Token导航 LogoToken导航TokenDH.com
研究检索external-servicegithub未标认证来源可访问许可证需确认审计提醒

airweave-search爱维维搜索

Agent Skill

airweave-search 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 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。

总安装

541

周安装

23

GitHub Stars

2

下载量

190
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

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:airweave-search(爱维维搜索)
来源仓库:https://github.com/airweave-ai/skills
仓库路径:skills/airweave-search
安装命令:
npx skills add https://github.com/airweave-ai/skills --skill airweave-search
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 npx skills 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。

skills.shnpx skills
npx skills add https://github.com/airweave-ai/skills --skill airweave-search

简介

airweave-search 用于在 Airweave 知识库中高效搜索和检索上下文信息,支持跨应用查询。

  • 适合回答涉及 Slack、Notion、GitHub 等连接应用的具体问题或查找文档记录。
  • 当用户询问工作空间内的事实性问题或引用特定工具内容时应优先使用此技能。
  • 依赖 Airweave 平台的数据接入状态,需确保相关应用已正确集成并提供搜索权限。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Airweave Search

Use this skill to effectively search and retrieve context from Airweave collections, whether answering questions or gathering context to complete tasks.

When to Search

Search when the user:

  • Asks about data in their connected apps ("What did we discuss in Slack about...")
  • Needs to find documents, messages, issues, or records
  • Asks factual questions about their workspace ("Who is responsible for...", "What's our policy on...")
  • References specific tools by name ("in Notion", "on GitHub", "in Jira")
  • Needs recent information you don't have in your training
  • Needs you to check app data for context to complete a task ("check our Notion docs", "look at the Jira ticket", "see what we decided in Slack")

Don't search when:

  • User asks general knowledge questions (use your training)
  • User is asking how to SET UP Airweave (use airweave-setup skill instead)
  • User already provided all needed context in the conversation
  • The question is about Airweave itself, not data within it

Search Modes

Airweave provides three search modes. Choose based on user intent:

ModeWhen to UseSpeed
instantSimple lookups, exact term matching, browsingFastest
classicMost searches — AI generates an optimized search planFast
agenticComplex questions requiring reasoning, multi-step retrievalSlower, highest quality

Mode Selection Guide

User IntentMode
Quick document lookupinstant
Finding specific informationclassic (default)
General topic explorationclassic
"Summarize", "analyze", "compare"agentic
Complex multi-source questionsagentic
Simple keyword searchinstant with retrieval_strategy: "keyword"

Query Formulation

Extract Key Concepts

Turn user intent into effective search queries:

User SaysSearch Query
"What did Sarah say about the launch?""Sarah product launch"
"Find the API documentation""API documentation"
"Any bugs reported this week?""bug report issues"
"What's our refund policy?""refund policy customer"

Query Tips

  1. Use natural language - Airweave uses semantic search, not keyword matching
  2. Include context - "pricing feedback" is better than just "pricing"
  3. Be specific but not too narrow - Start moderately specific, broaden if no results
  4. Avoid filler words - Skip "please find", "can you search for"

Parameter Quick Reference

ParameterValuesWhen to Use
modeinstant/classic/agenticinstant for speed, classic for most searches, agentic for complex reasoning
limit1-1000Lower (5-10) for quick answers, higher (20-50) for exploration
offset0+Pagination (instant/classic only)
retrieval_strategyhybrid/neural/keywordInstant mode only: keyword for exact terms, neural for concepts, hybrid (default) for both
thinkingbooleanAgentic mode only: enable extended reasoning for complex queries

See PARAMETERS.md for detailed guidance.

Handling Results

Interpreting Scores

Results include a relevance_score field:

ScoreMeaningAction
0.85+Highly relevantUse confidently
0.70-0.85Likely relevantUse with context
0.50-0.70Possibly relevantMention uncertainty
Below 0.50Weak matchConsider rephrasing query

Understanding Result Structure

Each result contains:

  • name — Document/entity title
  • textual_representation — The full text content
  • breadcrumbs — Hierarchy path (e.g., Workspace > Channel > Message)
  • airweave_system_metadata.source_name — Source app (e.g., "Slack", "Notion")
  • web_url — Link back to the original item
  • created_at / updated_at — Timestamps

Synthesizing Answers

When presenting results to users:

  1. Lead with the answer - Don't start with "I found 5 results"
  2. Cite sources - Mention where info came from ("According to your Slack conversation...")
  3. Use breadcrumbs - Reference the hierarchy path for context ("In the Engineering > API Design channel...")
  4. Synthesize, don't dump - Combine relevant parts into coherent response
  5. Acknowledge gaps - If results don't fully answer, say so

Handling No/Poor Results

If search returns no results or low-quality matches:

  1. Try a different mode - Switch from instant to classic, or classic to agentic
  2. Broaden the query - Remove specific terms, use more general concepts
  3. Try different phrasing - Rephrase using synonyms or related terms
  4. Increase limit - Fetch more results to find relevant matches
  5. Check source availability - The data source might not be connected
  6. Ask for clarification - User might have more context to share

Finding the Search Tool

Airweave MCP tools follow the naming pattern search-{collection-name}. Look for tools matching this pattern in your available MCP tools.

Examples:

  • search-acmes-slack-k8v2x1
  • search-acmes-notion-p3m9q7
  • search-acmes-jira-w5n4r2

If no Airweave search tool is available:

  • The user may not have Airweave MCP configured
  • Ask if they have Airweave set up and connected to their AI assistant
  • Suggest using the airweave-setup skill for configuration help

Multiple collections: If multiple search-* tools are available, choose based on the collection name and the user's request. If unclear which to use, ask the user or try the most general-sounding one first.

Calling the Search Tool

Use the search-{collection} MCP tool with your chosen parameters:

search-acmes-slack-k8v2x1({
  query: "customer feedback pricing",
  mode: "classic",
  limit: 10
})
search-acmes-notion-p3m9q7({
  query: "API authentication docs",
  mode: "instant",
  retrieval_strategy: "hybrid"
})
search-acmes-jira-w5n4r2({
  query: "What decisions were made about the refund policy?",
  mode: "agentic"
})

Examples

See EXAMPLES.md for complete conversation examples showing effective search patterns.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

33.89%
按下载量换算64

Claude

30.01%
按下载量换算57

Cursor

20.23%
按下载量换算38

Gemini CLI

9.35%
按下载量换算18

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

external-service

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 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills