[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DFYGZMX0JYX1RX85N2T82B":3,"skill-same:01M6DFYGZMX0JYX1RX85N2T82B":63},{"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":22,"publishedAt":32,"linkOnly":33,"markdownContent":34,"markdownBody":35,"frontMatter":36,"refName":37,"commitSha":38,"skillDirectory":39,"forksCount":13,"repositoryHtmlUrl":40,"repositoryHomepageUrl":6,"ownerHtmlUrl":41,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":42,"install":43,"resources":56},"01M6DFYGZMX0JYX1RX85N2T82B","add-parallel",null,"Add Parallel AI integration to NanoDex for quick web search and deeper research workflows.","mbaker95\u002Fnanodex","mbaker95","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F11398294?v=4","01M6DFXVNAJHZG78Y2D700Y6V3","01M6DFXVTTW83QGKTJ9FJ5YCH5",0,"MIT","https:\u002F\u002Fgithub.com\u002Fmbaker95\u002Fnanodex\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fadd-parallel\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31],"add parallel","parallel","research","web","workflows","search","integration","web search","deeper","2026-11-10 10:12:30",false,"---\nname: add-parallel\ndescription: Add Parallel AI integration to NanoDex for quick web search and deeper research workflows.\n---\n\n# Add Parallel AI Integration\n\nAdds Parallel AI MCP integration to NanoDex for advanced web research capabilities.\n\n## What This Adds\n\n- **Quick Search** - Fast web lookups using Parallel Search API (free to use)\n- **Deep Research** - Comprehensive analysis using Parallel Task API (asks permission)\n- **Non-blocking Design** - Uses NanoDex scheduler for result polling (no container blocking)\n\n## Prerequisites\n\nUser must have:\n1. Parallel AI API key from https:\u002F\u002Fplatform.parallel.ai\n2. NanoDex already set up and running\n3. Docker installed and running\n\n## Implementation Steps\n\nRun all steps automatically. Only pause for user input when explicitly needed.\n\n### 1. Get Parallel AI API Key\n\nAsk the user directly whether they already have a Parallel AI API key or want help creating one.\n\n**If they have one:**\nCollect it now.\n\n**If they need one:**\nTell them:\n> 1. Go to https:\u002F\u002Fplatform.parallel.ai\n> 2. Sign up or log in\n> 3. Navigate to API Keys section\n> 4. Create a new API key\n> 5. Copy the key and paste it here\n\nWait for the API key.\n\n### 2. Add API Key to Environment\n\nAdd `PARALLEL_API_KEY` to `.env`:\n\n```bash\n# Check if .env exists, create if not\nif [ ! -f .env ]; then\n    touch .env\nfi\n\n# Add PARALLEL_API_KEY if not already present\nif ! grep -q \"PARALLEL_API_KEY=\" .env; then\n    echo \"PARALLEL_API_KEY=${API_KEY_FROM_USER}\" >> .env\n    echo \"✓ Added PARALLEL_API_KEY to .env\"\nelse\n    # Update existing key\n    sed -i.bak \"s\u002F^PARALLEL_API_KEY=.*\u002FPARALLEL_API_KEY=${API_KEY_FROM_USER}\u002F\" .env\n    echo \"✓ Updated PARALLEL_API_KEY in .env\"\nfi\n```\n\nVerify:\n```bash\ngrep \"PARALLEL_API_KEY\" .env | head -c 50\n```\n\n### 3. Update Container Runner\n\nAdd `PARALLEL_API_KEY` to allowed environment variables in `src\u002Fcontainer-runner.ts`:\n\nFind the line:\n```typescript\nconst allowedVars = ['CLAUDE_CODE_OAUTH_TOKEN', 'ANTHROPIC_API_KEY'];\n```\n\nReplace with:\n```typescript\nconst allowedVars = ['CLAUDE_CODE_OAUTH_TOKEN', 'ANTHROPIC_API_KEY', 'PARALLEL_API_KEY'];\n```\n\n### 4. Configure MCP Servers in Agent Runner\n\nUpdate `container\u002Fagent-runner\u002Fsrc\u002Findex.ts`:\n\nFind the section where `mcpServers` is configured (around line 237-252):\n```typescript\nconst mcpServers: Record\u003Cstring, any> = {\n  nanoclaw: ipcMcp\n};\n```\n\nAdd Parallel AI MCP servers after the nanoclaw server:\n```typescript\nconst mcpServers: Record\u003Cstring, any> = {\n  nanoclaw: ipcMcp\n};\n\n\u002F\u002F Add Parallel AI MCP servers if API key is available\nconst parallelApiKey = process.env.PARALLEL_API_KEY;\nif (parallelApiKey) {\n  mcpServers['parallel-search'] = {\n    type: 'http',  \u002F\u002F REQUIRED: Must specify type for HTTP MCP servers\n    url: 'https:\u002F\u002Fsearch-mcp.parallel.ai\u002Fmcp',\n    headers: {\n      'Authorization': `Bearer ${parallelApiKey}`\n    }\n  };\n  mcpServers['parallel-task'] = {\n    type: 'http',  \u002F\u002F REQUIRED: Must specify type for HTTP MCP servers  \n    url: 'https:\u002F\u002Ftask-mcp.parallel.ai\u002Fmcp',\n    headers: {\n      'Authorization': `Bearer ${parallelApiKey}`\n    }\n  };\n  log('Parallel AI MCP servers configured');\n} else {\n  log('PARALLEL_API_KEY not set, skipping Parallel AI integration');\n}\n```\n\nAlso update the `allowedTools` array to include Parallel MCP tools (around line 242-248):\n```typescript\nallowedTools: [\n  'Bash',\n  'Read', 'Write', 'Edit', 'Glob', 'Grep',\n  'WebSearch', 'WebFetch',\n  'mcp__nanoclaw__*',\n  'mcp__parallel-search__*',\n  'mcp__parallel-task__*'\n],\n```\n\n### 5. Add Usage Instructions to AGENTS.md\n\nAdd Parallel AI usage instructions to `groups\u002Fmain\u002FAGENTS.md`:\n\nFind the \"## What You Can Do\" section and add after the existing bullet points:\n```markdown\n- Use Parallel AI for web research and deep learning tasks\n```\n\nThen add a new section after \"## What You Can Do\":\n```markdown\n## Web Research Tools\n\nYou have access to two Parallel AI research tools:\n\n### Quick Web Search (`mcp__parallel-search__search`)\n**When to use:** Freely use for factual lookups, current events, definitions, recent information, or verifying facts.\n\n**Examples:**\n- \"Who invented the transistor?\"\n- \"What's the latest news about quantum computing?\"\n- \"When was the UN founded?\"\n- \"What are the top programming languages in 2026?\"\n\n**Speed:** Fast (2-5 seconds)\n**Cost:** Low\n**Permission:** Not needed - use whenever it helps answer the question\n\n### Deep Research (`mcp__parallel-task__create_task_run`)\n**When to use:** Comprehensive analysis, learning about complex topics, comparing concepts, historical overviews, or structured research.\n\n**Examples:**\n- \"Explain the development of quantum mechanics from 1900-1930\"\n- \"Compare the literary styles of Hemingway and Faulkner\"\n- \"Research the evolution of jazz from bebop to fusion\"\n- \"Analyze the causes of the French Revolution\"\n\n**Speed:** Slower (1-20 minutes depending on depth)\n**Cost:** Higher (varies by processor tier)\n**Permission:** Always ask the user explicitly before using this tool\n\n**How to ask permission:**\n```\nI can do deep research on [topic] using Parallel's Task API. This will take 2-5 minutes and provide comprehensive analysis with citations. Should I proceed?\n```\n\n**After permission - DO NOT BLOCK! Use scheduler instead:**\n\n1. Create the task using `mcp__parallel-task__create_task_run`\n2. Get the `run_id` from the response\n3. Create a polling scheduled task using `mcp__nanodex__schedule_task`:\n   ```\n   Prompt: \"Check Parallel AI task run [run_id] and send results when ready.\n\n   1. Use the Parallel Task MCP to check the task status\n   2. If status is 'completed', extract the results\n   3. Send results to user with mcp__nanodex__send_message\n   4. Use the NanoDex task tools to mark this task as done\n\n   If status is still 'running' or 'pending', do nothing (task will run again in 30s).\n   If status is 'failed', send error message and complete the task.\"\n\n   Schedule: interval every 30 seconds\n   Context mode: isolated\n   ```\n4. Send acknowledgment with tracking link\n5. Exit immediately - scheduler handles the rest\n\n### Choosing Between Them\n\n**Use Search when:**\n- Question needs a quick fact or recent information\n- Simple definition or clarification\n- Verifying specific details\n- Current events or news\n\n**Use Deep Research (with permission) when:**\n- User wants to learn about a complex topic\n- Question requires analysis or comparison\n- Historical context or evolution of concepts\n- Structured, comprehensive understanding needed\n- User explicitly asks to \"research\" or \"explain in depth\"\n\n**Default behavior:** Prefer search for most questions. Only suggest deep research when the topic genuinely requires comprehensive analysis.\n```\n\n### 6. Rebuild Container\n\nBuild the container with updated agent runner:\n\n```bash\n.\u002Fcontainer\u002Fbuild.sh\n```\n\nVerify the build:\n```bash\necho '{}' | docker run -i --entrypoint \u002Fbin\u002Fecho nanodex-agent:latest \"Container OK\"\n```\n\n### 7. Restart Service\n\nRebuild the main app and restart:\n\n```bash\nnpm run build\nlaunchctl kickstart -k gui\u002F$(id -u)\u002Fcom.nanodex  # macOS\n# Linux: systemctl --user restart nanodex\n```\n\nWait 3 seconds for service to start, then verify:\n```bash\nsleep 3\nlaunchctl list | grep nanodex  # macOS\n# Linux: systemctl --user status nanodex\n```\n\n### 8. Test Integration\n\nTell the user to test:\n> Send a message to your assistant: `@[YourAssistantName] what's the latest news about AI?`\n>\n> The assistant should use Parallel Search API to find current information.\n>\n> Then try: `@[YourAssistantName] can you research the history of artificial intelligence?`\n>\n> The assistant should ask for permission before using the Task API.\n\nCheck logs to verify MCP servers loaded:\n```bash\ntail -20 logs\u002Fnanodex.log\n```\n\nLook for: `Parallel AI MCP servers configured`\n\n## Troubleshooting\n\n**Container hangs or times out:**\n- Check that `type: 'http'` is specified in MCP server config\n- Verify API key is correct in .env\n- Check container logs: `cat groups\u002Fmain\u002Flogs\u002Fcontainer-*.log | tail -50`\n\n**MCP servers not loading:**\n- Ensure PARALLEL_API_KEY is in .env\n- Verify container-runner.ts includes PARALLEL_API_KEY in allowedVars\n- Check agent-runner logs for \"Parallel AI MCP servers configured\" message\n\n**Task polling not working:**\n- Verify scheduled task was created: `sqlite3 store\u002Fmessages.db \"SELECT * FROM scheduled_tasks\"`\n- Check task runs: `tail -f logs\u002Fnanodex.log | grep \"scheduled task\"`\n- Ensure task prompt includes proper Parallel MCP tool names\n\n## Uninstalling\n\nTo remove Parallel AI integration:\n\n1. Remove from .env: `sed -i.bak '\u002FPARALLEL_API_KEY\u002Fd' .env`\n2. Revert changes to container-runner.ts and agent-runner\u002Fsrc\u002Findex.ts\n3. Remove Web Research Tools section from groups\u002Fmain\u002FAGENTS.md\n4. Rebuild: `.\u002Fcontainer\u002Fbuild.sh && npm run build`\n5. Restart: `launchctl kickstart -k gui\u002F$(id -u)\u002Fcom.nanodex` (macOS) or `systemctl --user restart nanodex` (Linux)\n","# Add Parallel AI Integration\n\nAdds Parallel AI MCP integration to NanoDex for advanced web research capabilities.