web-research

作者: langchain-ai

協調多來源網路研究,透過委派子代理、綜合發現並產出附有引用的報告。將研究問題拆解為2至5個明確的子主題,建立研究計畫檔案,並平行啟動最多3個子代理以進行高效調查。每個子代理針對每個子主題執行3至5次網路搜尋,並將發現結果(包含關鍵事實、引用語句及來源網址)寫入本地檔案。最後透過讀取本地發現檔案,整合各子主題的見解,綜合產出結果。

npx skills add https://github.com/langchain-ai/deepagents --skill web-research

Web Research Skill

Research Process

Step 1: Create and Save Research Plan

Before delegating to subagents, you MUST:

  1. Create a research folder - Organize all research files in a dedicated folder relative to the current working directory:

    mkdir research_[topic_name]
    

    This keeps files organized and prevents clutter in the working directory.

  2. Analyze the research question - Break it down into distinct, non-overlapping subtopics

  3. Write a research plan file - Use the write_file tool to create research_[topic_name]/research_plan.md containing:

    • The main research question
    • 2-5 specific subtopics to investigate
    • Expected information from each subtopic
    • How results will be synthesized

Planning Guidelines:

  • Simple fact-finding: 1-2 subtopics
  • Comparative analysis: 1 subtopic per comparison element (max 3)
  • Complex investigations: 3-5 subtopics

Step 2: Delegate to Research Subagents

For each subtopic in your plan:

  1. Use the task tool to spawn a research subagent with:

    • Clear, specific research question (no acronyms)
    • Instructions to write findings to a file: research_[topic_name]/findings_[subtopic].md
    • Budget: 3-5 web searches maximum
  2. Run up to 3 subagents in parallel for efficient research

Subagent Instructions Template:

Research [SPECIFIC TOPIC]. Use the web_search tool to gather information.
After completing your research, use write_file to save your findings to research_[topic_name]/findings_[subtopic].md.
Include key facts, relevant quotes, and source URLs.
Use 3-5 web searches maximum.

Step 3: Synthesize Findings

After all subagents complete:

  1. Review the findings files that were saved locally:

    • First run list_files research_[topic_name] to see what files were created
    • Then use read_file with the file paths (e.g., research_[topic_name]/findings_*.md)
    • Important: Use read_file for LOCAL files only, not URLs
  2. Synthesize the information - Create a comprehensive response that:

    • Directly answers the original question
    • Integrates insights from all subtopics
    • Cites specific sources with URLs (from the findings files)
    • Identifies any gaps or limitations
  3. Write final report (optional) - Use write_file to create research_[topic_name]/research_report.md if requested

Note: If you need to fetch additional information from URLs, use the fetch_url tool, not read_file.

Best Practices

  • Plan before delegating - Always write research_plan.md first
  • Clear subtopics - Ensure each subagent has distinct, non-overlapping scope
  • File-based communication - Have subagents save findings to files, not return them directly
  • Systematic synthesis - Read all findings files before creating final response
  • Stop appropriately - Don't over-research; 3-5 searches per subtopic is usually sufficient

來自 langchain-ai 的更多技能

langgraph-docs
langchain-ai
存取 LangGraph 文件以建構具狀態代理與多代理工作流程。擷取官方 LangGraph Python 文件,涵蓋狀態機、基於圖形的代理設計及人機協作模式。根據查詢類型優先提供相關文件:實作指南用於操作問題、概念頁面用於理論、教學用於端到端範例、API 參考用於技術細節。自動選取 2 至 4 個最相關的文件 URL 並擷取內容以回答...
official
langgraph-human-in-the-loop
langchain-ai
暫停圖形執行以進行人工審查、批准或驗證,然後根據其輸入繼續執行。需要三個組件:檢查點儲存器(InMemorySaver 或 PostgresSaver)、配置中的執行緒 ID,以及可序列化為 JSON 的中斷負載。interrupt(value) 會暫停並顯示資料;Command(resume=value) 會繼續執行,並將該值返回給暫停的節點。所有 interrupt() 之前的程式碼在恢復時會重新執行,因此副作用必須是冪等的(使用 upsert,而非 insert)。支援審批工作流程,...
official
web-research
langchain-ai
使用此技能處理與網路研究相關的請求;它提供了一種結構化方法來進行全面的網路研究
official
langchain-oss-primer
langchain-ai
務必從此處開始任何 LangChain、Deep Agents 或 Lang
official
skill-creator
langchain-ai
建立有效技能的指南,透過專業知識、工作流程或工具整合來擴展代理功能。當使用者…時,請使用此技能。
official
social-media
langchain-ai
根據研究內容撰寫特定平台的社群媒體貼文,並生成搭配圖片。支援LinkedIn貼文(1,300字元,專業語氣)與Twitter/X推文串(每則280字元,採用1/🧵格式)。寫作前需將研究任務委派給子代理,並閱讀其發現以確保準確性與相關性。使用generate_social_image工具自動生成吸睛的社群圖片,採用大膽高對比構圖,針對小螢幕進行優化。
official
deep-agents-memory
langchain-ai
為Deep Agents提供可插拔的記憶體與檔案後端,支援短暫、持久及混合路由選項。四種後端類型:StateBackend(執行緒範圍內短暫)、StoreBackend(跨工作階段持久)、FilesystemBackend(本地開發的真實磁碟存取)及CompositeBackend(將不同路徑路由至不同後端)。FilesystemMiddleware提供六種檔案操作工具:ls、read_file、write_file、edit_file、glob、grep。CompositeBackend使用最長前綴匹配進行路由...
official
deep-agents-orchestration
langchain-ai
協調子代理、規劃多步驟任務,並在敏感操作時要求人類批准。透過任務工具將工作委派給專業子代理;自訂子代理支援隔離的工具集與系統提示,而預設的「通用」子代理則繼承主代理配置。使用 write_todos 規劃與追蹤複雜工作流程,將任務組織為待處理、進行中與已完成狀態;需提供 thread_id 以在多次調用間保持持續性。實作...
official