Agent skill · software engineering · aradotso

deerflow-super-agent-harness

deerflow-super-agent-harness — an agent skill for coding agents.

Why this skill is useful

Adds installation scripts, configuration patterns, and integration commands for the DeerFlow super agent harness that are not widely documented.

What it needs

Requires python installed locally. Requires anthropic, brave, feishu, openai, slack, tavily, telegram account access. About 7k tokens when loaded. Last updated 2026-07-09. 70 stars on the source repository.

What this skill does

bash After downloading the DMG, drag to Applications, then: Right-click → Open if you see a security warning deer-flow command becomes available in terminal deer-flow --help 1. Run deer-flowx64.exe 2. Follow installer prompts 3. Open Deer-Flow from Start Menu bash Clone the repository git clone https://github.com/bytedance/deer-flow.git cd deer-flow Install Python dependencies (Python 3.10+ required) pip install -r requirements.txt Copy and configure environment cp .env.example .env bash LLM Provider — OpenAI-compatible API OPENAIAPIKEY=youropenaiapikey OPENAIBASEURL=https://api.openai.com/v1 # or any compatible endpoint Optional: Anthropic ANTHROPICAPIKEY=youranthropicapikey Web Search TAVILYAPIKEY=yourtavilyapikey # recommended for research tasks BRAVEAPIKEY=yourbraveapikey # alternative Messaging channels (optional) TELEGRAMBOTTOKEN=yourtelegrambottoken SLACKBOTTOKEN=xoxb-yourslackbottoken SLACKAPPTOKEN=xapp-yourslackapptoken FEISHUAPPID=yourfeishuappid FEISHUAPPSECRET=yourfeishuappsecret yaml Sandbox execution mode sandbox: mode: docker # Options: local docker kubernetes LangGraph server langgraph: url: http://localhost:2024 Gateway API gateway: url: http://localhost:8001 port: 8001 Model configuration models: default: gpt-4o reasoning: o3-mini # for complex planning tasks multimodal: gpt-4o # for image/video understanding Channels (messaging integrations) channels: langgraphurl: http://localhost:2024 gatewayurl: http://localhost:8001 session: assistantid: leadagent config: recursionlimit: 100 context: thinkingenabled: true isplanmode: false subagentenabled: true telegram: enabled: true bottoken: $TELEGRAMBOTTOKEN allowedusers: [] # empty = allow all users slack: enabled: false bottoken: $SLACKBOTTOKEN apptoken: $SLACKAPPTOKEN allowedusers: [] feishu: enabled: false appid: $FEISHUAPPID appsecret: $FEISHUAPPSECRET bash Start DeerFlow server deer-flow start Start with specific config deer-flow start --config config.yaml Run a single task (non-interactive) deer-flo …

How to use it

Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:

@skills aradotso/deerflow-super-agent-harness

View the source on GitHub

Browse the @skills marketplace