\n\n## What This Adds\n\n- **Quick Search** - Fast web lookups using Parallel Search API (free to use)\n- **Deep Research** - Comprehensive analysis using Parallel Task API (asks permission)\n- **Non-blocking Design** - Uses NanoDex scheduler for result polling (no container blocking)\n\n## Prerequisites\n\nUser must have:\n1. Parallel AI API key from https:\u002F\u002Fplatform.parallel.ai\n2. NanoDex already set up and running\n3. Docker installed and running\n\n## Implementation Steps\n\nRun all steps automatically. Only pause for user input when explicitly needed.\n\n### 1. Get Parallel AI API Key\n\nAsk the user directly whether they already have a Parallel AI API key or want help creating one.\n\n**If they have one:**\nCollect it now.\n\n**If they need one:**\nTell them:\n> 1. Go to https:\u002F\u002Fplatform.parallel.ai\n> 2. Sign up or log in\n> 3. Navigate to API Keys section\n> 4. Create a new API key\n> 5. Copy the key and paste it here\n\nWait for the API key.\n\n### 2. Add API Key to Environment\n\nAdd `PARALLEL_API_KEY` to `.env`:\n\n```bash\n# Check if .env exists, create if not\nif [ ! -f .env ]; then\n    touch .env\nfi\n\n# Add PARALLEL_API_KEY if not already present\nif ! grep -q \"PARALLEL_API_KEY=\" .env; then\n    echo \"PARALLEL_API_KEY=${API_KEY_FROM_USER}\" >> .env\n    echo \"✓ Added PARALLEL_API_KEY to .env\"\nelse\n    # Update existing key\n    sed -i.bak \"s\u002F^PARALLEL_API_KEY=.*\u002FPARALLEL_API_KEY=${API_KEY_FROM_USER}\u002F\" .env\n    echo \"✓ Updated PARALLEL_API_KEY in .env\"\nfi\n```\n\nVerify:\n```bash\ngrep \"PARALLEL_API_KEY\" .env | head -c 50\n```\n\n### 3. Update Container Runner\n\nAdd `PARALLEL_API_KEY` to allowed environment variables in `src\u002Fcontainer-runner.ts`:\n\nFind the line:\n```typescript\nconst allowedVars = ['CLAUDE_CODE_OAUTH_TOKEN', 'ANTHROPIC_API_KEY'];\n```\n\nReplace with:\n```typescript\nconst allowedVars = ['CLAUDE_CODE_OAUTH_TOKEN', 'ANTHROPIC_API_KEY', 'PARALLEL_API_KEY'];\n```\n\n### 4. Configure MCP Servers in Agent Runner\n\nUpdate `container\u002Fagent-runner\u002Fsrc\u002Findex.ts`:\n\nFind the section where `mcpServers` is configured (around line 237-252):\n```typescript\nconst mcpServers: Record\u003Cstring, any> = {\n  nanoclaw: ipcMcp\n};\n```\n\nAdd Parallel AI MCP servers after the nanoclaw server:\n```typescript\nconst mcpServers: Record\u003Cstring, any> = {\n  nanoclaw: ipcMcp\n};\n\n\u002F\u002F Add Parallel AI MCP servers if API key is available\nconst parallelApiKey = process.env.PARALLEL_API_KEY;\nif (parallelApiKey) {\n  mcpServers['parallel-search'] = {\n    type: 'http',  \u002F\u002F REQUIRED: Must specify type for HTTP MCP servers\n    url: 'https:\u002F\u002Fsearch-mcp.parallel.ai\u002Fmcp',\n    headers: {\n      'Authorization': `Bearer ${parallelApiKey}`\n    }\n  };\n  mcpServers['parallel-task'] = {\n    type: 'http',  \u002F\u002F REQUIRED: Must specify type for HTTP MCP servers  \n    url: 'https:\u002F\u002Ftask-mcp.parallel.ai\u002Fmcp',\n    headers: {\n      'Authorization': `Bearer ${parallelApiKey}`\n    }\n  };\n  log('Parallel AI MCP servers configured');\n} else {\n  log('PARALLEL_API_KEY not set, skipping Parallel AI integration');\n}\n```\n\nAlso update the `allowedTools` array to include Parallel MCP tools (around line 242-248):\n```typescript\nallowedTools: [\n  'Bash',\n  'Read', 'Write', 'Edit', 'Glob', 'Grep',\n  'WebSearch', 'WebFetch',\n  'mcp__nanoclaw__*',\n  'mcp__parallel-search__*',\n  'mcp__parallel-task__*'\n],\n```\n\n### 5. Add Usage Instructions to AGENTS.md\n\nAdd Parallel AI usage instructions to `groups\u002Fmain\u002FAGENTS.md`:\n\nFind the \"## What You Can Do\" section and add after the existing bullet points:\n```markdown\n- Use Parallel AI for web research and deep learning tasks\n```\n\nThen add a new section after \"## What You Can Do\":\n```markdown\n## Web Research Tools\n\nYou have access to two Parallel AI research tools:\n\n### Quick Web Search (`mcp__parallel-search__search`)\n**When to use:** Freely use for factual lookups, current events, definitions, recent information, or verifying facts.\n\n**Examples:**\n- \"Who invented the transistor?\"\n- \"What's the latest news about quantum computing?\"\n- \"When was the UN founded?\"\n- \"What are the top programming languages in 2026?\"\n\n**Speed:** Fast (2-5 seconds)\n**Cost:** Low\n**Permission:** Not needed - use whenever it helps answer the question\n\n### Deep Research (`mcp__parallel-task__create_task_run`)\n**When to use:** Comprehensive analysis, learning about complex topics, comparing concepts, historical overviews, or structured research.\n\n**Examples:**\n- \"Explain the development of quantum mechanics from 1900-1930\"\n- \"Compare the literary styles of Hemingway and Faulkner\"\n- \"Research the evolution of jazz from bebop to fusion\"\n- \"Analyze the causes of the French Revolution\"\n\n**Speed:** Slower (1-20 minutes depending on depth)\n**Cost:** Higher (varies by processor tier)\n**Permission:** Always ask the user explicitly before using this tool\n\n**How to ask permission:**\n```\nI can do deep research on [topic] using Parallel's Task API. This will take 2-5 minutes and provide comprehensive analysis with citations. Should I proceed?\n```\n\n**After permission - DO NOT BLOCK! Use scheduler instead:**\n\n1. Create the task using `mcp__parallel-task__create_task_run`\n2. Get the `run_id` from the response\n3. Create a polling scheduled task using `mcp__nanodex__schedule_task`:\n   ```\n   Prompt: \"Check Parallel AI task run [run_id] and send results when ready.\n\n   1. Use the Parallel Task MCP to check the task status\n   2. If status is 'completed', extract the results\n   3. Send results to user with mcp__nanodex__send_message\n   4. Use the NanoDex task tools to mark this task as done\n\n   If status is still 'running' or 'pending', do nothing (task will run again in 30s).\n   If status is 'failed', send error message and complete the task.\"\n\n   Schedule: interval every 30 seconds\n   Context mode: isolated\n   ```\n4. Send acknowledgment with tracking link\n5. Exit immediately - scheduler handles the rest\n\n### Choosing Between Them\n\n**Use Search when:**\n- Question needs a quick fact or recent information\n- Simple definition or clarification\n- Verifying specific details\n- Current events or news\n\n**Use Deep Research (with permission) when:**\n- User wants to learn about a complex topic\n- Question requires analysis or comparison\n- Historical context or evolution of concepts\n- Structured, comprehensive understanding needed\n- User explicitly asks to \"research\" or \"explain in depth\"\n\n**Default behavior:** Prefer search for most questions. Only suggest deep research when the topic genuinely requires comprehensive analysis.\n```\n\n### 6. Rebuild Container\n\nBuild the container with updated agent runner:\n\n```bash\n.