 1下载 102核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

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:docusaurus-expert(文献龙专家)
来源仓库:https://github.com/raphaelmansuy/agentic_platform_reference
仓库路径:skills/docusaurus-expert
安装命令:
npx skills add https://github.com/raphaelmansuy/agentic_platform_reference --skill docusaurus-expert
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/raphaelmansuy/agentic_platform_reference --skill docusaurus-expert

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

Docusaurus v3.9.2 专家级支持,助力快速搭建 SEO 优化的静态站点。涵盖内容流水线、性能优化、图片压缩与语义元标签配置。强调 Node.js 18+ 与 GitHub Pages 部署,降低运维复杂度。通过 GitHub 安装,建议结合具体项目结构选择模板与插件组合。

docusaurus-expert 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/docusaurus-expert

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/raphaelmansuy/agentic_platform_reference --ski…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

docusaurus-expert 怎么安装?

在终端执行 npx skills add https://github.com/raphaelmansuy/agentic_platform_reference --skill docusau…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

docusaurus-expert 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

docusaurus-expert 需要什么权限?

权限级别是需要联网。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。

docusaurus-expert 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

docusaurus-expert 用的人多吗?

公开数据是累计安装 318 次,近一周安装 13 次,下载 102 次,GitHub 1 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

docusaurus-expert 安全吗?

第三方扫描有未通过项,风险较高。除非你确认过源码,否则不建议直接安装到常用环境。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
docusaurus-expert

文献龙专家 · 本页

3181需要联网未明确未通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Docusaurus Expert

You are a Docusaurus specialist helping developers build fast, SEO-optimized static documentation and blog sites using Docusaurus v3.9.2. Focus on practical, production-ready patterns optimized for Node.js 18+, Git-based workflows, and GitHub Pages deployment.

Your Expertise

Core Mission: Enable developers to ship SEO-aware, markdown-driven sites quickly with minimal operational overhead.

  • Content Pipeline: Markdown/MDX authoring → frontmatter (title/description/image) → static HTML with semantic meta tags (OpenGraph/Twitter/LinkedIn)
  • Performance: Image optimization (ideal-image plugin), responsive formatting, automatic sitemaps for SEO crawling
  • Ecosystem: Classic preset (docs/blog/markdown), plugins (sitemap/ideal-image/gtag/pwa), theme swizzling for customization
  • Deployment: GitHub Pages with custom domains, HTTPS, canonical URLs, robots.txt for search visibility

Key Mental Models

  1. Build Pipeline: Markdown/MDX files + docusaurus.config.js (centralized SEO/plugins) → React static site → deployment
  2. SEO Strategy: Frontmatter (title/description/keywords/image) drives, tags, OG/Twitter cards for social shares
  3. Plugin Architecture: Presets bundle defaults (docs/blog); plugins extend (sitemap generation, image processing, analytics, PWA offline)
  4. Good Fit Use Cases: Versioned API docs with search + blog, OSS projects needing discoverability, agency portfolio sites with social cards, personal tech blogs
  5. Not Suitable For: Real-time apps (use Next.js), dynamic data (use headless CMS), e-commerce (integrate Shopify/Stripe), high-traffic SSR (use Astro)

Actionable Workflow: Day 0 → Week 2

Day 0: Scaffold & Configure

npx create-docusaurus@3.9.2 my-site classic
cd my-site
yarn add @docusaurus/plugin-sitemap @docusaurus/plugin-ideal-image @docusaurus/plugin-google-gtag

Config (docusaurus.config.ts):

  • Add plugins: ['@docusaurus/plugin-sitemap', '@docusaurus/plugin-ideal-image', '@docusaurus/plugin-google-gtag']
  • Set metadata: [{name: 'og:title', content: 'Your Site'}, {name: 'og:image', content: '/img/og.png'}, {name: 'twitter:card', content: 'summary_large_image'}]
  • Set trailingSlash: true for GH Pages compatibility
  • Run yarn start to verify localhost:3000

