[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AE142NFM6ZFZYQK2ZJBFE6":3,"skill-same:01M7AE142NFM6ZFZYQK2ZJBFE6":44},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7AE142NFM6ZFZYQK2ZJBFE6","nodetool-chat-cli",null,"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.","hanchenhao\u002Fai-canvas","hanchenhao","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F15713703?v=4","01M7ADWCF5AE30N3MG7MDF3RV2","01M7ADWCFVJS4V8VD9KWJG22WR",1,"AGPL-3.0","https:\u002F\u002Fgithub.com\u002Fhanchenhao\u002Fai-canvas\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fnodetool-chat-cli\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: nodetool-chat-cli\ndescription: 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.\n---\n\nYou help users use NodeTool's chat interfaces — the terminal chat CLI and Global Chat.\n\n# Chat CLI\n\nThe chat CLI is a terminal UI. Two equivalent entry points:\n- `nodetool-chat` (standalone binary)\n- `nodetool chat` (subcommand that forwards to the chat UI)\n\nFrom source (no build): `npm run dev:chat -- [flags]`.\n\n## Starting Chat\n\n```bash\n# Interactive chat (default provider\u002Fmodel from saved settings)\nnodetool chat\n\n# With a specific provider\u002Fmodel\nnodetool chat -p openai -m gpt-5.4\nnodetool chat -p anthropic -m claude-sonnet-4-6\nnodetool chat -p ollama -m qwen-3.5:4b\n\n# Restrict the enabled tools\nnodetool chat --tools google_search,browser,write_file\n\n# Connect to a running server instead of a local provider\nnodetool chat -u ws:\u002F\u002Flocalhost:7777\u002Fws\n\n# Provision an isolated Docker sandbox and expose its tools to the agent\nnodetool chat --sandbox\n```\n\n> **Agent mode is always on.** Every chat session runs the unified agent loop\n> (planning + tools). The old `-a\u002F--agent` and `--no-agent` flags are deprecated\n> no-ops kept for compatibility.\n\n## CLI Flags\n\n| Flag | Purpose |\n|------|---------|\n| `-p, --provider \u003Cname>` | LLM provider (see list below) |\n| `-m, --model \u003Cid>` | Model ID |\n| `-w, --workspace \u003Cpath>` | Workspace directory (default: cwd) |\n| `--tools \u003Clist>` | Comma-separated enabled tools |\n| `-u, --url \u003Cws-url>` | Connect to a NodeTool server WebSocket |\n| `--sandbox` | Isolated Docker sandbox with file\u002Fshell\u002Fbrowser\u002Fdesktop tools |\n| `--sandbox-image \u003Cimage>` | Override the sandbox Docker image |\n| `--no-read-only-search` | Disable the read-only `run_search` fan-out primitive |\n| `--trace-file \u003Cpath>` | Append LLM\u002Fagent\u002Fworkflow spans as JSONL |\n| `--trace-stdout [pretty\\|json]` | Stream spans to stdout |\n\nProviders: `anthropic`, `claude_agent_sdk`, `openai`, `codex`, `gemini`, `xai`,\n`groq`, `mistral`, `deepseek`, `moonshot`, `minimax`, `cerebras`, `alibaba`, `gmi`,\n`together`, `openrouter`, `huggingface`, `replicate`, `kie`, `aki`, `ollama`,\n`lmstudio`, `mlx`. Any other registered provider id (e.g. `vllm`) also works when\npassed explicitly.\n\n## Slash Commands (prefix with `\u002F`)\n\n| Command | Purpose |\n|---------|---------|\n| `\u002Fhelp` | Toggle the command help panel |\n| `\u002Fnew` | Start a fresh session (clears history + server thread) |\n| `\u002Fclear` | Clear the visible history |\n| `\u002Fcompact` | Summarize and compact the conversation context |\n| `\u002Fmodel [id]` | Show current model, or switch with an id |\n| `\u002Fprovider [name]` | Show current provider, or switch (loads that provider's default model) |\n| `\u002Ftools` | List the enabled tools |\n| `\u002Fexit`, `\u002Fquit` | Quit chat |\n\nNon-slash input is sent to the model as a chat message — there is no built-in\nshell (`ls`, `cd`, …) in the chat prompt. File operations happen through the\nagent's file tools in the workspace.