\u002Fcontainer\u002Fbuild.sh\n```\n\nVerify the build:\n```bash\necho '{}' | docker run -i --entrypoint \u002Fbin\u002Fecho nanodex-agent:latest \"Container OK\"\n```\n\n### 7. Restart Service\n\nRebuild the main app and restart:\n\n```bash\nnpm run build\nlaunchctl kickstart -k gui\u002F$(id -u)\u002Fcom.nanodex  # macOS\n# Linux: systemctl --user restart nanodex\n```\n\nWait 3 seconds for service to start, then verify:\n```bash\nsleep 3\nlaunchctl list | grep nanodex  # macOS\n# Linux: systemctl --user status nanodex\n```\n\n### 8. Test Integration\n\nTell the user to test:\n> Send a message to your assistant: `@[YourAssistantName] what's the latest news about AI?`\n>\n> The assistant should use Parallel Search API to find current information.\n>\n> Then try: `@[YourAssistantName] can you research the history of artificial intelligence?`\n>\n> The assistant should ask for permission before using the Task API.\n\nCheck logs to verify MCP servers loaded:\n```bash\ntail -20 logs\u002Fnanodex.log\n```\n\nLook for: `Parallel AI MCP servers configured`\n\n## Troubleshooting\n\n**Container hangs or times out:**\n- Check that `type: 'http'` is specified in MCP server config\n- Verify API key is correct in .env\n- Check container logs: `cat groups\u002Fmain\u002Flogs\u002Fcontainer-*.log | tail -50`\n\n**MCP servers not loading:**\n- Ensure PARALLEL_API_KEY is in .env\n- Verify container-runner.ts includes PARALLEL_API_KEY in allowedVars\n- Check agent-runner logs for \"Parallel AI MCP servers configured\" message\n\n**Task polling not working:**\n- Verify scheduled task was created: `sqlite3 store\u002Fmessages.db \"SELECT * FROM scheduled_tasks\"`\n- Check task runs: `tail -f logs\u002Fnanodex.log | grep \"scheduled task\"`\n- Ensure task prompt includes proper Parallel MCP tool names\n\n## Uninstalling\n\nTo remove Parallel AI integration:\n\n1. Remove from .env: `sed -i.bak '\u002FPARALLEL_API_KEY\u002Fd' .env`\n2. Revert changes to container-runner.ts and agent-runner\u002Fsrc\u002Findex.ts\n3. Remove Web Research Tools section from groups\u002Fmain\u002FAGENTS.md\n4. Rebuild: `.\u002Fcontainer\u002Fbuild.sh && npm run build`\n5. Restart: `launchctl kickstart -k gui\u002F$(id -u)\u002Fcom.nanodex` (macOS) or `systemctl --user restart nanodex` (Linux)\n",{"name":5,"description":7},"main","b6b2f4d4a0c7243409d1684119a6772629bfeba6",".agents\u002Fskills\u002Fadd-parallel","https:\u002F\u002Fgithub.com\u002Fmbaker95\u002Fnanodex","https:\u002F\u002Fgithub.com\u002Fmbaker95","2026-03-12 23:02:12",{"source":8,"skillName":5,"commands":44,"prompt":54,"zipAvailable":55},[45,48,51],{"tool":46,"command":47},"npx","npx skills add mbaker95\u002Fnanodex --skill add-parallel",{"tool":49,"command":50},"bunx","bunx skills add mbaker95\u002Fnanodex --skill add-parallel",{"tool":52,"command":53},"pnpm","pnpm dlx skills add mbaker95\u002Fnanodex --skill add-parallel","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmbaker95\u002Fnanodex\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fadd-parallel\u002FSKILL.md",true,[57],{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"scripts\u002Fwechat_article_search_api.py","SCRIPT","脚本",4053,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fdevops-cloud-operations\u002Fbrowser-automation-reference\u002Fwechat-article-search-api-skill\u002Fscripts\u002Fwechat_article_search_api.py",[64,89,107,130,142,154],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":71,"publishedAt":32},"01M6DG2XYNH5XV7XGTJJ1SF0TG","agent-browser","Browse the web for any task — research topics, read articles, interact with web apps, fill forms, take screenshots, extract data, and test web pages. Use whenever a browser would be useful, not just when the user explicitly asks.","https:\u002F\u002Fgithub.com\u002Fmbaker95\u002Fnanodex\u002Fblob\u002Fmain\u002Fcontainer\u002Fskills\u002Fagent-browser\u002FSKILL.md",[70],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[72,73,74,75,76,77,78,79,80,81,82,83,84,25,85,26,86,87,88],"agent browser","browser","pages","forms","task","test web","take","use","extract","data","user","read","screenshots","test","just","Bash","browse",{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":98,"publishedAt":32},"01M6DG2TPZAT3SMWSYFJ3K82TE","x-integration","X (Twitter) integration for NanoClaw. Post tweets, like, reply, retweet, and quote. Use for setup, testing, or troubleshooting X functionality. Triggers on \"setup x\", \"x integration\", \"twitter\", \"post tweet\", \"tweet\".","https:\u002F\u002Fgithub.com\u002Fmbaker95\u002Fnanodex\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fx-integration\u002FSKILL.md",[95],{"categoryNo":96,"categoryName":97,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",[99,29,79,100,101,102,103,104,105,106],"x integration","testing","setup","troubleshooting","twitter","reply","quote","triggers",{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":32},"01M6DG2Q4BJQ046BZSR9N7GZ72","use-local-whisper","Use when the user wants local voice transcription instead of OpenAI Whisper API. Switches to whisper.cpp running on Apple Silicon. WhatsApp only for now. Requires voice-transcription skill to be applied first.","https:\u002F\u002Fgithub.com\u002Fmbaker95\u002Fnanodex\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fuse-local-whisper\u002FSKILL.md",[],[114,115,79,116,117,118,119,120,82,121,122,123,124,125,126,127,128,129],"whisper","local whisper","local","use local whisper","apple","openai whisper","only","voice","apple silicon","api","first","openai","cpp","transcription","openai whisper api","whatsapp",{"skillNo":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":136,"publishedAt":32},"01M6DG2N2Z1V8VV4MQFRKFAQV0","update-skills","Check for and apply updates to installed skill branches from upstream.","https:\u002F\u002Fgithub.com\u002Fmbaker95\u002Fnanodex\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fupdate-skills\u002FSKILL.md",[],[137,138,139,140,141],"update","update skills","upstream","branches","check",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":148,"publishedAt":32},"01M6DG2J5D7Y3R2BF8V87XZAXF","update-nanoclaw","Efficiently bring upstream NanoClaw updates into a customized install, with preview, selective cherry-pick, and low token usage.","https:\u002F\u002Fgithub.com\u002Fmbaker95\u002Fnanodex\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fupdate-nanoclaw\u002FSKILL.md",[],[137,149,150,151,139,152,153],"update nanoclaw","install","pick","token","preview",{"skillNo":155,"name":101,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":159,"publishedAt":32},"01M6DG2FN7S7DVD337CNT5Y67D","Run initial NanoClaw setup. Use when user wants to install dependencies, authenticate messaging channels, register their main channel, or start the background services. Triggers on \"setup\", \"install\", \"configure nanoclaw\", or first-time setup requests.","https:\u002F\u002Fgithub.com\u002Fmbaker95\u002Fnanodex\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fsetup\u002FSKILL.md",[],[101,150,106,160,161,37,79,162,82,163,124,164,165,166,167],"time","dependencies","channel","configure","services","start","messaging","run"]