claude-to-deerflow

Interaja com a plataforma de agentes de IA DeerFlow por meio de sua API HTTP. Use esta skill quando o usuário quiser enviar mensagens ou perguntas ao DeerFlow para pesquisa/análise, iniciar uma conversa no DeerFlow, verificar o status ou a integridade do DeerFlow, listar modelos/skills/agentes disponíveis no DeerFlow, gerenciar a memória do DeerFlow, enviar arquivos para threads do DeerFlow ou delegar tarefas complexas de pesquisa ao DeerFlow. Use também quando o usuário mencionar deerflow, deer flow ou quiser executar uma tarefa de pesquisa aprofundada que o DeerFlow possa realizar.

O que é claude-to-deerflow?

Esta skill permite que um agente de IA (como Claude Code) se comunique com uma instância do DeerFlow em execução por meio de sua API HTTP. DeerFlow é uma plataforma de agentes de IA construída em LangGraph que orquestra subagentes para tarefas como pesquisa, execução de código e navegação na web. A skill expõe operações como verificação de saúde, envio de mensagens com streaming de respostas (em diferentes modos como Flash, Standard, Pro e Ultra), gerenciamento de threads, listagem de modelos, skills e agentes, upload de arquivos, e acesso à memória do sistema. Ela é especialmente útil para delegar tarefas complexas de pesquisa e análise ao DeerFlow, que podem envolver planejamento e uso de subagentes. A comunicação é feita via requisições HTTP, e a skill fornece um script auxiliar (chat.sh) para simplificar o envio de mensagens e a coleta de respostas completas.

Funciona com✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/bytedance/deer-flow/tree/main/skills/public/claude-to-deerflow

Installed? Explore more Programação e Desenvolvimento skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →

Perguntar na sua IA favorita

Abre um novo chat com esta habilidade de agente já pré-carregada.

Documentação

Skill DeerFlow

Comunique-se com uma instância do DeerFlow em execução por meio de sua API HTTP. DeerFlow é uma plataforma de agentes de IA construída em LangGraph que orquestra subagentes para pesquisa, execução de código, navegação na web e muito mais.

Arquitetura

O DeerFlow expõe duas superfícies de API atrás de um proxy reverso Nginx:

ServiçoPorta DiretaVia ProxyFinalidade
API Gateway8001$DEERFLOW_GATEWAY_URLEndpoints REST e runtime de agente incorporado
API compatível com LangGraph8001$DEERFLOW_LANGGRAPH_URLThreads de agente, execuções, streaming

Variáveis de Ambiente

Todas as URLs são configuráveis por meio de variáveis de ambiente. Leia essas variáveis de ambiente antes de fazer qualquer requisição.

VariávelPadrãoDescrição
DEERFLOW_URLhttp://localhost:2026URL base do proxy unificado
DEERFLOW_GATEWAY_URL${DEERFLOW_URL}URL base da API do Gateway (modelos, skills, memória, uploads)
DEERFLOW_LANGGRAPH_URL${DEERFLOW_URL}/api/langgraphURL base da API LangGraph (threads, execuções)

Ao fazer chamadas curl, sempre resolva as URLs assim:

# Resolver URLs base a partir do ambiente (faça isso PRIMEIRO antes de qualquer chamada à API)
DEERFLOW_URL="${DEERFLOW_URL:-http://localhost:2026}"
DEERFLOW_GATEWAY_URL="${DEERFLOW_GATEWAY_URL:-$DEERFLOW_URL}"
DEERFLOW_LANGGRAPH_URL="${DEERFLOW_LANGGRAPH_URL:-$DEERFLOW_URL/api/langgraph}"

Operações Disponíveis

1. Verificação de Saúde

Verifique se o DeerFlow está em execução:

curl -s "$DEERFLOW_GATEWAY_URL/health"

2. Enviar uma Mensagem (Streaming)

Esta é a operação principal. Ela cria uma thread e transmite a resposta do agente.

Passo 1: Criar uma thread

curl -s -X POST "$DEERFLOW_LANGGRAPH_URL/threads" \
  -H "Content-Type: application/json" \
  -d '{}'

Resposta: {"thread_id": "<uuid>", ...}

Passo 2: Transmitir uma execução

curl -s -N -X POST "$DEERFLOW_LANGGRAPH_URL/threads/<thread_id>/runs/stream" \
  -H "Content-Type: application/json" \
  -d '{
    "assistant_id": "lead_agent",
    "input": {
      "messages": [
        {
          "type": "human",
          "content": [{"type": "text", "text": "SUA MENSAGEM AQUI"}]
        }
      ]
    },
    "stream_mode": ["values", "messages-tuple"],
    "stream_subgraphs": true,
    "config": {
      "recursion_limit": 1000
    },
    "context": {
      "thinking_enabled": true,
      "is_plan_mode": true,
      "subagent_enabled": true,
      "thread_id": "<thread_id>"
    }
  }'

A resposta é um stream SSE. Cada evento tem o formato:

event: <tipo_evento>
data: <dados_json>

Tipos de evento principais:

  • metadata — metadados da execução, incluindo run_id
  • values — instantâneo completo do estado com array messages
  • messages-tuple — atualizações incrementais de mensagens (pedaços de texto de IA, chamadas de ferramenta, resultados de ferramenta)
  • end — stream completo

Modos de contexto (definidos via context):

  • Modo Flash: thinking_enabled: false, is_plan_mode: false, subagent_enabled: false
  • Modo Padrão: thinking_enabled: true, is_plan_mode: false, subagent_enabled: false
  • Modo Pro: thinking_enabled: true, is_plan_mode: true, subagent_enabled: false
  • Modo Ultra: thinking_enabled: true, is_plan_mode: true, subagent_enabled: true

3. Continuar uma Conversa

Para enviar mensagens de acompanhamento, reutilize o mesmo thread_id do passo 2 e faça um POST de outra execução com a nova mensagem.

4. Listar Modelos

curl -s "$DEERFLOW_GATEWAY_URL/api/models"

Retorna: {"models": [{"name": "...", "provider": "...", ...}, ...]}

5. Listar Skills

curl -s "$DEERFLOW_GATEWAY_URL/api/skills"

Retorna: {"skills": [{"name": "...", "enabled": true, ...}, ...]}

6. Ativar/Desativar uma Skill

curl -s -X PUT "$DEERFLOW_GATEWAY_URL/api/skills/<nome_skill>" \
  -H "Content-Type: application/json" \
  -d '{"enabled": true}'

7. Listar Agentes

curl -s "$DEERFLOW_GATEWAY_URL/api/agents"

Retorna: {"agents": [{"name": "...", ...}, ...]}

8. Obter Memória

curl -s "$DEERFLOW_GATEWAY_URL/api/memory"

Retorna contexto do usuário, fatos e resumos do histórico da conversa.

9. Enviar Arquivos para uma Thread

curl -s -X POST "$DEERFLOW_GATEWAY_URL/api/threads/<thread_id>/uploads" \
  -F "files=@/caminho/para/arquivo.pdf"

Suporta PDF, PPTX, XLSX, DOCX — converte automaticamente para Markdown.

10. Listar Arquivos Enviados

curl -s "$DEERFLOW_GATEWAY_URL/api/threads/<thread_id>/uploads/list"

11. Obter Histórico da Thread

curl -s "$DEERFLOW_LANGGRAPH_URL/threads/<thread_id>/history"

12. Listar Threads

curl -s -X POST "$DEERFLOW_LANGGRAPH_URL/threads/search" \
  -H "Content-Type: application/json" \
  -d '{"limit": 20, "sort_by": "updated_at", "sort_order": "desc"}'

Script de Uso

Para enviar mensagens e coletar a resposta completa, use o script auxiliar:

bash /caminho/para/skills/claude-to-deerflow/scripts/chat.sh "Sua pergunta aqui"

Veja scripts/chat.sh para a implementação. O script:

  1. Verifica a saúde
  2. Cria uma thread
  3. Transmite a execução e coleta a resposta final da IA
  4. Imprime o resultado

Analisando a Saída SSE

O stream retorna eventos SSE. Para extrair a resposta final da IA de um evento values:

  • Procure pelo último bloco event: values
  • Analise seu JSON data
  • O array messages contém todas as mensagens; a última com type: "ai" é a resposta
  • O campo content dessa mensagem é a resposta de texto da IA

Tratamento de Erros

  • Se a verificação de saúde falhar, o DeerFlow não está em execução. Informe ao usuário que ele precisa iniciá-lo.
  • Se o stream retornar um evento de erro, extraia e exiba a mensagem de erro.
  • Problemas comuns: porta não aberta, serviços ainda iniciando, erros de configuração.

Dicas

  • Para perguntas rápidas, use o modo Flash (mais rápido, sem planejamento).
  • Para tarefas de pesquisa, use o modo Pro ou Ultra (permite planejamento e subagentes).
  • Você pode enviar arquivos primeiro e depois referenciá-los em sua mensagem.
  • Os IDs de thread persistem — você pode retornar a uma conversa posteriormente.

