// Use NodeTool chat CLI commands, interactive terminal, agent mode, workspace management, and Global Chat features. Use when user asks about chat commands, interactive terminal, chat features, agent mode in chat, or the Global Chat interface.
| name | nodetool-chat-cli |
| description | Use NodeTool chat CLI commands, interactive terminal, agent mode, workspace management, and Global Chat features. Use when user asks about chat commands, interactive terminal, chat features, agent mode in chat, or the Global Chat interface. |
You help users use NodeTool's chat interfaces — CLI chat and Global Chat.
# Interactive chat (default model)
nodetool chat
# With specific provider/model
nodetool chat -p openai -m gpt-4o
nodetool chat -p anthropic -m claude-3.5-sonnet
nodetool chat -p ollama -m llama3
# With agent mode enabled
nodetool chat -a
# With specific tools
nodetool chat --tools google_search,browser,write_file
/)| Command | Purpose |
|---|---|
/help | Show all commands |
/provider | Current provider status |
/providers | List all available providers |
/models | List available models |
/model <id> | Switch to a different model |
/agent [on|off] | Toggle agent mode |
/tools [name] | List tools or show tool details |
/usage | Show token usage stats |
/exit | Quit chat |
/ prefix)These work like a sandboxed shell within the chat:
| Command | Purpose |
|---|---|
pwd | Print working directory |
ls [path] | List files |
cd [path] | Change directory |
mkdir <dir> | Create directory |
rm <path> | Remove file |
open <file> | Open file in default app |
cat <file> | Display file contents |
cp <src> <dest> | Copy file |
mv <src> <dest> | Move/rename file |
grep <pattern> [path] | Search file contents |
cdw | Jump to workspace root |
~/.nodetool_settings~/.nodetool_historyWhen agent mode is enabled (/agent on or -a flag), the chat gains:
| Tool | Capability |
|---|---|
google_search | Web search |
browser | Browse and extract web content |
write_file | Create/write files in workspace |
read_file | Read file contents |
execute_code | Run code snippets |
terminal | Shell commands |
grep | Search file contents |
calculator | Math operations |
screenshot | Take screenshots |
Global Chat is the desktop app's built-in chat interface with additional features.
1. Save a workflow in NodeTool editor
2. Open Global Chat
3. Select the workflow from the workflow picker
4. Chat naturally — the agent can invoke the workflow
nodetool chat -p openai -m gpt-4o
> What's the difference between FAISS and ChromaDB?
nodetool chat -a --tools google_search,browser,write_file
> Research the top 5 TypeScript ORMs and write a comparison to comparison.md
nodetool chat -p anthropic -m claude-3.5-sonnet -a --tools write_file,read_file,terminal
> Create a Python script that processes CSV files and generates summary statistics
For programmatic chat without the interactive terminal:
# Via Chat API (OpenAI-compatible)
curl -X POST http://localhost:7777/v1/chat/completions \
-H "Authorization: Bearer TOKEN" \
-d '{"model": "gpt-4o", "messages": [{"role": "user", "content": "Hello"}]}'
nodetool secrets store OPENAI_API_KEY)/agent on or -a flag/models to see available model IDscdw to jump back to workspace root/saveCreate custom NodeTool nodes, implement BaseNode subclasses, use @prop decorators, build node packages with process/genProcess methods, register nodes, handle media refs and secrets. Use when user asks to create a node, add a node type, build a custom node, implement a processor, or extend NodeTool with new functionality.
Configure AI model providers (OpenAI, Anthropic, Gemini, Ollama, HuggingFace, FAL, Replicate), set up API keys, choose models by task, run local inference with llama.cpp/MLX. Use when user asks about models, providers, API keys, which model to use, or configure any AI provider.
Build and edit NodeTool visual workflows using UI tools. Use this skill whenever the user asks to create a workflow, connect nodes, build a pipeline, add nodes to a graph, generate images/video/audio via workflows, or asks about workflow patterns. Also use when the user mentions node types, data flow, or wants to automate any multi-step process in NodeTool.
Create and configure NodeTool agent YAML configs, set up agent tools, system prompts, planning agents, and workspace isolation. Use when user asks to create an agent config, write YAML for an agent, configure agent tools, set up autonomous execution, or work with the agent CLI.
Create browser automation agents that navigate websites, extract data, fill forms, and perform multi-step web tasks using natural language instructions. Use when user asks to automate browsing, scrape websites with AI, build a web agent, or perform complex browser interactions.
Strip "AI slop" from code and prose in this repo — over-engineered abstractions, defensive checks on trusted paths, narrating comments, dead error handlers, redundant types, useEffect-for-derived-data, raw MUI imports, whole-store Zustand subscriptions, throat-clearing prose. Use when reviewing your own diff before commit, when the user says "unslop this", or when refactoring AI-generated code in `web/`, `electron/`, `mobile/`, or `packages/`. Triggers on TypeScript/React/Zustand/MUI/TanStack Query files. Tailored to NodeTool's stack (React 19, Zustand 4.5, MUI v7 + ui_primitives, TanStack Query v5, Vitest/Jest, Drizzle).