[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69A42XAVDA303FJ21XTGC4W":3,"skill-same:01M69A42XAVDA303FJ21XTGC4W":55},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":27,"linkOnly":28,"markdownContent":29,"markdownBody":30,"frontMatter":31,"refName":32,"commitSha":33,"skillDirectory":34,"forksCount":35,"repositoryHtmlUrl":36,"repositoryHomepageUrl":6,"ownerHtmlUrl":37,"ownerBlogUrl":38,"ownerDescription":39,"updatedAt":40,"install":41,"resources":54},"01M69A42XAVDA303FJ21XTGC4W","add-ollama-tool",null,"Add Ollama MCP server so the container agent can call local models and optionally manage the Ollama model library.","microsoft\u002Famplifier-app-nanoclaw","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M69A31J3GTKVZDZZVPRQWWR5",5,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Famplifier-app-nanoclaw\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fadd-ollama-tool\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26],"add ollama tool","MCP","mcp server","2026-11-10 10:12:30",false,"---\nname: add-ollama-tool\ndescription: Add Ollama MCP server so the container agent can call local models and optionally manage the Ollama model library.\n---\n\n# Add Ollama Integration\n\nThis skill adds a stdio-based MCP server that exposes local Ollama models as tools for the container agent. Claude remains the orchestrator but can offload work to local models, and can optionally manage the model library directly.\n\nCore tools (always available):\n- `ollama_list_models` — list installed Ollama models with name, size, and family\n- `ollama_generate` — send a prompt to a specified model and return the response\n\nManagement tools (opt-in via `OLLAMA_ADMIN_TOOLS=true`):\n- `ollama_pull_model` — pull (download) a model from the Ollama registry\n- `ollama_delete_model` — delete a locally installed model to free disk space\n- `ollama_show_model` — show model details: modelfile, parameters, and architecture info\n- `ollama_list_running` — list models currently loaded in memory with memory usage and processor type\n\n## Phase 1: Pre-flight\n\n### Check if already applied\n\nCheck if `container\u002Fagent-runner\u002Fsrc\u002Follama-mcp-stdio.ts` exists. If it does, skip to Phase 3 (Configure).\n\n### Check prerequisites\n\nVerify Ollama is installed and running on the host:\n\n```bash\nollama list\n```\n\nIf Ollama is not installed, direct the user to https:\u002F\u002Follama.com\u002Fdownload.\n\nIf no models are installed, suggest pulling one:\n\n> You need at least one model. I recommend:\n>\n> ```bash\n> ollama pull gemma3:1b    # Small, fast (1GB)\n> ollama pull llama3.2     # Good general purpose (2GB)\n> ollama pull qwen3-coder:30b  # Best for code tasks (18GB)\n> ```\n\n## Phase 2: Apply Code Changes\n\n### Ensure upstream remote\n\n```bash\ngit remote -v\n```\n\nIf `upstream` is missing, add it:\n\n```bash\ngit remote add upstream https:\u002F\u002Fgithub.com\u002Fnanocoai\u002Fnanoclaw.git\n```\n\n### Merge the skill branch\n\n```bash\ngit fetch upstream skill\u002Follama-tool\ngit merge upstream\u002Fskill\u002Follama-tool\n```\n\nThis merges in:\n- `container\u002Fagent-runner\u002Fsrc\u002Follama-mcp-stdio.ts` (Ollama MCP server)\n- `scripts\u002Follama-watch.sh` (macOS notification watcher)\n- Ollama MCP config in `container\u002Fagent-runner\u002Fsrc\u002Findex.ts` (allowedTools + mcpServers)\n- `[OLLAMA]` log surfacing in `src\u002Fcontainer-runner.ts`\n- `OLLAMA_HOST` in `.env.example`\n\nIf the merge reports conflicts, resolve them by reading the conflicted files and understanding the intent of both sides.