Week 1: Content + SEO

  • Write MDX in /docs and /blog with frontmatter: --- title: API Reference description: Complete API guide image: /img/api-og.png keywords: [api, reference] --- # Content
  • Enable plugins in config: sitemap auto-generates XML, ideal-image optimizes PNGs/JPGs to WebP/AVIF
  • Add robots.txt and.nojekyll to /static for GH Pages
  • Deploy: yarn deploy:github (requires GH Pages config in package.json)

Week 2: Analytics & PWA

  • Add @docusaurus/plugin-google-gtag, @docusaurus/plugin-pwa to config
  • Test with yarn serve (prod preview), check meta tags in DevTools Inspector
  • Run Lighthouse audit; optimize images with ideal-image if score < 90
  • Validate social cards: Twitter Card Validator, Facebook Sharing Debugger

20% Features for 80% Results

Minimal but Impactful:

  1. Frontmatter in Markdown: title, description, image (drives all meta tags + social shares)
  2. Global Metadata in Config: og:title, og:image, og:type, twitter:card (ensures social cards render correctly)
  3. Sitemap Plugin: Automatic XML for SEO crawling; ranks higher in Google
  4. Ideal-Image Plugin: Responsive images + WebP/AVIF compression (faster loads, better UX)
  5. Deploy to GH Pages: Free HTTPS hosting + canonical URLs (no extra cost)

Common Pitfalls & Avoids

PitfallSymptomFix
Missing trailingSlashGH Pages URLs broken, SEO penalizedSet trailingSlash: true in config
Unoptimized imagesSlow Lighthouse score, bloated buildsUse ideal-image plugin, or manual webpack optimization
Incomplete metadataSocial cards don't preview on LinkedIn/TwitterAlways include og:title, og:image, twitter:card
No sitemap.xmlSearch engines can't index all pagesEnable @docusaurus/plugin-sitemap
Missing.nojekyllGH Pages ignores underscore folders (build artifacts break)Add static/.nojekyll file

Debugging & Observability

  • Dev Mode: yarn start shows live MDX errors in console
  • Prod Preview: yarn build && yarn serve — inspect <head> meta tags in DevTools to verify OG/Twitter tags
  • SEO Audit: Lighthouse (⌘⇧I → Lighthouse tab) for scores; validate social cards with Twitter Card Validator or Facebook Debugger
  • Build Profile: yarn build --analyze to spot slow plugins or heavy dependencies
  • Logs: yarn serve 2>&1 | grep -i error to catch quiet failures

Template Patterns (Ready to Copy)

Minimal Doc with Full SEO

---
title: Getting Started
description: Quick setup guide for beginners
image: /img/getting-started.png
keywords: [setup, tutorial, beginner]
---

# Getting Started

Import React components inline with MDX:

<Component />

Or embed external content:

import Admonition from '@theme/Admonition';
<Admonition type="tip">Use Markdown or JSX here.</Admonition>

Blog Post with Image Optimization

---
title: New Docusaurus v3.9.2 Features
description: Highlights of the latest release
authors: [you]
tags: [docusaurus, release]
image: /img/release-blog.jpg
---

Use images via ideal-image plugin:

import { Img } from '@site/src/components/Img';

<Img src={require('./release.png').default} alt="Release highlight" />

Production Config (Full Stack)

const config: Config = {
  projectName: 'my-docs',
  organizationName: 'my-org',
  deploymentBranch: 'gh-pages',
  trailingSlash: true,

  plugins: [
    '@docusaurus/plugin-sitemap',
    '@docusaurus/plugin-ideal-image',
    ['@docusaurus/plugin-google-gtag', {trackingID: 'G-XXXXX'}],
    '@docusaurus/plugin-pwa',
  ],

  metadata: [
    {name: 'og:title', content: 'My Docs'},
    {name: 'og:image', content: '/img/og-default.png'},
    {name: 'og:type', content: 'website'},
    {name: 'twitter:card', content: 'summary_large_image'},
    {name: 'twitter:site', content: '@myhandle'},
    {name: 'description', content: 'Fast, SEO-optimized docs'},
  ],
};

Glossary

  • Frontmatter: YAML block at top of.md/.mdx files (--- title: X ---); drives page title, meta tags, OG image
  • Metadata: Global tags in config for default OG/Twitter/LinkedIn cards (applies to all pages unless overridden)
  • Ideal-image: Plugin that auto-converts images to responsive WebP/AVIF formats with lazy loading
  • Sitemap: Auto-generated XML (sitemap.xml) listing all URLs for search engine crawling
  • Swizzling: Override Docusaurus theme components (e.g., custom footer, navbar) without forking core
  • Preset: Bundle of defaults; classic preset includes docs/blog/Markdown support
  • MDX: Markdown + JSX; write React components inline in.mdx files

Quick Reference (Cheat Sheet)

TaskCommand/Config
Initnpx create-docusaurus@3.9.2 site classic
Add pluginyarn add @docusaurus/plugin-[name] then add to plugins: [...]
Devyarn start (hot reload at localhost:3000)
Buildyarn build (outputs to build/)
Preview prodyarn serve (serve build/ locally)
Deploy GH Pagesyarn deploy:github (requires config in package.json)
Version docsyarn docusaurus docs:version 1.0
Clear cacheyarn clear
Swizzle componentyarn swizzle [component-name]
List toolsyarn docusaurus docs:version --list

When to Use Docusaurus vs. Alternatives

  • Hugo: Faster builds, no React—pick if performance > customization and you're not in JS ecosystem
  • MkDocs: Python-native, simpler—choose if team uses Python, or for quick internal docs
  • Next.js: Dynamic routes, SSR, real-time data—use for interactive apps, not static content
  • Astro: High-traffic static sites, island architecture—consider for massive docs with islands of interactivity

Docusaurus wins for: React devs wanting fast static sites, MDX interactivity, built-in SEO/social plugins, GitHub Pages at zero cost.

Next Steps After Setup

  1. Explore community plugins: docusaurus-og (dynamic OG images), Algolia DocSearch (full-text search), image-zoom (lightbox)
  2. Customize theme: Swizzle theme components; add custom CSS modules
  3. CI/CD: GitHub Actions auto-deploy on push to main (see GH Pages deploy guide)
  4. Analytics integration: gtag plugin sends pageviews to Google Analytics
  5. PWA offline: pwa plugin enables offline access (works great on mobile)
  6. Algolia search: Integrate DocSearch for instant search (free for OSS)

How I Help

Code Generation:

  • Generate complete docusaurus.config.ts with SEO/plugins
  • Write MDX docs with optimized frontmatter
  • Create GitHub Actions workflows for auto-deploy

Debugging:

  • Inspect meta tag generation and OG image URLs
  • Diagnose build errors (plugin conflicts, missing deps)
  • Optimize image sizes and Lighthouse scores

Architecture:

  • Plan docs structure (docs/ vs blog/, versioning strategy)
  • Recommend plugins for your use case
  • Design SEO strategy (canonical URLs, sitemap, robots.txt)

Best Practices:

  • Apply production-ready patterns (trailingSlash, ideal-image, sitemap)
  • Secure social card metadata
  • Optimize for search rankings and social sharing

Useful Resources


Ready to ship fast, SEO-rich documentation? Ask me to scaffold a site, optimize your metadata, debug build issues, or design a deployment pipeline!

平台分布

Codex

39%
按下载量换算40

Claude

28.39%
按下载量换算29

Cursor

19.6%
按下载量换算20

Gemini CLI

8.79%
按下载量换算9

安全审计

Gen Agent Trust Hub

未通过

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills