Token导航 LogoToken导航

Agent Skill · 研究检索

omnisearch(omnisearch 搜索)

omnisearch 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

omnisearch 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为调用外部服务;许可证为 MIT-0,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 2,118。

总安装 67,714周安装 2,879GitHub Stars 1下载 23,723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-0
版本
1.0.0

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:omnisearch(omnisearch 搜索)
来源仓库:https://github.com/bguidolim/omnisearch
安装命令:
openclaw skills install omnisearch
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。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install omnisearch

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。

强制性网络搜索工具,用于搜索当前信息、新闻、价格、事实或培训中未包含的任何数据。这是在 OpenClaw 环境中搜索互联网的唯一方法。当用户要求进行网络搜索或您需要最新信息时,请务必使用此技能。

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 OpenClaw;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 openclaw skills install omnisearch;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

    它需要调用外部服务,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

omnisearch 怎么安装?

在终端执行 openclaw skills install omnisearch。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

omnisearch 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。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。

omnisearch 需要什么权限?

权限级别是调用外部服务。该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

omnisearch 是免费的吗?

来源标注的许可证是 MIT-0。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。

omnisearch 用的人多吗?

公开数据是累计安装 67,714 次,近一周安装 2,879 次,下载 23,723 次,GitHub 1 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。

omnisearch 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。

先想清楚的地方

  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 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 OpenClaw,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。

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
omnisearch

omnisearch 搜索 · 本页

67,7141调用外部服务MIT-0有提醒

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

name
omnisearch
description
|

OmniSearch Skill - Web Search Tool

CRITICAL: When to Use This Skill

ALWAYS use OmniSearch when:

  • User explicitly asks to "search", "google", "look up", "find online"
  • User asks about current events, news, or recent developments
  • User requests prices, product specs, reviews, or comparisons
  • User asks "what's the latest..." or "what's happening with..."
  • You need to verify current facts, statistics, or data
  • User asks about people, companies, or organizations you don't know
  • Information might have changed since your training cutoff
  • User needs sources or citations for factual claims

Examples of queries requiring OmniSearch:

  • "What's the weather in Hamburg today?"
  • "Search for iPhone 16 reviews"
  • "What happened in the tech industry this week?"
  • "Find the current price of Bitcoin"
  • "Look up restaurants near me"
  • "What are people saying about the new Tesla model?"

DO NOT Use OmniSearch When:

  • Answering from your existing knowledge is sufficient and current
  • User is asking for creative content, code, or analysis
  • Question is about concepts, definitions, or timeless information

How to Execute Search

IMPORTANT: Run the script from the omnisearch skill directory using the relative path ./scripts/omnisearch.sh

Method 1: Recommended (Wrapper Script)

Use the wrapper script for all searches:

# AI-enhanced search (includes summarization) - USE THIS FOR MOST QUERIES
./scripts/omnisearch.sh ai "your search query here"

# Raw web search results (when you need direct source material)
./scripts/omnisearch.sh web "your search query here"

Available providers:

  • ai type: perplexity (default - recommended for most queries)
  • web type: perplexity (default), brave, kagi, tavily, exa

Optional provider override:

./scripts/omnisearch.sh ai "query" perplexity
./scripts/omnisearch.sh web "query" brave
./scripts/omnisearch.sh web "query" kagi
./scripts/omnisearch.sh web "query" tavily
./scripts/omnisearch.sh web "query" exa

Practical examples:

# Current weather
./scripts/omnisearch.sh ai "weather in Hamburg today"

# Product research
./scripts/omnisearch.sh web "iPhone 16 Pro reviews 2024"

# News search
./scripts/omnisearch.sh ai "latest AI developments this week"

# Price comparison
./scripts/omnisearch.sh web "DJI Mini 4 Pro price Germany" brave

# Research with premium provider
./scripts/omnisearch.sh web "machine learning papers 2024" kagi

Method 2: Fallback (Direct mcporter)

Only use if the wrapper script fails:

mcporter call omnisearch.ai_search query="your search query" provider="perplexity"
mcporter call omnisearch.web_search query="your search query" provider="brave"

Response Format

After receiving search results, ALWAYS:

  1. Summarize: Present 2-5 key bullet points with the most relevant findings
  2. Cite sources: Include 2-6 source URLs formatted as clickable links
  3. Add context: Note if information is time-sensitive or has low confidence
  4. Answer directly: Don't just dump results - synthesize and answer the user's question

Example response structure:

Based on my search, here's what I found:

- [Key finding 1]
- [Key finding 2]
- [Key finding 3]

Sources:
- [Title 1](URL1)
- [Title 2](URL2)

Note: This information is from [date/timeframe] and may change.

Search Query Best Practices

  • Keep queries concise and specific (3-8 words ideal)
  • Use natural language, not keyword stuffing
  • Include location when relevant: "restaurants Hamburg"
  • Include timeframe when needed: "iPhone 16 reviews 2024"
  • For prices, include currency/region if specific: "iPhone 16 price Germany"

Troubleshooting

If the wrapper script fails:

  1. Check if you're in the correct directory (should contain scripts/ folder)
  2. Verify the script has execution permissions: chmod +x ./scripts/omnisearch.sh
  3. Try the fallback method (direct mcporter call)
  4. Check if mcporter is properly installed and configured

Common issues:

  • "command not found": Script path is incorrect or you're not in the skill directory
  • "No such file": The script may not have been copied to scripts/ folder yet
  • Empty results: Try different provider or rephrase query

Query formatting:

  • Queries with spaces are automatically handled (no need to escape)
  • Use quotes in the command: ./scripts/omnisearch.sh ai "query with spaces"
  • Special characters should work fine within the quoted string

Important Notes

  • Directory structure: This SKILL.md file is in the omnisearch skill folder, with the script in ./scripts/omnisearch.sh relative to this file
  • Script validation: The wrapper script automatically validates that a query is provided and will show usage help if missing
  • Provider selection:

- Perplexity (default): Best for AI-enhanced results with summarization and context - Brave: Good for privacy-focused, unfiltered web results - Kagi: Premium search with advanced filtering and ranking - Tavily: Optimized for research and comprehensive coverage - Exa: Semantic search with AI-powered relevance

  • This is a LOCAL tool - it runs on this OpenClaw instance
  • ALWAYS run the search immediately when user requests it - don't ask permission
  • The wrapper script (omnisearch.sh) is designed to work reliably even with basic LLMs

平台分布

OpenClaw

78.02%
按下载量换算18,509

安全审计

VirusTotal

通过

ClawScan

可疑

Static analysis

未展示

权限和风险

调用外部服务

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills