Skip to content
Agentmart
Submit a tool

search

网络搜索统一入口 - 整合通用搜索、学术搜索、多引擎搜索和 AI 搜索的全流程支持

Skill by JIRBOY

IndexedMIT★ 1
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/jirboy-search

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

网络搜索统一入口 - 整合通用搜索、学术搜索、多引擎搜索和 AI 搜索的全流程支持

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/search

What's inside

Skill name
search
Description
网络搜索统一入口 - 整合通用搜索、学术搜索、多引擎搜索和 AI 搜索的全流程支持
License
MIT
Instructions
410 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • package.json

SKILL.md (first lines)

# 网络搜索统一入口技能

**版本:** 1.0.0  
**整合自:** baidu-search, google-scholar-search, semantic-scholar-search, baidu-scholar-search, literature-search-pro, multi-search-engine, tavily-search

---

## 🎯 功能概览

| 命令 | 功能 | 原技能 | 适用场景 |
|------|------|--------|---------|
| `web` | 通用网页搜索 | baidu-search, multi-search-engine | 新闻、文档、一般信息检索 |
| `scholar` | 学术搜索(多源) | literature-search-pro, semantic-scholar-search, google-scholar-search, baidu-scholar-search | 学术论文检索、文献调研 |
| `multi` | 多引擎搜索(17 个) | multi-search-engine | 隐私搜索、特定引擎搜索、对比搜索 |
| `tavily` | AI 搜索(高质量) | tavily-search | 高质量搜索结果、AI 总结摘要 |
| `site` | 站内搜索 | multi-search-engine | 特定网站内容搜索 |
| `file` | 文件搜索 | multi-search-engine | PDF/PPT/DOC 等文件搜索 |

---

## 📖 使用方式

### 1️⃣ 通用网页搜索
```
web [搜索关键词]
web 人工智能最新进展
web 2026 年 A 股走势分析
web Python 教程
```

### 2️⃣ 学术搜索
```
scholar [研究领域] [参数]
scholar 振动控制 max_papers=20
scholar 深度学习 结构健康监测 year=2020-2026
scholar RTHS 时滞补偿 high_citation
```

### 3️⃣ 多引擎搜索
```
multi [引擎名] [关键词]
multi google privacy tools
multi duckduckgo AI news
multi wolfram 100 USD to CNY
```

### 4️⃣ AI 搜索(Tavily)
```
tavily [搜索关键词] [参数]
tavily 2024 年 AI 技术发展 search_depth=advanced
tavily 新能源汽车市场 max_results=10
```

### 5️⃣ 站内搜索
```
site [网站] [关键词]
site github.com react tutorial
site zhihu.com 振动控制
```

### 6️⃣ 文件搜索
```
file [文件类型] [关键词]
file pdf machine learning survey
file ppt 深度学习 应用
```

---

## 🛠️ 工作流程

### web 命令流程
```
1. 识别搜索意图(新闻/文档/一般信息)
2. 选择默认引擎(Baidu/Google)
3. 执行搜索(count=10,freshness=可选)
4. 返回结构化结果(标题/链接/摘要/时间)
```

### scholar 命令流程(多源搜索)
```
步骤 1: 选择数据库
  - OpenAlex(10K/天,最宽松)→ 第一优先
  - Semantic Scholar(1K/5 分钟)→ 第二优先
  - arXiv(最新预印本)→ 第三优先
  - Google Scholar(需代理)→ 可选
  - 百度学术(中文文献)→ 可选

步骤 2: 执行搜索
  - 关键词搜索(标题/摘要)
  - 年份过滤(可选)
  - 引用数排序(可选)

步骤 3: 去重合并
  - DOI 去重
  - arXiv ID 去重
  - 标题模糊匹配去重

步骤 4: 返回结果
  - 标题/作者/年份/期刊
  - 引用数/摘要/链接
  - 按质量排序(引用数优先)
```

### multi 命令流程
```
1. 解析引擎选择(google/baidu/duckduckgo/wolfram 等)
2. 构建搜索 URL(含高级操作符)
3. 执行搜索(web_fetch)
4. 提取结果(标题/链接/摘要)
```

### tavily 命令流程
```
1. 检查 API Key 配置
2. 调用 Tavily API
   - search_depth: basic/advanced
   - include_answer: true(AI 总结)
   - max_results: 5-10

From JIRBOY/openclaw-bridge-skills, MIT.

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Apr 12, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from JIRBOY

Cite this page

search skill. Agent Mart. https://agentmart.dev/skills/jirboy-search (last updated 2026-10-24)