Token导航 LogoToken导航

Agent Skill · 研究检索

web-content(网页内容)

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。

web-content 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;许可证为 MIT,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 22,753。

总安装 4,468周安装 179GitHub Stars 588下载 1,446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
MIT

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:web-content(网页内容)
来源仓库:https://github.com/alinaqi/claude-bootstrap
仓库路径:skills/web-content
安装命令:
npx skills add https://github.com/alinaqi/claude-bootstrap --skill web-content
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/alinaqi/claude-bootstrap --skill web-content

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。

用于辅助文档、README、Markdown 等内容的整理与改写。适合提炼结构、补齐章节、统一术语或检查链接。使用时需保留项目事实,避免写成确定结论;对外文案应控制语气。通过 npx 命令从指定仓库安装,适用于主流 AI Agent 宿主。建议确认权限和维护状态,避免触发不必要的联网或文件操作。

来源仓库内路径:skills/web-content

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/alinaqi/claude-bootstrap --skill web-content;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

web-content 怎么安装?

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

web-content 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。

web-content 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。

web-content 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

web-content 用的人多吗?

公开数据是累计安装 4,468 次,近一周安装 179 次,下载 1,446 次,GitHub 588 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。

web-content 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

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。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 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。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 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
web-content

网页内容 · 本页

4,468588需要联网MIT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

Web Content Skill

For creating web content optimized for both traditional SEO and AI discovery (ChatGPT, Perplexity, Claude, Gemini).

Sources: GEO Complete Guide | AI Search SEO | LLM Optimization | Generative Engine Optimization


Philosophy

SEO gets clicks. GEO gets citations.

Traditional SEO optimizes for Google rankings. Generative Engine Optimization (GEO) optimizes for being cited by AI assistants. Modern content needs both:

  • SEO: Rank on search results pages
  • GEO: Be cited in AI-generated answers (ChatGPT, Perplexity, Claude, Gemini)

AI traffic grew 1,200% between July 2024 and February 2025. Google's search share dropped below 90% for the first time in a decade. Optimize for both.


Content Structure for AI + SEO

The Golden Rule

Write for humans, structure for machines.

AI systems prefer:

  • Short, clear, fact-based content
  • Clean formatting (headers, bullets, tables)
  • Standalone sections that can be quoted
  • Direct answers to questions

Page Types & Templates

Homepage

## Homepage Structure

### Above the Fold
- **Headline**: Clear value proposition (what you do + for whom)
- **Subheadline**: How you deliver that value
- **Primary CTA**: One clear action
- **Trust signals**: Logos, testimonials, stats

### Content Sections
1. **Problem Statement**: Pain point you solve
2. **Solution Overview**: How you solve it (3-4 key features)
3. **Social Proof**: Testimonials, case studies, logos
4. **How It Works**: 3-step process (simple)
5. **Pricing Preview**: Or link to pricing page
6. **FAQ Section**: 5-7 common questions (GEO gold)
7. **Final CTA**: Repeat primary action

### Schema Required
- Organization schema (name, logo, founding date, social links)
- WebSite schema with SearchAction
- FAQ schema for questions section

Product/Service Page

## Product Page Structure

### Hero Section
- **Product Name**: Clear, descriptive
- **One-line Description**: What it does in 10 words or less
- **Key Benefit**: Primary value proposition
- **CTA**: Buy/Try/Demo

### Content Sections
1. **TL;DR Box**: 3-5 bullet summary (AI-quotable)
2. **Problem → Solution**: What problem, how solved
3. **Features Grid**: 4-6 features with icons
4. **Comparison Table**: vs. alternatives (GEO loves these)
5. **Use Cases**: Who uses it and how
6. **Testimonials**: Real names, photos, companies
7. **Pricing**: Clear tiers if applicable
8. **FAQ**: Product-specific questions

### Schema Required
- Product schema (name, description, price, availability)
- Review schema (aggregate rating)
- FAQ schema
- BreadcrumbList schema

Blog Post / Article

## Blog Post Structure

### Opening (First 100 words)
- **TL;DR**: Direct answer to the title's question
- **What you'll learn**: Bullet list of takeaways
- This section should be quotable standalone

### Body Structure
- **H2 sections**: Main topics (5-7 per article)
- **H3 subsections**: Supporting points
- **Bullet lists**: For scanability
- **Stat boxes**: Highlight key numbers
- **Comparison tables**: When comparing options

### Content Elements
- Definition boxes ("What is X?")
- Step-by-step instructions
- Code examples (if technical)
- Original statistics/research
- Expert quotes with attribution

### Closing
- **Summary**: Key takeaways (bulleted)
- **Next steps**: What reader should do
- **Related content**: Internal links

### Metadata Required
- Author name + bio + photo
- Publication date
- Last updated date (visible!)
- Reading time
- Article schema with author

FAQ Page

## FAQ Page Structure

### Organization
- Group questions by category
- Most common questions first
- Direct, concise answers
- Link to detailed pages for more info

### Question Format
Q: [Exact question users ask]
A: [Direct answer in first sentence, then elaboration]

### Schema Required
- FAQPage schema (critical for AI discovery)
- Each Q&A as Question/Answer schema

Landing Page

## Landing Page Structure

### Single Focus
- One offer
- One audience
- One CTA (repeated)

### Sections
1. **Headline**: Benefit-focused, specific
2. **Problem Agitation**: Pain points
3. **Solution**: Your offer
4. **Proof**: Testimonials, stats, logos
5. **Features**: 3-5 key benefits
6. **Objection Handling**: FAQ or guarantee
7. **CTA**: Clear, urgent

### No Navigation
- Remove header nav (reduce exits)
- Single path: read → convert

AI-Optimized Content Formats

TL;DR Boxes

<div class="tldr-box">
  <h3>TL;DR</h3>
  <ul>
    <li>Key point 1 with specific detail</li>
    <li>Key point 2 with number/stat</li>
    <li>Key point 3 with actionable insight</li>
  </ul>
</div>

Place at top of articles. AI systems extract these for summaries.

Definition Blocks

## What is [Term]?

[Term] is [concise definition in one sentence]. It [what it does] by [how it works].

**Key characteristics:**
- Characteristic 1
- Characteristic 2
- Characteristic 3

Start with "What is X?" - AI systems look for this pattern.

Comparison Tables

| Feature | Product A | Product B | Our Product |
|---------|-----------|-----------|-------------|
| Price | $99/mo | $149/mo | $79/mo |
| Feature 1 | ✓ | ✗ | ✓ |
| Feature 2 | ✗ | ✓ | ✓ |
| Best For | Enterprise | Startups | SMBs |

AI loves structured comparisons. Include in product and review pages.

Stat Boxes

<div class="stat-box">
  <span class="stat-number">73%</span>
  <span class="stat-label">of users prefer AI search for complex queries</span>
  <span class="stat-source">Source: Adobe Analytics, 2024</span>
</div>

Original statistics with sources get cited by AI.

Step-by-Step Guides

## How to [Do Thing]

### Step 1: [Action Verb] [Object]
[Explanation of what to do]

**Example:**
[Concrete example]

### Step 2: [Action Verb] [Object]
[Explanation]

### Step 3: [Action Verb] [Object]
[Explanation]

**Result:** [What user achieves]

Use HowTo schema markup for these.


Schema Markup (Critical for AI)

Organization Schema

{
  "@context": "https://schema.org",
  "@type": "Organization",
  "name": "Your Company",
  "url": "https://yoursite.com",
  "logo": "https://yoursite.com/logo.png",
  "foundingDate": "2020",
  "description": "One sentence description",
  "sameAs": [
    "https://twitter.com/yourcompany",
    "https://linkedin.com/company/yourcompany",
    "https://github.com/yourcompany"
  ],
  "contactPoint": {
    "@type": "ContactPoint",
    "email": "hello@yoursite.com",
    "contactType": "customer service"
  }
}

Article Schema

{
  "@context": "https://schema.org",
  "@type": "Article",
  "headline": "Article Title",
  "description": "Meta description",
  "image": "https://yoursite.com/article-image.jpg",
  "author": {
    "@type": "Person",
    "name": "Author Name",
    "url": "https://yoursite.com/team/author-name",
    "jobTitle": "Role at Company",
    "sameAs": [
      "https://linkedin.com/in/author",
      "https://twitter.com/author"
    ]
  },
  "publisher": {
    "@type": "Organization",
    "name": "Your Company",
    "logo": {
      "@type": "ImageObject",
      "url": "https://yoursite.com/logo.png"
    }
  },
  "datePublished": "2025-01-15",
  "dateModified": "2025-01-20"
}

FAQ Schema

{
  "@context": "https://schema.org",
  "@type": "FAQPage",
  "mainEntity": [
    {
      "@type": "Question",
      "name": "What is your product?",
      "acceptedAnswer": {
        "@type": "Answer",
        "text": "Direct answer here. Keep concise but complete."
      }
    },
    {
      "@type": "Question",
      "name": "How much does it cost?",
      "acceptedAnswer": {
        "@type": "Answer",
        "text": "Pricing starts at $X/month for basic plan..."
      }
    }
  ]
}

Product Schema

{
  "@context": "https://schema.org",
  "@type": "Product",
  "name": "Product Name",
  "description": "Product description",
  "image": "https://yoursite.com/product.jpg",
  "brand": {
    "@type": "Brand",
    "name": "Your Company"
  },
  "offers": {
    "@type": "Offer",
    "price": "29.99",
    "priceCurrency": "USD",
    "availability": "https://schema.org/InStock"
  },
  "aggregateRating": {
    "@type": "AggregateRating",
    "ratingValue": "4.8",
    "reviewCount": "127"
  }
}

HowTo Schema

{
  "@context": "https://schema.org",
  "@type": "HowTo",
  "name": "How to Set Up Your Account",
  "description": "Step-by-step guide to getting started",
  "step": [
    {
      "@type": "HowToStep",
      "name": "Create account",
      "text": "Go to signup page and enter your email"
    },
    {
      "@type": "HowToStep",
      "name": "Verify email",
      "text": "Click the link in the verification email"
    }
  ]
}

Platform-Specific Optimization

ChatGPT Optimization

✅ DO:
- TL;DR sections at top of articles
- Consistent formatting (headers, bullets)
- Named authors with credentials
- Original research and statistics
- Multi-intent content (covers related questions)

❌ AVOID:
- Thin content without substance
- Missing author attribution
- Outdated information (no dates)

Perplexity Optimization

✅ DO:
- Original statistics with sources
- Comparison tables and structured data
- Clean URL slugs (/topic-name not /p=123)
- Short, declarative statements
- Images, charts, diagrams
- YouTube videos (Perplexity shows these)

❌ AVOID:
- Generic content without unique insights
- Missing citations/sources
- Poor URL structure

Claude Optimization

✅ DO:
- Well-structured, logical content
- Clear definitions and explanations
- Technical accuracy
- Balanced perspectives
- Proper citations

❌ AVOID:
- Misleading or sensational content
- Missing context
- Outdated technical information

Gemini Optimization

✅ DO:
- Rich schema markup
- Detailed image alt-text
- YouTube content (Google-owned)
- Multimedia (video, audio with transcripts)

❌ AVOID:
- Missing structured data
- Images without alt-text
- Text-only content

E-E-A-T for AI Discovery

Experience

  • First-person case studies
  • "We tested X and found Y"
  • Original screenshots and data
  • User testimonials with real details

Expertise

  • Author bios with credentials
  • Link to author's other work
  • Industry-specific terminology
  • Technical depth appropriate to topic

Authoritativeness

  • Backlinks from trusted sources
  • Mentions in industry publications
  • Citations from other experts
  • Social proof (followers, engagement)

Trustworthiness

  • Contact information visible
  • About page with team details
  • Privacy policy and terms
  • Secure site (HTTPS)
  • Accurate, up-to-date info

Content Freshness

Visible Dates (Required)

<article>
  <header>
    <h1>Article Title</h1>
    <div class="meta">
      <span class="author">By John Smith</span>
      <span class="published">Published: January 15, 2025</span>
      <span class="updated">Last updated: January 20, 2025</span>
    </div>
  </header>
</article>

AI systems prefer recent content. Show dates prominently.

Update Schedule

Content TypeUpdate Frequency
Product pagesOn feature changes
PricingImmediately on change
Blog postsQuarterly review
StatisticsWhen new data available
GuidesSemi-annually

Analytics for AI Traffic

GA4 Regex Filter

.*chatgpt\.com.*|.*perplexity\.ai.*|.*gemini\.google\.com.*|.*copilot\.microsoft\.com.*|.*openai\.com.*|.*claude\.ai.*|.*poe\.com.*|.*you\.com.*|.*phind\.com.*

Track AI Referrals

// Check for AI referrer
const aiReferrers = [
  'chatgpt.com',
  'chat.openai.com',
  'perplexity.ai',
  'claude.ai',
  'gemini.google.com',
  'copilot.microsoft.com',
  'poe.com',
  'you.com',
  'phind.com'
];

const referrer = document.referrer;
const isAIReferral = aiReferrers.some(ai => referrer.includes(ai));

if (isAIReferral) {
  analytics.track('ai_referral', {
    source: referrer,
    page: window.location.pathname
  });
}

Survey for AI Discovery

Add to forms:

How did you hear about us?
- [ ] Google Search
- [ ] ChatGPT
- [ ] Perplexity
- [ ] Claude
- [ ] Social Media
- [ ] Referral
- [ ] Other

Content Checklist

Before Publishing

## SEO Checklist
- [ ] Title tag (50-60 chars) with primary keyword
- [ ] Meta description (150-160 chars) with CTA
- [ ] URL slug is clean and descriptive
- [ ] H1 matches title intent
- [ ] H2/H3 hierarchy is logical
- [ ] Images have descriptive alt-text
- [ ] Internal links to related content
- [ ] External links to authoritative sources

## GEO Checklist
- [ ] TL;DR or summary at top
- [ ] Direct answer to main question in first paragraph
- [ ] Stat boxes with sources
- [ ] Comparison tables where applicable
- [ ] FAQ section with schema
- [ ] Author name, bio, and credentials
- [ ] Publication and last-updated dates visible
- [ ] Schema markup validated
- [ ] Content can be quoted standalone
- [ ] Original insights or data included

Schema Validation

# Validate schema markup
# Use: https://validator.schema.org/
# Or: https://search.google.com/test/rich-results

Project Structure

project/
├── content/
│   ├── pages/
│   │   ├── home.md
│   │   ├── about.md
│   │   ├── pricing.md
│   │   └── contact.md
│   ├── blog/
│   │   ├── post-1.md
│   │   └── post-2.md
│   └── legal/
│       ├── privacy.md
│       └── terms.md
├── components/
│   ├── SchemaMarkup.tsx
│   ├── TLDRBox.tsx
│   ├── StatBox.tsx
│   ├── FAQSection.tsx
│   └── AuthorBio.tsx
└── lib/
    └── schema.ts           # Schema generators

Anti-Patterns

  • No dates - AI deprioritizes undated content
  • Anonymous content - No author = no E-E-A-T
  • Walls of text - Break up with headers, bullets, boxes
  • Generic content - Add original insights, data, opinions
  • Missing schema - Invisible to structured data crawlers
  • Outdated info - Update quarterly minimum
  • No FAQ - Missing easy GEO win
  • Poor URL structure - Use /topic-name not /p=12345

Quick Reference

Content Formats AI Loves

  1. TL;DR summaries
  2. Definition boxes ("What is X?")
  3. Comparison tables
  4. Step-by-step guides
  5. FAQ sections
  6. Stat boxes with sources
  7. Listicles with numbers

Required Schema by Page Type

Page TypeSchema
HomepageOrganization, WebSite
Blog PostArticle, Author, FAQ
ProductProduct, Review, FAQ
FAQFAQPage
How-toHowTo
AboutOrganization, Person

平台分布

Claude Code

30%
按下载量换算434

OpenCode

24.24%
按下载量换算351

Antigravity

18.32%
按下载量换算265

Gemini CLI

13.89%
按下载量换算201

Cursor

7.67%
按下载量换算111

Codex

3.35%
按下载量换算48

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。

继续浏览同类 Skills