web-search

网络搜索与网页内容获取。当用户需要搜索互联网信息、获取网页内容、查找实时数据、进行 websearch 时使用此技能。支持多种搜索工具:WebFetch、Firecrawl skill、Tavily skill。

33 stars

Best use case

web-search is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

网络搜索与网页内容获取。当用户需要搜索互联网信息、获取网页内容、查找实时数据、进行 websearch 时使用此技能。支持多种搜索工具:WebFetch、Firecrawl skill、Tavily skill。

Teams using web-search should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/web-search/SKILL.md --create-dirs "https://raw.githubusercontent.com/aAAaqwq/AGI-Super-Team/main/skills/web-search/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/web-search/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How web-search Compares

Feature / Agentweb-searchStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

网络搜索与网页内容获取。当用户需要搜索互联网信息、获取网页内容、查找实时数据、进行 websearch 时使用此技能。支持多种搜索工具:WebFetch、Firecrawl skill、Tavily skill。

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# 网络搜索与网页内容获取

## 功能说明
此技能提供全面的网络搜索和网页内容获取能力。

## 可用工具

### 1. WebFetch (OpenClaw 内置)
- **功能**: 获取网页内容
- **使用场景**: 获取特定网页的内容

### 2. Tavily Skill (AI 优化搜索)
- **位置**: `~/clawd/skills/tavily/`
- **功能**: AI 优化的网络搜索
- **命令**: `~/clawd/skills/tavily/scripts/tavily.sh`

#### Tavily 用法
```bash
# 基础搜索
~/clawd/skills/tavily/scripts/tavily.sh search <query> [max_results]

# 深度搜索
~/clawd/skills/tavily/scripts/tavily.sh search <query> --deep

# 搜索并提取
~/clawd/skills/tavily/scripts/tavily.sh extract <query> [max_results]
```

### 3. Firecrawl Skill (专业抓取)
- **位置**: `~/clawd/skills/firecrawl/`
- **功能**: 专业网页抓取和数据提取
- **命令**: `~/clawd/skills/firecrawl/scripts/firecrawl.sh`

#### Firecrawl 用法
```bash
# 抓取单个网页
~/clawd/skills/firecrawl/scripts/firecrawl.sh scrape <url> [format]

# 搜索并抓取
~/clawd/skills/firecrawl/scripts/firecrawl.sh search <query> [limit]

# 批量爬取
~/clawd/skills/firecrawl/scripts/firecrawl.sh crawl <url> [max_pages]
```

## 使用场景

### 何时使用 Tavily
- 搜索互联网信息
- 获取实时数据
- 需要 AI 优化的搜索结果

### 何时使用 WebFetch
- 简单获取网页内容
- 快速查看页面信息

### 何时使用 Firecrawl
- 复杂网页抓取
- 结构化数据提取
- 批量网站爬取

## 示例

### 搜索 Polymarket 信息 (Tavily)
```bash
~/clawd/skills/tavily/scripts/tavily.sh search "Polymarket Fed decision March 2026" 5
```

### 抓取特定页面 (Firecrawl)
```bash
~/clawd/skills/firecrawl/scripts/firecrawl.sh scrape "https://polymarket.com/event/fed-decision-in-march-885"
```

# 网络搜索与网页内容获取

## 功能说明
此技能提供全面的网络搜索和网页内容获取能力,包括:
- 互联网搜索(新闻、信息、数据)
- 网页内容抓取和解析
- 实时数据查询
- 多源搜索结果整合

## 可用工具

### 1. OpenClaw 内置 WebSearch
- **功能**: 互联网搜索
- **使用场景**: 搜索新闻、信息、实时数据
- **触发**: 用户问需要实时信息的问题时

### 2. OpenClaw 内置 WebFetch
- **功能**: 获取网页内容
- **使用场景**: 获取特定网页的内容
- **触发**: 用户提供 URL 并要求获取内容时

### 3. Firecrawl MCP
- **功能**: 专业网页抓取和数据提取
- **工具**: mcp__firecrawl__scrape, mcp__firecrawl__crawl, mcp__firecrawl__search
- **使用场景**: 复杂网页抓取、结构化数据提取、批量爬取
- **优势**: 支持复杂网页、动态内容、结构化输出

## 使用场景

### 何时使用 WebSearch
- "搜索最新的 AI 新闻"
- "查找 Polymarket 最新赔率"
- "今天的天气怎么样"
- "某公司的最新股价"

### 何时使用 WebFetch
- "获取这个网页的内容"
- "读取这个 URL 的内容"
- "这个页面说了什么"

### 何时使用 Firecrawl MCP
- "抓取这个网站的所有产品信息"
- "从这个网页提取结构化数据"
- "爬取这个网站的多个页面"

## 工作流程

1. **分析需求**: 确定需要搜索还是抓取
2. **选择工具**:
   - 简单搜索 → WebSearch
   - 单页抓取 → WebFetch 或 mcp__firecrawl__scrape
   - 复杂抓取 → mcp__firecrawl__crawl
3. **执行操作**: 调用相应工具
4. **整合结果**: 将搜索结果整合到回答中

## 示例

### 搜索信息
```
用户: "搜索一下最新的 AI 新闻"
操作: 使用 WebSearch 搜索 "AI news latest"
```

### 获取网页内容
```
用户: "获取 https://example.com 的内容"
操作: 使用 WebFetch 或 mcp__firecrawl__scrape
```

### 结构化数据提取
```
用户: "从这个网页提取所有产品价格"
操作: 使用 mcp__firecrawl__scrape 并指定提取格式
```

## 注意事项

- 搜索结果可能包含过时或不准确的信息,需要验证
- 网页抓取需要遵守网站的 robots.txt 和使用条款
- 对于付费内容或需要登录的页面,可能无法直接获取
- 大量抓取可能触发反爬虫机制

Related Skills

tech-selection-research

33
from aAAaqwq/AGI-Super-Team

Use when the user wants to research, compare, or evaluate a technology, framework, platform, or engineering tool for product R&D decision-making, such as "调研 FastAPI", "技术选型", "compare Spring Boot vs NestJS", "写 ADR", "评估是否适合", "PoC 方案", or "technology radar".

skills-search

33
from aAAaqwq/AGI-Super-Team

Search skills.sh registry from CLI. Find and discover agent skills from the skills.sh ecosystem.

skill-search-optimizer

33
from aAAaqwq/AGI-Super-Team

Optimize agent skills for discoverability on ClawdHub/MoltHub. Use when improving search ranking, writing descriptions for semantic search, understanding how the registry indexes skills, testing search visibility, or analyzing why a skill isn't being found.

search-specialist

33
from aAAaqwq/AGI-Super-Team

Expert web researcher using advanced search techniques and synthesis. Masters search operators, result filtering, and multi-source verification. Handles competitive analysis and fact-checking. Use PROACTIVELY for deep research, information gathering, or trend analysis.

search-layer

33
from aAAaqwq/AGI-Super-Team

四源同级:Brave (`web_search`) + Exa + Tavily + Grok。按意图自动选策略、调权重、做合成。 DEFAULT search tool for ALL search/lookup needs. Multi-source search and deduplication layer with intent-aware scoring. Integrates Brave Search (web_search), Exa, Tavily, and Grok to provide high-coverage, high-quality results. Automatically classifies query intent and adjusts search strategy, scoring weights, and result synthesis. Use for ANY query that requires web search — factual lookups, research, news, comparisons, resource finding, "what is X", status checks, etc. Do NOT use raw web_search directly; always route through this skill.

search-first

33
from aAAaqwq/AGI-Super-Team

Research-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Invokes the researcher agent.

research-engineer

33
from aAAaqwq/AGI-Super-Team

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal impl...

orchestra-research-skills

33
from aAAaqwq/AGI-Super-Team

> 多源研究编排——聚合多个数据源进行深度研究

multi-search-engine

33
from aAAaqwq/AGI-Super-Team

> 多搜索引擎聚合查询——17 个搜索引擎一站式检索

Market Research

33
from aAAaqwq/AGI-Super-Team

Size markets, analyze competitors, and validate opportunities with practical frameworks and free data sources.

lead-research-assistant

33
from aAAaqwq/AGI-Super-Team

Identifies high-quality leads for your product or service by analyzing your business, searching for target companies, and providing actionable contact strategies. Perfect for sales, business development, and marketing professionals.

deep-research

33
from aAAaqwq/AGI-Super-Team

Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any topic with evidence and citations.