\n\n## Configuration\n\n- Settings file: `~\u002F.nodetool\u002Fchat-settings.json` (persists provider + model)\n\n# Agent Capabilities\n\nBecause the agent loop is always active, the chat can:\n\n1. **Plan** — break tasks into steps\n2. **Use tools** — search, browse, file ops, code execution, media generation\n3. **Iterate** — execute steps, evaluate results, adapt\n4. **Run workflows** — trigger saved NodeTool workflows\n\n## Common Tools\n\n| Tool | Capability |\n|------|-----------|\n| `google_search` | Web search |\n| `browser` | Browse and extract web content |\n| `read_file` \u002F `write_file` \u002F `edit_file` | Workspace file ops |\n| `grep` \u002F `glob` | Search files |\n| `screenshot` | Capture a page screenshot |\n| `find_model` | Pick a model by capability |\n| `generate_image` \u002F `generate_video` \u002F `generate_speech` | Media generation |\n\nRestrict the set with `--tools a,b,c`; inspect the active set with `\u002Ftools`.\n\n# Global Chat\n\nGlobal Chat is the desktop app's built-in chat interface.\n\n## Features\n\n- Chat with any configured AI model (OpenAI, Anthropic, Gemini, local)\n- Multiple conversation threads\n- Standalone window (launch from the system tray)\n- Tools: web search, image generation, workflow execution\n- The same always-on agent loop as the CLI\n\n## Workflow Integration\n\n```\n1. Save a workflow in the NodeTool editor\n2. Open Global Chat\n3. Select the workflow from the workflow picker\n4. Chat naturally — the agent can invoke the workflow as a tool\n```\n\n# Typical Flows\n\n## Quick Question\n```bash\nnodetool chat -p openai -m gpt-5.4\n> What's the difference between FAISS and ChromaDB?\n```\n\n## Research Task\n```bash\nnodetool chat --tools google_search,browser,write_file\n> Research the top 5 TypeScript ORMs and write a comparison to comparison.md\n```\n\n## Code Generation\n```bash\nnodetool chat -p anthropic -m claude-sonnet-4-6 --tools write_file,read_file,grep\n> Create a Python script that processes CSV files and generates summary statistics\n```\n\n## Headless \u002F Programmatic Chat\n\nFor non-interactive chat, use the OpenAI-compatible Chat API on a running server\n(`nodetool serve`):\n\n```bash\ncurl -X POST http:\u002F\u002Flocalhost:7777\u002Fv1\u002Fchat\u002Fcompletions \\\n  -H \"Authorization: Bearer TOKEN\" \\\n  -d '{\"model\": \"gpt-5.4\", \"messages\": [{\"role\": \"user\", \"content\": \"Hello\"}]}'\n```\n\n# Common Pitfalls\n\n- **No provider configured**: store a key first (`nodetool secrets store OPENAI_API_KEY`). Providers without a key are greyed out and `\u002Fprovider \u003Cname>` refuses them.\n- **Wrong model ID**: switch with `\u002Fmodel \u003Cid>`; each provider's default is loaded when you switch providers.\n- **Expecting a shell**: bare commands like `ls` are sent to the model, not run. Use the agent's file tools or `--sandbox`.\n- **Looking for `\u002Fagent`**: agent mode is always on; there is no toggle.\n","You help users use NodeTool's chat interfaces — the terminal chat CLI and Global Chat.\n\n# Chat CLI\n\nThe chat CLI is a terminal UI. Two equivalent entry points:\n- `nodetool-chat` (standalone binary)\n- `nodetool chat` (subcommand that forwards to the chat UI)\n\nFrom source (no build): `npm run dev:chat -- [flags]`.\n\n## Starting Chat\n\n```bash\n# Interactive chat (default provider\u002Fmodel from saved settings)\nnodetool chat\n\n# With a specific provider\u002Fmodel\nnodetool chat -p openai -m gpt-5.4\nnodetool chat -p anthropic -m claude-sonnet-4-6\nnodetool chat -p ollama -m qwen-3.5:4b\n\n# Restrict the enabled tools\nnodetool chat --tools google_search,browser,write_file\n\n# Connect to a running server instead of a local provider\nnodetool chat -u ws:\u002F\u002Flocalhost:7777\u002Fws\n\n# Provision an isolated Docker sandbox and expose its tools to the agent\nnodetool chat --sandbox\n```\n\n> **Agent mode is always on.** Every chat session runs the unified agent loop\n> (planning + tools). The old `-a\u002F--agent` and `--no-agent` flags are deprecated\n> no-ops kept for compatibility.\n\n## CLI Flags\n\n| Flag | Purpose |\n|------|---------|\n| `-p, --provider \u003Cname>` | LLM provider (see list below) |\n| `-m, --model \u003Cid>` | Model ID |\n| `-w, --workspace \u003Cpath>` | Workspace directory (default: cwd) |\n| `--tools \u003Clist>` | Comma-separated enabled tools |\n| `-u, --url \u003Cws-url>` | Connect to a NodeTool server WebSocket |\n| `--sandbox` | Isolated Docker sandbox with file\u002Fshell\u002Fbrowser\u002Fdesktop tools |\n| `--sandbox-image \u003Cimage>` | Override the sandbox Docker image |\n| `--no-read-only-search` | Disable the read-only `run_search` fan-out primitive |\n| `--trace-file \u003Cpath>` | Append LLM\u002Fagent\u002Fworkflow spans as JSONL |\n| `--trace-stdout [pretty\\|json]` | Stream spans to stdout |\n\nProviders: `anthropic`, `claude_agent_sdk`, `openai`, `codex`, `gemini`, `xai`,\n`groq`, `mistral`, `deepseek`, `moonshot`, `minimax`, `cerebras`, `alibaba`, `gmi`,\n`together`, `openrouter`, `huggingface`, `replicate`, `kie`, `aki`, `ollama`,\n`lmstudio`, `mlx`. Any other registered provider id (e.g. `vllm`) also works when\npassed explicitly.\n\n## Slash Commands (prefix with `\u002F`)\n\n| Command | Purpose |\n|---------|---------|\n| `\u002Fhelp` | Toggle the command help panel |\n| `\u002Fnew` | Start a fresh session (clears history + server thread) |\n| `\u002Fclear` | Clear the visible history |\n| `\u002Fcompact` | Summarize and compact the conversation context |\n| `\u002Fmodel [id]` | Show current model, or switch with an id |\n| `\u002Fprovider [name]` | Show current provider, or switch (loads that provider's default model) |\n| `\u002Ftools` | List the enabled tools |\n| `\u002Fexit`, `\u002Fquit` | Quit chat |\n\nNon-slash input is sent to the model as a chat message — there is no built-in\nshell (`ls`, `cd`, …) in the chat prompt. File operations happen through the\nagent's file tools in the workspace.\n\n## Configuration\n\n- Settings file: `~\u002F.nodetool\u002Fchat-settings.json` (persists provider + model)\n\n# Agent Capabilities\n\nBecause the agent loop is always active, the chat can:\n\n1. **Plan** — break tasks into steps\n2. **Use tools** — search, browse, file ops, code execution, media generation\n3. **Iterate** — execute steps, evaluate results, adapt\n4. **Run workflows** — trigger saved NodeTool workflows\n\n## Common Tools\n\n| Tool | Capability |\n|------|-----------|\n| `google_search` | Web search |\n| `browser` | Browse and extract web content |\n| `read_file` \u002F `write_file` \u002F `edit_file` | Workspace file ops |\n| `grep` \u002F `glob` | Search files |\n| `screenshot` | Capture a page screenshot |\n| `find_model` | Pick a model by capability |\n| `generate_image` \u002F `generate_video` \u002F `generate_speech` | Media generation |\n\nRestrict the set with `--tools a,b,c`; inspect the active set with `\u002Ftools`.\n\n# Global Chat\n\nGlobal Chat is the desktop app's built-in chat interface.\n\n## Features\n\n- Chat with any configured AI model (OpenAI, Anthropic, Gemini, local)\n- Multiple conversation threads\n- Standalone window (launch from the system tray)\n- Tools: web search, image generation, workflow execution\n- The same always-on agent loop as the CLI\n\n## Workflow Integration\n\n```\n1. Save a workflow in the NodeTool editor\n2. Open Global Chat\n3. Select the workflow from the workflow picker\n4. Chat naturally — the agent can invoke the workflow as a tool\n```\n\n# Typical Flows\n\n## Quick Question\n```bash\nnodetool chat -p openai -m gpt-5.4\n> What's the difference between FAISS and ChromaDB?\n```\n\n## Research Task\n```bash\nnodetool chat --tools google_search,browser,write_file\n> Research the top 5 TypeScript ORMs and write a comparison to comparison.md\n```\n\n## Code Generation\n```bash\nnodetool chat -p anthropic -m claude-sonnet-4-6 --tools write_file,read_file,grep\n> Create a Python script that processes CSV files and generates summary statistics\n```\n\n## Headless \u002F Programmatic Chat\n\nFor non-interactive chat, use the OpenAI-compatible Chat API on a running server\n(`nodetool serve`):\n\n```bash\ncurl -X POST http:\u002F\u002Flocalhost:7777\u002Fv1\u002Fchat\u002Fcompletions \\\n  -H \"Authorization: Bearer TOKEN\" \\\n  -d '{\"model\": \"gpt-5.4\", \"messages\": [{\"role\": \"user\", \"content\": \"Hello\"}]}'\n```\n\n# Common Pitfalls\n\n- **No provider configured**: store a key first (`nodetool secrets store OPENAI_API_KEY`). Providers without a key are greyed out and `\u002Fprovider \u003Cname>` refuses them.\n- **Wrong model ID**: switch with `\u002Fmodel \u003Cid>`; each provider's default is loaded when you switch providers.\n- **Expecting a shell**: bare commands like `ls` are sent to the model, not run. Use the agent's file tools or `--sandbox`.\n- **Looking for `\u002Fagent`**: agent mode is always on; there is no toggle.\n",{"name":5,"description":7},"main","4ef72a828b24c99c49109033c7ec504c34f3bd17",".claude\u002Fskills\u002Fnodetool-chat-cli",0,"https:\u002F\u002Fgithub.com\u002Fhanchenhao\u002Fai-canvas","https:\u002F\u002Fgithub.com\u002Fhanchenhao","2026-08-18 16:41:12",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add hanchenhao\u002Fai-canvas --skill nodetool-chat-cli",{"tool":36,"command":37},"bunx","bunx skills add hanchenhao\u002Fai-canvas --skill nodetool-chat-cli",{"tool":39,"command":40},"pnpm","pnpm dlx skills add hanchenhao\u002Fai-canvas --skill nodetool-chat-cli","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhanchenhao\u002Fai-canvas\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fnodetool-chat-cli\u002FSKILL.md",true,[],[45,52,59,66,73,80],{"skillNo":46,"name":47,"nameZh":6,"description":48,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":18},"01M7AE5NP5AWGV47WS3F37VPZ1","sandbox-zip","Read and write zip archives in a Code node or CodeAct action, with fflate running on the host under a 50 MB inflation cap","https:\u002F\u002Fgithub.com\u002Fhanchenhao\u002Fai-canvas\u002Fblob\u002Fmain\u002Fpackages\u002Fsandbox-packs\u002Fsandbox-zip\u002FSKILL.md",[],[],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":18},"01M7AE5JP0CG2S114Q246RC6MH","sandbox-yaml","Read and write YAML inside a Code node or CodeAct action, with js-yaml running in the guest","https:\u002F\u002Fgithub.com\u002Fhanchenhao\u002Fai-canvas\u002Fblob\u002Fmain\u002Fpackages\u002Fsandbox-packs\u002Fsandbox-yaml\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":18},"01M7AE5GJ9AV36WM1DPW1878VM","sandbox-xml","Parse XML feeds and sitemaps in a Code node or CodeAct action, with fast-xml-parser running on the host","https:\u002F\u002Fgithub.com\u002Fhanchenhao\u002Fai-canvas\u002Fblob\u002Fmain\u002Fpackages\u002Fsandbox-packs\u002Fsandbox-xml\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":18},"01M7AE5DMYDAGJW27G8KKTZ2BN","sandbox-xlsx","Read and write Excel workbooks in a Code node or CodeAct action, with exceljs running on the host","https:\u002F\u002Fgithub.com\u002Fhanchenhao\u002Fai-canvas\u002Fblob\u002Fmain\u002Fpackages\u002Fsandbox-packs\u002Fsandbox-xlsx\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":18},"01M7AE5BARJSFCT296SEMYDSJQ","sandbox-twilio","Send SMS and WhatsApp messages and look up numbers from a Code node or CodeAct action, with NodeTool's Twilio request builder running on the host","https:\u002F\u002Fgithub.com\u002Fhanchenhao\u002Fai-canvas\u002Fblob\u002Fmain\u002Fpackages\u002Fsandbox-packs\u002Fsandbox-twilio\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M7AE57C5APRDF96NB3G0WQMW","sandbox-tfjs","Classify and embed images, detect objects, and answer from a passage in a Code node or CodeAct action, with TensorFlow.js running on the host","https:\u002F\u002Fgithub.com\u002Fhanchenhao\u002Fai-canvas\u002Fblob\u002Fmain\u002Fpackages\u002Fsandbox-packs\u002Fsandbox-tfjs\u002FSKILL.md",[],[]]