web-research

Orquestra pesquisa web multi-fontes delegando a subagentes, sintetizando descobertas e produzindo relatórios citados. Divide perguntas de pesquisa em 2 a 5 subtópicos distintos, cria um arquivo de plano de pesquisa e gera até 3 subagentes em paralelo para investigação eficiente. Cada subagente realiza de 3 a 5 pesquisas na web por subtópico e escreve descobertas em arquivos locais com fatos-chave, citações e URLs de origem. Sintetiza resultados lendo arquivos locais de descobertas, integrando insights entre subtópicos e...

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

Mais skills de langchain-ai

deepagents-thread-inspector
langchain-ai
Inspecione e explique conversas no armazenamento de sessões SQLite local do Deep Agents Code. Use como fallback quando a ferramenta de rastreamento LangSmith não estiver disponível, para…
deepagents-python-quickstart
langchain-ai
Estruture um Deep Agent local mínimo em Python seguindo o quickstart oficial, usando busca web nativa do provedor em vez de Tavily. Use quando o usuário quiser…
deepagents-typescript-quickstart
langchain-ai
Estruture um Deep Agent local mínimo em TypeScript seguindo o quickstart oficial, usando busca web nativa do provedor em vez de Tavily. Use quando o usuário…
eval-engineering
langchain-ai
Inspecione iterativamente um repositório de agente e traces opcionais fornecidos pelo usuário, entreviste o usuário e crie, execute e audite evals do Harbor um por vez. Use para…
LangChain RAG Pipeline
langchain-ai
INVOQUE ESTA HABILIDADE ao construir QUALQUER sistema de geração aumentada por recuperação (RAG). Abrange carregadores de documentos, RecursiveCharacterTextSplitter, embeddings (OpenAI),…
LangChain Structured Output & HITL
langchain-ai
langchain-structured-output-&-hitl — uma skill instalável para agentes de IA, publicada por langchain-ai/langchain-skills.
LangSmith Datasets
langchain-ai
INVOQUE ESTA HABILIDADE ao criar conjuntos de dados de avaliação a partir de rastreamento OU ao fazer upload de conjuntos de dados para o LangSmith OU ao consultar conjuntos de dados. Abrange tipos de conjuntos de dados (final_response,…
langsmith-evaluator
langchain-ai
INVOQUE ESTA HABILIDADE ao construir pipelines de avaliação para LangSmith. Abrange três componentes principais: (1) Criação de Avaliadores - LLM como Juiz, código personalizado; (2)…