← 返回 Skills 市场

Multi Search Engine

Name: Multi Search Engine
Author: jirboy

作者 JIRBOY · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ✓ 安全检测通过

总下载

当前安装

版本数

在 OpenClaw 中安装

/install multi-search-engine-cn

功能描述

Multi search engine integration with 17 engines (8 CN + 9 Global). Supports advanced search operators, time filters, site search, privacy engines, and Wolfra...

使用说明 (SKILL.md)

\r \r

Multi Search Engine v2.0.1\r

\r Integration of 17 search engines for web crawling without API keys.\r \r

Search Engines\r

Domestic (8)\r

Baidu: https://www.baidu.com/s?wd={keyword}\r
Bing CN: https://cn.bing.com/search?q={keyword}&ensearch=0\r
Bing INT: https://cn.bing.com/search?q={keyword}&ensearch=1\r
360: https://www.so.com/s?q={keyword}\r
Sogou: https://sogou.com/web?query={keyword}\r
WeChat: https://wx.sogou.com/weixin?type=2&query={keyword}\r
Toutiao: https://so.toutiao.com/search?keyword={keyword}\r
Jisilu: https://www.jisilu.cn/explore/?keyword={keyword}\r \r

International (9)\r

Google: https://www.google.com/search?q={keyword}\r
Google HK: https://www.google.com.hk/search?q={keyword}\r
DuckDuckGo: https://duckduckgo.com/html/?q={keyword}\r
Yahoo: https://search.yahoo.com/search?p={keyword}\r
Startpage: https://www.startpage.com/sp/search?query={keyword}\r
Brave: https://search.brave.com/search?q={keyword}\r
Ecosia: https://www.ecosia.org/search?q={keyword}\r
Qwant: https://www.qwant.com/?q={keyword}\r
WolframAlpha: https://www.wolframalpha.com/input?i={keyword}\r \r

Quick Examples\r

// Basic search\r
web_fetch({"url": "https://www.google.com/search?q=python+tutorial"})\r
\r
// Site-specific\r
web_fetch({"url": "https://www.google.com/search?q=site:github.com+react"})\r
\r
// File type\r
web_fetch({"url": "https://www.google.com/search?q=machine+learning+filetype:pdf"})\r
\r
// Time filter (past week)\r
web_fetch({"url": "https://www.google.com/search?q=ai+news&tbs=qdr:w"})\r
\r
// Privacy search\r
web_fetch({"url": "https://duckduckgo.com/html/?q=privacy+tools"})\r
\r
// DuckDuckGo Bangs\r
web_fetch({"url": "https://duckduckgo.com/html/?q=!gh+tensorflow"})\r
\r
// Knowledge calculation\r
web_fetch({"url": "https://www.wolframalpha.com/input?i=100+USD+to+CNY"})\r
```\r
\r
## Advanced Operators\r
\r
| Operator | Example | Description |\r
|----------|---------|-------------|\r
| `site:` | `site:github.com python` | Search within site |\r
| `filetype:` | `filetype:pdf report` | Specific file type |\r
| `""` | `"machine learning"` | Exact match |\r
| `-` | `python -snake` | Exclude term |\r
| `OR` | `cat OR dog` | Either term |\r
\r
## Time Filters\r
\r
| Parameter | Description |\r
|-----------|-------------|\r
| `tbs=qdr:h` | Past hour |\r
| `tbs=qdr:d` | Past day |\r
| `tbs=qdr:w` | Past week |\r
| `tbs=qdr:m` | Past month |\r
| `tbs=qdr:y` | Past year |\r
\r
## Privacy Engines\r
\r
- **DuckDuckGo**: No tracking\r
- **Startpage**: Google results + privacy\r
- **Brave**: Independent index\r
- **Qwant**: EU GDPR compliant\r
\r
## Bangs Shortcuts (DuckDuckGo)\r
\r
| Bang | Destination |\r
|------|-------------|\r
| `!g` | Google |\r
| `!gh` | GitHub |\r
| `!so` | Stack Overflow |\r
| `!w` | Wikipedia |\r
| `!yt` | YouTube |\r
\r
## WolframAlpha Queries\r
\r
- Math: `integrate x^2 dx`\r
- Conversion: `100 USD to CNY`\r
- Stocks: `AAPL stock`\r
- Weather: `weather in Beijing`\r
\r
## Documentation\r
\r
- `references/advanced-search.md` - Domestic search guide\r
- `references/international-search.md` - International search guide\r
- `CHANGELOG.md` - Version history\r
\r
## License\r
\r
MIT\r

安全使用建议

This skill is coherent and appears to do only what it claims: compose and fetch search URLs against public search engines. Before installing, consider: (1) provenance — the author/homepage are unknown, so maintenance, updates, or tamper history are unclear; (2) privacy — any query you issue (including sensitive strings) will be sent to third-party search sites (and DuckDuckGo bangs may redirect to other domains), so avoid searching secrets or private tokens; (3) scraping/legal concerns — aggressive automated fetching may trigger rate limits, CAPTCHAs, or violate terms of service of some engines; verify the agent's web_fetch implementation doesn't automatically include your credentials, cookies, or internal network access when it makes requests. If those points are acceptable, the skill's footprint is proportionate to its purpose.

功能分析

Type: OpenClaw Skill Name: multi-search-engine-cn Version: 1.0.0 The skill bundle provides a legitimate integration for 17 search engines (domestic and international) using standard URL templates. While the documentation in 'references/international-search.md' includes 'Google Dorking' examples (e.g., searching for passwords or admin panels), these are presented as educational advanced search techniques rather than automated malicious actions. There is no evidence of data exfiltration, unauthorized execution, or harmful prompt injection targeting the agent.

能力标签

requires-sensitive-credentials

能力评估

✓ Purpose & Capability

Name/description list multiple search engines and the files provide only URL templates, examples, and documentation. No binaries, env vars, or installs are requested — everything needed to perform searches (URL templates and examples for web_fetch) is present and proportional to the purpose.

✓ Instruction Scope

SKILL.md instructs the agent to construct and fetch search URLs (web_fetch calls) and documents advanced search operators. It does not instruct reading local files, accessing unrelated environment variables, or contacting hidden endpoints. The instructions remain within the stated scope of issuing search queries.

✓ Install Mechanism

Instruction-only skill with no install spec and no code files to write to disk. This is the lowest-risk install pattern and matches the manifest.

✓ Credentials

No environment variables, credentials, or config paths are required. The documented use cases (search and WolframAlpha queries) do not require API keys, matching the declared metadata.

✓ Persistence & Privilege

always is false and there are no requests to modify other skills or agent-wide settings. The skill does not request elevated persistence or privileges.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install multi-search-engine-cn
安装完成后，直接呼叫该 Skill 的名称或使用 /multi-search-engine-cn 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

- Integrates 17 search engines (8 Chinese, 9 international) with advanced operator and time filter support. - Enables site-specific, file type, and privacy-focused searches directly—no API keys required. - Supports DuckDuckGo bangs and WolframAlpha knowledge queries. - Provides quick usage examples and documentation links for advanced searching. - Highlights privacy-centric engine options and relevant search shortcuts.

元数据

Slug multi-search-engine-cn

版本 1.0.0

许可证 MIT-0

累计安装 1

当前安装数 1

历史版本数 1

常见问题