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

academic-paper-review

Use this skill when the user requests to review, analyze, critique, or summarize academic papers, research articles, preprints, or scientific publications. Supports comprehensive structured reviews covering methodology assessment, contribution evaluation, literature positioning, and constructive feedback generation. Trigger on queries involving paper URLs, uploaded PDFs, arXiv links, or requests like "review this paper", "analyze this research", "summarize this study", or "write a peer review".

bootstrap

Generate a personalized SOUL.md through a warm, adaptive onboarding conversation. Trigger when the user wants to create, set up, or initialize their AI partner's identity — e.g., "create my SOUL.md", "bootstrap my agent", "set up my AI partner", "define who you are", "let's do onboarding", "personalize this AI", "make you mine", or when a SOUL.md is missing. Also trigger for updates: "update my SOUL.md", "change my AI's personality", "tweak the soul".

bytedance/academic-paper-review

Use this skill when the user requests to review, analyze, critique, or summarize academic papers, research articles, preprints, or scientific publications. Supports comprehensive structured reviews covering methodology assessment, contribution evaluation, literature positioning, and constructive feedback generation. Trigger on queries involving paper URLs, uploaded PDFs, arXiv links, or requests like "review this paper", "analyze this research", "summarize this study", or "write a peer review".

bytedance/chart-visualization

This skill should be used when the user wants to visualize data. It intelligently selects the most suitable chart type from 26 available options, extracts parameters based on detailed specifications, and generates a chart image using a JavaScript script.

bytedance/claude-to-deerflow

Interact with DeerFlow AI agent platform via its HTTP API. Use this skill when the user wants to send messages or questions to DeerFlow for research/analysis, start a DeerFlow conversation thread, check DeerFlow status or health, list available models/skills/agents in DeerFlow, manage DeerFlow memory, upload files to DeerFlow threads, or delegate complex research tasks to DeerFlow. Also use when the user mentions deerflow, deer flow, or wants to run a deep research task that DeerFlow can handle.

bytedance/consulting-analysis

Use this skill when the user requests to generate, create, or write professional research reports including but not limited to market analysis, consumer insights, brand analysis, financial analysis, industry research, competitive intelligence, investment due diligence, or any consulting-grade analytical report. This skill operates in two phases — (1) generating a structured analysis framework with chapter skeleton, data query requirements, and analysis logic, and (2) after data collection by other skills, producing the final consulting-grade report with structured narratives, embedded charts, and strategic insights.

bytedance/data-analysis

Use this skill when the user uploads Excel (.xlsx/.xls) or CSV files and wants to perform data analysis, generate statistics, create summaries, pivot tables, SQL queries, or any form of structured data exploration. Supports multi-sheet Excel workbooks, aggregation, filtering, joins, and exporting results to CSV/JSON/Markdown.

bytedance/deep-research

Use this skill instead of WebSearch for ANY question requiring web research. Trigger on queries like "what is X", "explain X", "compare X and Y", "research X", or before content generation tasks. Provides systematic multi-angle research methodology instead of single superficial searches. Use this proactively when the user's question needs online information.

bytedance/find-skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

bytedance/frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

bytedance/github-deep-research

Conduct multi-round deep research on any GitHub Repo. Use when users request comprehensive analysis, timeline reconstruction, competitive analysis, or in-depth investigation of GitHub. Produces structured markdown reports with executive summaries, chronological timelines, metrics analysis, and Mermaid diagrams. Triggers on Github repository URL or open source projects.

bytedance/image-generation

Use this skill when the user requests to generate, create, imagine, or visualize images including characters, scenes, products, or any visual content. Supports structured prompts and reference images for guided generation.

bytedance/podcast-generation

Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.

bytedance/ppt-generation

Use this skill when the user requests to generate, create, or make presentations (PPT/PPTX). Creates visually rich slides by generating images for each slide and composing them into a PowerPoint file.

bytedance/skill-creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

bytedance/surprise-me

Create a delightful, unexpected "wow" experience for the user by dynamically discovering and creatively combining other enabled skills. Triggers when the user says "surprise me" or any request expressing a desire for an unexpected creative showcase. Also triggers when the user is bored, wants inspiration, or asks for "something interesting".

bytedance/vercel-deploy

Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production", "Create a preview deployment", "Deploy and give me the link", or "Push this live". No authentication required - returns preview URL and claimable deployment link.

bytedance/video-generation

Use this skill when the user requests to generate, create, or imagine videos. Supports structured prompts and reference image for guided generation.

bytedance/web-design-guidelines

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".

chart-visualization

This skill should be used when the user wants to visualize data. It intelligently selects the most suitable chart type from 26 available options, extracts parameters based on detailed specifications, and generates a chart image using a JavaScript script.

Habilidades Relacionadas