\n\n### Copy to per-group agent-runner\n\nExisting groups have a cached copy of the agent-runner source. Copy the new files:\n\n```bash\nfor dir in data\u002Fsessions\u002F*\u002Fagent-runner-src; do\n  cp container\u002Fagent-runner\u002Fsrc\u002Follama-mcp-stdio.ts \"$dir\u002F\"\n  cp container\u002Fagent-runner\u002Fsrc\u002Findex.ts \"$dir\u002F\"\ndone\n```\n\n### Validate code changes\n\n```bash\npnpm run build\n.\u002Fcontainer\u002Fbuild.sh\n```\n\nBuild must be clean before proceeding.\n\n## Phase 3: Configure\n\n### Enable model management tools (optional)\n\nAsk the user:\n\n> Would you like the agent to be able to **manage Ollama models** (pull, delete, inspect, list running)?\n>\n> - **Yes** — adds tools to pull new models, delete old ones, show model info, and check what's loaded in memory\n> - **No** — the agent can only list installed models and generate responses (you manage models yourself on the host)\n\nIf the user wants management tools, add to `.env`:\n\n```bash\nOLLAMA_ADMIN_TOOLS=true\n```\n\nIf they decline (or don't answer), do not add the variable — management tools will be disabled by default.\n\n### Set Ollama host (optional)\n\nBy default, the MCP server connects to `http:\u002F\u002Fhost.docker.internal:11434` (Docker Desktop) with a fallback to `localhost`. To use a custom Ollama host, add to `.env`:\n\n```bash\nOLLAMA_HOST=http:\u002F\u002Fyour-ollama-host:11434\n```\n\n### Restart the service\n\nRun from your NanoClaw project root:\n\n```bash\nsource setup\u002Flib\u002Finstall-slug.sh\nlaunchctl kickstart -k gui\u002F$(id -u)\u002F$(launchd_label)  # macOS\nsystemctl --user restart $(systemd_unit)              # Linux\n```\n\n## Phase 4: Verify\n\n### Test inference\n\nTell the user:\n\n> Send a message like: \"use ollama to tell me the capital of France\"\n>\n> The agent should use `ollama_list_models` to find available models, then `ollama_generate` to get a response.\n\n### Test model management (if enabled)\n\nIf `OLLAMA_ADMIN_TOOLS=true` was set, tell the user:\n\n> Send a message like: \"pull the gemma3:1b model\" or \"which ollama models are currently loaded in memory?\"\n>\n> The agent should call `ollama_pull_model` or `ollama_list_running` respectively.\n\n### Monitor activity (optional)\n\nRun the watcher script for macOS notifications when Ollama is used:\n\n```bash\n.\u002Fscripts\u002Follama-watch.sh\n```\n\n### Check logs if needed\n\n```bash\ntail -f logs\u002Fnanoclaw.log | grep -i ollama\n```\n\nLook for:\n- `[OLLAMA] >>> Generating` — generation started\n- `[OLLAMA] \u003C\u003C\u003C Done` — generation completed\n- `[OLLAMA] Pulling model:` — pull in progress (management tools)\n- `[OLLAMA] Deleted:` — model removed (management tools)\n\n## Troubleshooting\n\n### Agent says \"Ollama is not installed\"\n\nThe agent is trying to run `ollama` CLI inside the container instead of using the MCP tools. This means:\n1. The MCP server wasn't registered — check `container\u002Fagent-runner\u002Fsrc\u002Findex.ts` has the `ollama` entry in `mcpServers`\n2. The per-group source wasn't updated — re-copy files (see Phase 2)\n3. The container wasn't rebuilt — run `.\u002Fcontainer\u002Fbuild.sh`\n\n### \"Failed to connect to Ollama\"\n\n1. Verify Ollama is running: `ollama list`\n2. Check Docker can reach the host: `docker run --rm curlimages\u002Fcurl curl -s http:\u002F\u002Fhost.docker.internal:11434\u002Fapi\u002Ftags`\n3. If using a custom host, check `OLLAMA_HOST` in `.env`\n\n### Agent doesn't use Ollama tools\n\nThe agent may not know about the tools. Try being explicit: \"use the ollama_generate tool with gemma3:1b to answer: ...\"\n\n### `ollama_pull_model` times out on large models\n\nLarge models (7B+) can take several minutes. The tool uses `stream: false` so it blocks until complete — this is intentional. For very large pulls, use the host CLI directly: `ollama pull \u003Cmodel>`\n\n### Management tools not showing up\n\nEnsure `OLLAMA_ADMIN_TOOLS=true` is set in `.env` and the service was restarted after adding it.\n","# Add Ollama Integration\n\nThis skill adds a stdio-based MCP server that exposes local Ollama models as tools for the container agent. Claude remains the orchestrator but can offload work to local models, and can optionally manage the model library directly.\n\nCore tools (always available):\n- `ollama_list_models` — list installed Ollama models with name, size, and family\n- `ollama_generate` — send a prompt to a specified model and return the response\n\nManagement tools (opt-in via `OLLAMA_ADMIN_TOOLS=true`):\n- `ollama_pull_model` — pull (download) a model from the Ollama registry\n- `ollama_delete_model` — delete a locally installed model to free disk space\n- `ollama_show_model` — show model details: modelfile, parameters, and architecture info\n- `ollama_list_running` — list models currently loaded in memory with memory usage and processor type\n\n## Phase 1: Pre-flight\n\n### Check if already applied\n\nCheck if `container\u002Fagent-runner\u002Fsrc\u002Follama-mcp-stdio.ts` exists. If it does, skip to Phase 3 (Configure).\n\n### Check prerequisites\n\nVerify Ollama is installed and running on the host:\n\n```bash\nollama list\n```\n\nIf Ollama is not installed, direct the user to https:\u002F\u002Follama.com\u002Fdownload.\n\nIf no models are installed, suggest pulling one:\n\n> You need at least one model. I recommend:\n>\n> ```bash\n> ollama pull gemma3:1b    # Small, fast (1GB)\n> ollama pull llama3.2     # Good general purpose (2GB)\n> ollama pull qwen3-coder:30b  # Best for code tasks (18GB)\n> ```\n\n## Phase 2: Apply Code Changes\n\n### Ensure upstream remote\n\n```bash\ngit remote -v\n```\n\nIf `upstream` is missing, add it:\n\n```bash\ngit remote add upstream https:\u002F\u002Fgithub.com\u002Fnanocoai\u002Fnanoclaw.git\n```\n\n### Merge the skill branch\n\n```bash\ngit fetch upstream skill\u002Follama-tool\ngit merge upstream\u002Fskill\u002Follama-tool\n```\n\nThis merges in:\n- `container\u002Fagent-runner\u002Fsrc\u002Follama-mcp-stdio.ts` (Ollama MCP server)\n- `scripts\u002Follama-watch.sh` (macOS notification watcher)\n- Ollama MCP config in `container\u002Fagent-runner\u002Fsrc\u002Findex.ts` (allowedTools + mcpServers)\n- `[OLLAMA]` log surfacing in `src\u002Fcontainer-runner.ts`\n- `OLLAMA_HOST` in `.env.example`\n\nIf the merge reports conflicts, resolve them by reading the conflicted files and understanding the intent of both sides.\n\n### Copy to per-group agent-runner\n\nExisting groups have a cached copy of the agent-runner source. Copy the new files:\n\n```bash\nfor dir in data\u002Fsessions\u002F*\u002Fagent-runner-src; do\n  cp container\u002Fagent-runner\u002Fsrc\u002Follama-mcp-stdio.ts \"$dir\u002F\"\n  cp container\u002Fagent-runner\u002Fsrc\u002Findex.ts \"$dir\u002F\"\ndone\n```\n\n### Validate code changes\n\n```bash\npnpm run build\n.\u002Fcontainer\u002Fbuild.sh\n```\n\nBuild must be clean before proceeding.\n\n## Phase 3: Configure\n\n### Enable model management tools (optional)\n\nAsk the user:\n\n> Would you like the agent to be able to **manage Ollama models** (pull, delete, inspect, list running)?\n>\n> - **Yes** — adds tools to pull new models, delete old ones, show model info, and check what's loaded in memory\n> - **No** — the agent can only list installed models and generate responses (you manage models yourself on the host)\n\nIf the user wants management tools, add to `.env`:\n\n```bash\nOLLAMA_ADMIN_TOOLS=true\n```\n\nIf they decline (or don't answer), do not add the variable — management tools will be disabled by default.\n\n### Set Ollama host (optional)\n\nBy default, the MCP server connects to `http:\u002F\u002Fhost.docker.internal:11434` (Docker Desktop) with a fallback to `localhost`. To use a custom Ollama host, add to `.env`:\n\n```bash\nOLLAMA_HOST=http:\u002F\u002Fyour-ollama-host:11434\n```\n\n### Restart the service\n\nRun from your NanoClaw project root:\n\n```bash\nsource setup\u002Flib\u002Finstall-slug.sh\nlaunchctl kickstart -k gui\u002F$(id -u)\u002F$(launchd_label)  # macOS\nsystemctl --user restart $(systemd_unit)              # Linux\n```\n\n## Phase 4: Verify\n\n### Test inference\n\nTell the user:\n\n> Send a message like: \"use ollama to tell me the capital of France\"\n>\n> The agent should use `ollama_list_models` to find available models, then `ollama_generate` to get a response.\n\n### Test model management (if enabled)\n\nIf `OLLAMA_ADMIN_TOOLS=true` was set, tell the user:\n\n> Send a message like: \"pull the gemma3:1b model\" or \"which ollama models are currently loaded in memory?\"\n>\n> The agent should call `ollama_pull_model` or `ollama_list_running` respectively.\n\n### Monitor activity (optional)\n\nRun the watcher script for macOS notifications when Ollama is used:\n\n```bash\n.\u002Fscripts\u002Follama-watch.sh\n```\n\n### Check logs if needed\n\n```bash\ntail -f logs\u002Fnanoclaw.log | grep -i ollama\n```\n\nLook for:\n- `[OLLAMA] >>> Generating` — generation started\n- `[OLLAMA] \u003C\u003C\u003C Done` — generation completed\n- `[OLLAMA] Pulling model:` — pull in progress (management tools)\n- `[OLLAMA] Deleted:` — model removed (management tools)\n\n## Troubleshooting\n\n### Agent says \"Ollama is not installed\"\n\nThe agent is trying to run `ollama` CLI inside the container instead of using the MCP tools. This means:\n1. The MCP server wasn't registered — check `container\u002Fagent-runner\u002Fsrc\u002Findex.ts` has the `ollama` entry in `mcpServers`\n2. The per-group source wasn't updated — re-copy files (see Phase 2)\n3. The container wasn't rebuilt — run `.\u002Fcontainer\u002Fbuild.sh`\n\n### \"Failed to connect to Ollama\"\n\n1. Verify Ollama is running: `ollama list`\n2. Check Docker can reach the host: `docker run --rm curlimages\u002Fcurl curl -s http:\u002F\u002Fhost.docker.internal:11434\u002Fapi\u002Ftags`\n3. If using a custom host, check `OLLAMA_HOST` in `.env`\n\n### Agent doesn't use Ollama tools\n\nThe agent may not know about the tools. Try being explicit: \"use the ollama_generate tool with gemma3:1b to answer: ...\"\n\n### `ollama_pull_model` times out on large models\n\nLarge models (7B+) can take several minutes. The tool uses `stream: false` so it blocks until complete — this is intentional. For very large pulls, use the host CLI directly: `ollama pull \u003Cmodel>`\n\n### Management tools not showing up\n\nEnsure `OLLAMA_ADMIN_TOOLS=true` is set in `.env` and the service was restarted after adding it.\n",{"name":5,"description":7},"main","85a2d934766d21e4696ac1b00157179f28bca9e3",".claude\u002Fskills\u002Fadd-ollama-tool",2,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Famplifier-app-nanoclaw","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-10-30 04:24:16",{"source":8,"skillName":5,"commands":42,"prompt":52,"zipAvailable":53},[43,46,49],{"tool":44,"command":45},"npx","npx skills add microsoft\u002Famplifier-app-nanoclaw --skill add-ollama-tool",{"tool":47,"command":48},"bunx","bunx skills add microsoft\u002Famplifier-app-nanoclaw --skill add-ollama-tool",{"tool":50,"command":51},"pnpm","pnpm dlx skills add microsoft\u002Famplifier-app-nanoclaw --skill add-ollama-tool","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Famplifier-app-nanoclaw\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fadd-ollama-tool\u002FSKILL.md",true,[],[56,65,72,83,95,105],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":27},"01M69A6E27JZN10H82TZ2GMC3A","whatsapp-formatting","Format messages for WhatsApp, including mentions that render as real WhatsApp tags. Use when responding in a WhatsApp conversation (platform_id \u002F chatJid ends with @s.whatsapp.net or @g.us).","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Famplifier-app-nanoclaw\u002Fblob\u002Fmain\u002Fcontainer\u002Fskills\u002Fwhatsapp-formatting\u002FSKILL.md",[],[63,64],"whatsapp","whatsapp formatting",{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":27},"01M69A6CGJ968RNVGYTRSWZKWB","welcome","Introduce yourself to a newly connected channel. Triggered automatically when a channel is first wired. Send a friendly greeting and brief overview of what you can do.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Famplifier-app-nanoclaw\u002Fblob\u002Fmain\u002Fcontainer\u002Fskills\u002Fwelcome\u002FSKILL.md",[],[67],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":27},"01M69A6ADX690STSN63WKRD37K","vercel-cli","Deploy apps to Vercel. Use when asked to deploy, ship, or publish a web application, or manage Vercel projects, domains, and environment variables.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Famplifier-app-nanoclaw\u002Fblob\u002Fmain\u002Fcontainer\u002Fskills\u002Fvercel-cli\u002FSKILL.md",[],[79,80,81,82],"cli","vercel cli","web","deploy",{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":92,"publishedAt":27},"01M69A68WJ94V4MXGXGK9T0QG7","slack-formatting","Format messages for Slack using mrkdwn syntax. Use when responding to Slack channels (folder starts with \"slack_\" or JID contains slack identifiers).","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Famplifier-app-nanoclaw\u002Fblob\u002Fmain\u002Fcontainer\u002Fskills\u002Fslack-formatting\u002FSKILL.md",[89],{"categoryNo":90,"categoryName":91,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000005","邮件与沟通",[93,94],"slack","slack formatting",{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":102,"publishedAt":27},"01M69A673Z17TDXK3DBC5YJFM7","self-customize","Customize your own agent — add capabilities, install packages, add MCP servers, edit code or CLAUDE.md. Use when the user asks you to add a feature, install a tool, or modify how you work. For non-trivial code changes, delegate to a builder agent via create_agent.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Famplifier-app-nanoclaw\u002Fblob\u002Fmain\u002Fcontainer\u002Fskills\u002Fself-customize\u002FSKILL.md",[101],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[103,104,25],"customize","self customize",{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":112,"publishedAt":27},"01M69A657JFNEG45Z1Y05BVK5R","onecli-gateway","OneCLI Gateway: transparent HTTPS proxy that injects stored credentials into outbound calls. You MUST use this skill when the user asks you to read emails, check calendar, access GitHub repos, create issues, check Stripe payments, or interact with ANY external service or API. Do NOT use browser extensions or OAuth CLI tools. Make HTTP requests directly; the gateway injects credentials automatically.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Famplifier-app-nanoclaw\u002Fblob\u002Fmain\u002Fcontainer\u002Fskills\u002Fonecli-gateway\u002FSKILL.md",[111],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[113,79,114,115],"onecli gateway","github","repos"]