← 返回 Skills 市场

26 Multi Search Engine

Name: 26 Multi Search Engine
Author: smallkeyboy

作者 smallKeyboy · 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 26-multi-search-engine

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)

Multi Search Engine v2.0.1

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

Search Engines

Domestic (8)

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

International (9)

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

Quick Examples

// Basic search
web_fetch({"url": "https://www.google.com/search?q=python+tutorial"})

// Site-specific
web_fetch({"url": "https://www.google.com/search?q=site:github.com+react"})

// File type
web_fetch({"url": "https://www.google.com/search?q=machine+learning+filetype:pdf"})

// Time filter (past week)
web_fetch({"url": "https://www.google.com/search?q=ai+news&tbs=qdr:w"})

// Privacy search
web_fetch({"url": "https://duckduckgo.com/html/?q=privacy+tools"})

// DuckDuckGo Bangs
web_fetch({"url": "https://duckduckgo.com/html/?q=!gh+tensorflow"})

// Knowledge calculation
web_fetch({"url": "https://www.wolframalpha.com/input?i=100+USD+to+CNY"})

Advanced Operators

Operator	Example	Description
`site:`	`site:github.com python`	Search within site
`filetype:`	`filetype:pdf report`	Specific file type
`""`	`"machine learning"`	Exact match
`-`	`python -snake`	Exclude term
`OR`	`cat OR dog`	Either term

Time Filters

Parameter	Description
`tbs=qdr:h`	Past hour
`tbs=qdr:d`	Past day
`tbs=qdr:w`	Past week
`tbs=qdr:m`	Past month
`tbs=qdr:y`	Past year

Privacy Engines

DuckDuckGo: No tracking
Startpage: Google results + privacy
Brave: Independent index
Qwant: EU GDPR compliant

Bangs Shortcuts (DuckDuckGo)

Bang	Destination
`!g`	Google
`!gh`	GitHub
`!so`	Stack Overflow
`!w`	Wikipedia
`!yt`	YouTube

WolframAlpha Queries

Math: integrate x^2 dx
Conversion: 100 USD to CNY
Stocks: AAPL stock
Weather: weather in Beijing

Documentation

references/advanced-search.md - Domestic search guide
references/international-search.md - International search guide
CHANGELOG.md - Version history

License

MIT

安全使用建议

This skill is internally consistent: it just builds search URLs and shows web_fetch examples and needs no credentials or installs. Before installing: (1) Consider provenance—there's no source URL or homepage and the bundled files show a different version/owner than the registry entry, which lowers trust. (2) Be aware the examples include queries that can be used to find sensitive information (e.g., intext:password, site:filetype), so avoid running or enabling autonomous agent behaviors that perform broad reconnaissance against third-party sites. (3) Check Terms-of-Service and rate limits for the search engines you plan to query and consider running the skill with explicit user invocation only (disable autonomous runs) if you want to reduce accidental scraping or abusive queries. (4) If you need higher assurance, ask the publisher for source/homepage and a signed release or use a vetted alternative.

功能分析

Type: OpenClaw Skill Name: 26-multi-search-engine Version: 1.0.0 The bundle is a comprehensive search engine aggregator providing configurations and documentation for 17 different search engines (e.g., Google, Baidu, DuckDuckGo). It includes detailed guides in 'SKILL.md' and 'references/international-search.md' on using advanced search operators and 'Google Dorks' for specialized queries. While some documentation examples demonstrate how to find sensitive files (e.g., 'intext:password filetype:txt'), these are presented as educational examples of search engine capabilities rather than intentional instructions to attack the host or exfiltrate user data. No malicious code, obfuscation, or unauthorized network behaviors were found.

能力标签

requires-sensitive-credentials

能力评估

ℹ Purpose & Capability

The name/description match the actual content: a list of 17 search engine URLs and examples for building queries. The skill requires no binaries, env vars, or API keys, which is coherent. Minor inconsistencies: registry metadata lists version 1.0.0 while bundled files claim v2.0.1, and the provided ownerId in files differs from the registry owner ID; source/homepage are missing. These are metadata integrity issues (not direct functional mismatches) and reduce provenance confidence.

ℹ Instruction Scope

SKILL.md only instructs the agent to perform web_fetch calls against the listed search URLs and documents advanced operators. That stays within the stated purpose. However, the examples include search queries (e.g., intext:password filetype:txt, site:… with filetype) that can be used for sensitive-data reconnaissance. While this is functionality-consistent for a search tool, it expands potential for misuse and should be considered by deployers.

✓ Install Mechanism

No install spec and no code files to execute — instruction-only. This minimizes on-disk risk and is proportionate to the described capability.

✓ Credentials

No environment variables, credentials, or config paths are requested. The lack of secret/credential requirements is consistent with the skill's claim of 'No API keys required.'

✓ Persistence & Privilege

always is false and model invocation is allowed (default). The skill does not request permanent presence or elevated platform 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 26-multi-search-engine
安装完成后，直接呼叫该 Skill 的名称或使用 /26-multi-search-engine 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

- Initial release: integrates 17 search engines (8 Chinese, 9 global), including Google, Baidu, DuckDuckGo, and WolframAlpha. - Supports advanced search operators, time filters, privacy-focused search engines, and DuckDuckGo Bangs. - No API keys required for web crawling and querying. - Includes detailed usage examples and documentation references.

元数据

Slug 26-multi-search-engine

版本 1.0.0

许可证 MIT-0

累计安装 1

当前安装数 0

历史版本数 1

常见问题