[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MYGRB65R85XSSZNTSJD68V":3,"skill-same:01M6MYGRB65R85XSSZNTSJD68V":66},{"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":32,"linkOnly":33,"markdownContent":34,"markdownBody":35,"frontMatter":36,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":6,"ownerHtmlUrl":49,"ownerBlogUrl":6,"ownerDescription":50,"updatedAt":51,"install":52,"resources":65},"01M6MYGRB65R85XSSZNTSJD68V","phone-call",null,"Make autonomous phone calls with AI voice using Twilio, Deepgram, and ElevenLabs","Kernel8901\u002Fai-agent-skills-classification","Kernel8901","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F72647553?v=4","01M6KV388J2H5PNC8D8P940BJD","01M6KV38CS5B3AY63RKZB410YM",7,"MIT","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Fconcierge\u002Fskills\u002Fphone-call\u002FSKILL.md",[],[18,19,20,21,22,23,24,25,26,27,28,29,30,31],"phone","call","phone call","voice","autonomous","elevenlabs","phone calls","twilio","make","deepgram","with","calls","hotel","book","2026-11-10 10:12:30",false,"---\nname: phone-call\ndescription: Make autonomous phone calls with AI voice using Twilio, Deepgram, and ElevenLabs\nversion: 1.2.0\ntriggers:\n  - call\n  - phone\n  - dial\n  - make a call\n  - book by phone\n  - call the hotel\n  - call the restaurant\n---\n\n# Phone Call Skill\n\nMake autonomous phone calls with a goal-driven AI agent. The AI handles the conversation until the goal is achieved.\n\n## Prerequisites\n\n1. **Required configuration:**\n   ```bash\n   concierge config set twilioAccountSid \u003Cyour-sid>\n   concierge config set twilioAuthToken \u003Cyour-token>\n   concierge config set twilioPhoneNumber \u003Cyour-number>\n   concierge config set deepgramApiKey \u003Cyour-key>\n   concierge config set elevenLabsApiKey \u003Cyour-key>\n   concierge config set elevenLabsVoiceId \u003Cvoice-id>\n   concierge config set anthropicApiKey \u003Cyour-key>\n   ```\n\n2. **Optional for auto-managed ngrok:**\n   ```bash\n   concierge config set ngrokAuthToken \u003Cyour-ngrok-token>\n   ```\n\n## Usage\n\n### Basic call\n```bash\nconcierge call \"+1-555-123-4567\" \\\n  --goal \"Book a hotel room for February 15\" \\\n  --name \"John Smith\" \\\n  --email \"john@example.com\" \\\n  --customer-phone \"+1-555-444-1212\" \\\n  --context \"2 nights, king bed preferred\"\n```\n\n### Interactive mode\n```bash\nconcierge call \"+1-555-123-4567\" \\\n  --goal \"Make a reservation\" \\\n  --name \"John Smith\" \\\n  --email \"john@example.com\" \\\n  --customer-phone \"+1-555-444-1212\" \\\n  --interactive\n```\nIn interactive mode, you type what the AI should say in real-time.\n\n### Infrastructure behavior\n\n- By default, `call` auto-starts `ngrok` and `server` if server is unavailable.\n- Use `--no-auto-infra` to disable this and run everything manually.\n- Auto-managed processes are stopped automatically when the call ends.\n- Log files are written to:\n  - `~\u002F.config\u002Fconcierge\u002Fcall-runs\u002F\u003Crun-id>\u002Fserver.log`\n  - `~\u002F.config\u002Fconcierge\u002Fcall-runs\u002F\u003Crun-id>\u002Fngrok.log`\n\n### Server management\n```bash\n# Check server status\nconcierge server status\n\n# Start server\nconcierge server start --public-url \u003Cngrok-url>\n\n# Stop server\nconcierge server stop\n```\n\n## Preflight checks\n\nBefore dialing, the system validates:\n- Local runtime dependencies (`ffmpeg` binary + MP3 decode support, plus `ngrok` if auto-infra is used)\n- Twilio credentials\u002Faccount status\u002Ffrom-number availability\n- Deepgram API key\u002Fauth reachability\n- ElevenLabs character quota sufficiency (estimated call budget)\n\n## How It Works\n\n1. CLI sends a call request with goal + customer identity details\n2. The server places the call via Twilio\n3. Audio streams bidirectionally via WebSocket\n4. Deepgram transcribes human speech in real-time\n5. Claude generates appropriate responses\n6. ElevenLabs synthesizes speech for responses\n7. Call continues until goal is achieved or human hangs up\n\n## Examples\n\n### Book a hotel reservation\n```bash\nconcierge call \"+1-800-HILTON\" \\\n  --goal \"Book a room for 2 nights\" \\\n  --name \"Sarah Johnson\" \\\n  --email \"sarah@example.com\" \\\n  --customer-phone \"+1-555-000-2222\" \\\n  --context \"Check-in: March 10, Guest: Sarah Johnson, King bed, non-smoking\"\n```\n\n### Make a restaurant reservation\n```bash\nconcierge call \"+1-555-DINER\" \\\n  --goal \"Reserve a table for dinner\" \\\n  --name \"Garcia\" \\\n  --email \"garcia@example.com\" \\\n  --customer-phone \"+1-555-000-3333\" \\\n  --context \"Party of 4, 7:30 PM, Saturday, name: Garcia\"\n```\n\n### Cancel an appointment\n```bash\nconcierge call \"+1-555-DOCTOR\" \\\n  --goal \"Cancel appointment\" \\\n  --name \"Mike Chen\" \\\n  --email \"mike@example.com\" \\\n  --customer-phone \"+1-555-000-4444\" \\\n  --context \"Patient: Mike Chen, Appointment on Tuesday at 2 PM\"\n```\n\n## Supported Voice IDs\n\nSome popular ElevenLabs voices:\n- `EXAVITQu4vr4xnSDxMaL` - Rachel (default, conversational female)\n- `pNInz6obpgDQGcFmaJgB` - Adam (conversational male)\n- `21m00Tcm4TlvDq8ikWAM` - Rachel (narration)\n- `AZnzlk1XvdvUeBnXmlld` - Domi (young female)\n\nSet your preferred voice:\n```bash\nconcierge config set elevenLabsVoiceId \u003Cvoice-id>\n```\n\n## Latency\n\nTarget voice-to-voice latency: \u003C 500ms\n\n- Deepgram STT: ~150ms\n- Response generation: ~100-200ms\n- ElevenLabs TTS: ~75ms\n- Network: ~50ms\n\n## Troubleshooting\n\n### Server won't start\n- Check all config keys are set: `concierge config show`\n- If using manual mode, ensure ngrok is running and URL is correct\n- Check port 3000 is available\n\n### Call not connecting\n- Verify Twilio phone number is active\n- Check Twilio account has sufficient balance\n- Ensure ngrok URL is publicly accessible (manual mode)\n\n### TTS fails mid-call\n- Check ElevenLabs quota\u002Fcredits.\n- New preflight usually catches this before dialing.\n- If it still happens, reduce prompt\u002Fcontext length or top up ElevenLabs.\n\n### Audio quality issues\n- ElevenLabs uses optimized phone call settings\n- Deepgram uses the phone call model\n- Audio is at 8kHz (telephone quality)\n","# Phone Call Skill\n\nMake autonomous phone calls with a goal-driven AI agent. The AI handles the conversation until the goal is achieved.\n\n## Prerequisites\n\n1. **Required configuration:**\n   ```bash\n   concierge config set twilioAccountSid \u003Cyour-sid>\n   concierge config set twilioAuthToken \u003Cyour-token>\n   concierge config set twilioPhoneNumber \u003Cyour-number>\n   concierge config set deepgramApiKey \u003Cyour-key>\n   concierge config set elevenLabsApiKey \u003Cyour-key>\n   concierge config set elevenLabsVoiceId \u003Cvoice-id>\n   concierge config set anthropicApiKey \u003Cyour-key>\n   ```\n\n2. **Optional for auto-managed ngrok:**\n   ```bash\n   concierge config set ngrokAuthToken \u003Cyour-ngrok-token>\n   ```\n\n## Usage\n\n### Basic call\n```bash\nconcierge call \"+1-555-123-4567\" \\\n  --goal \"Book a hotel room for February 15\" \\\n  --name \"John Smith\" \\\n  --email \"john@example.com\" \\\n  --customer-phone \"+1-555-444-1212\" \\\n  --context \"2 nights, king bed preferred\"\n```\n\n### Interactive mode\n```bash\nconcierge call \"+1-555-123-4567\" \\\n  --goal \"Make a reservation\" \\\n  --name \"John Smith\" \\\n  --email \"john@example.com\" \\\n  --customer-phone \"+1-555-444-1212\" \\\n  --interactive\n```\nIn interactive mode, you type what the AI should say in real-time.\n\n### Infrastructure behavior\n\n- By default, `call` auto-starts `ngrok` and `server` if server is unavailable.\n- Use `--no-auto-infra` to disable this and run everything manually.\n- Auto-managed processes are stopped automatically when the call ends.\n- Log files are written to:\n  - `~\u002F.config\u002Fconcierge\u002Fcall-runs\u002F\u003Crun-id>\u002Fserver.log`\n  - `~\u002F.config\u002Fconcierge\u002Fcall-runs\u002F\u003Crun-id>\u002Fngrok.log`\n\n### Server management\n```bash\n# Check server status\nconcierge server status\n\n# Start server\nconcierge server start --public-url \u003Cngrok-url>\n\n# Stop server\nconcierge server stop\n```\n\n## Preflight checks\n\nBefore dialing, the system validates:\n- Local runtime dependencies (`ffmpeg` binary + MP3 decode support, plus `ngrok` if auto-infra is used)\n- Twilio credentials\u002Faccount status\u002Ffrom-number availability\n- Deepgram API key\u002Fauth reachability\n- ElevenLabs character quota sufficiency (estimated call budget)\n\n## How It Works\n\n1. CLI sends a call request with goal + customer identity details\n2. The server places the call via Twilio\n3. Audio streams bidirectionally via WebSocket\n4. Deepgram transcribes human speech in real-time\n5. Claude generates appropriate responses\n6. ElevenLabs synthesizes speech for responses\n7. Call continues until goal is achieved or human hangs up\n\n## Examples\n\n### Book a hotel reservation\n```bash\nconcierge call \"+1-800-HILTON\" \\\n  --goal \"Book a room for 2 nights\" \\\n  --name \"Sarah Johnson\" \\\n  --email \"sarah@example.com\" \\\n  --customer-phone \"+1-555-000-2222\" \\\n  --context \"Check-in: March 10, Guest: Sarah Johnson, King bed, non-smoking\"\n```\n\n### Make a restaurant reservation\n```bash\nconcierge call \"+1-555-DINER\" \\\n  --goal \"Reserve a table for dinner\" \\\n  --name \"Garcia\" \\\n  --email \"garcia@example.com\" \\\n  --customer-phone \"+1-555-000-3333\" \\\n  --context \"Party of 4, 7:30 PM, Saturday, name: Garcia\"\n```\n\n### Cancel an appointment\n```bash\nconcierge call \"+1-555-DOCTOR\" \\\n  --goal \"Cancel appointment\" \\\n  --name \"Mike Chen\" \\\n  --email \"mike@example.com\" \\\n  --customer-phone \"+1-555-000-4444\" \\\n  --context \"Patient: Mike Chen, Appointment on Tuesday at 2 PM\"\n```\n\n## Supported Voice IDs\n\nSome popular ElevenLabs voices:\n- `EXAVITQu4vr4xnSDxMaL` - Rachel (default, conversational female)\n- `pNInz6obpgDQGcFmaJgB` - Adam (conversational male)\n- `21m00Tcm4TlvDq8ikWAM` - Rachel (narration)\n- `AZnzlk1XvdvUeBnXmlld` - Domi (young female)\n\nSet your preferred voice:\n```bash\nconcierge config set elevenLabsVoiceId \u003Cvoice-id>\n```\n\n## Latency\n\nTarget voice-to-voice latency: \u003C 500ms\n\n- Deepgram STT: ~150ms\n- Response generation: ~100-200ms\n- ElevenLabs TTS: ~75ms\n- Network: ~50ms\n\n## Troubleshooting\n\n### Server won't start\n- Check all config keys are set: `concierge config show`\n- If using manual mode, ensure ngrok is running and URL is correct\n- Check port 3000 is available\n\n### Call not connecting\n- Verify Twilio phone number is active\n- Check Twilio account has sufficient balance\n- Ensure ngrok URL is publicly accessible (manual mode)\n\n### TTS fails mid-call\n- Check ElevenLabs quota\u002Fcredits.\n- New preflight usually catches this before dialing.\n- If it still happens, reduce prompt\u002Fcontext length or top up ElevenLabs.\n\n### Audio quality issues\n- ElevenLabs uses optimized phone call settings\n- Deepgram uses the phone call model\n- Audio is at 8kHz (telephone quality)\n",{"name":5,"version":37,"triggers":38,"description":7},"1.2.0",[19,18,39,40,41,42,43],"dial","make a call","book by phone","call the hotel","call the restaurant","main","f4cb2d49f7667e79ef7804f50396d5aaffdf1f56","人工智能与大型语言模型\u002Fconcierge\u002Fskills\u002Fphone-call",1,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification","https:\u002F\u002Fgithub.com\u002FKernel8901","a little little little dobe in life but science geek","2026-04-05 16:43:56",{"source":8,"skillName":5,"commands":53,"prompt":63,"zipAvailable":64},[54,57,60],{"tool":55,"command":56},"npx","npx skills add Kernel8901\u002Fai-agent-skills-classification --skill phone-call",{"tool":58,"command":59},"bunx","bunx skills add Kernel8901\u002Fai-agent-skills-classification --skill phone-call",{"tool":61,"command":62},"pnpm","pnpm dlx skills add Kernel8901\u002Fai-agent-skills-classification --skill phone-call","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Fconcierge\u002Fskills\u002Fphone-call\u002FSKILL.md",true,[],[67,91,127,138,148,178],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":32},"01M6Q5R6WZ06RRB9RQTW54B34B","zyfai","Earn yield on any Ethereum wallet on Base, Arbitrum, and Plasma. Use when a user wants passive DeFi yield on their funds. Deploys a non-custodial subaccount (Safe) linked to their EOA, enables automated yield optimization, and lets them deposit\u002Fwithdraw anytime.","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fzyfai-sdk\u002FSKILL.md",[],[69,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90],"safe","ethereum","defi","Optimization","user","use","Wallet","base","deposit","withdraw","yield","arbitrum","non-custodial","passive","defi yield","earn","yield optimization",{"skillNo":92,"name":93,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":109,"publishedAt":32},"01M6Q5R337B5JSNER4P4YS03TN","zerion-api","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fzerion-api\u002FSKILL.md",[96,101,104],{"categoryNo":97,"categoryName":98,"taxonomyType":99,"taxonomyTypeDesc":100},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":102,"categoryName":103,"taxonomyType":99,"taxonomyTypeDesc":100},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":105,"categoryName":106,"taxonomyType":107,"taxonomyTypeDesc":108},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[110,111,112,113,114,115,116,76,117,80,118,119,120,121,122,123,124,125,126],"api","zerion api","zerion","MCP","mcp server","server","blockchain","transactions","crypto wallet","crypto","evm","solana","query","across","positions","token","prices",{"skillNo":128,"name":129,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":135,"publishedAt":32},"01M6Q5QZFYTDAZMZ27BN5VZXAR","zerion-api-skill","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fzerion-api-skill\u002FSKILL.md",[132,133,134],{"categoryNo":97,"categoryName":98,"taxonomyType":99,"taxonomyTypeDesc":100},{"categoryNo":102,"categoryName":103,"taxonomyType":99,"taxonomyTypeDesc":100},{"categoryNo":105,"categoryName":106,"taxonomyType":107,"taxonomyTypeDesc":108},[110,136,137,111,112,113,114,115,116,76,117,80,119,120,121,122,123,124,125,126],"api skill","zerion api skill",{"skillNo":139,"name":140,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":146,"publishedAt":32},"01M6Q5QW17QW98RA3FE45E4RD8","zerion-api-mcp","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fzerion-api-mcp\u002FSKILL.md",[143,144,145],{"categoryNo":97,"categoryName":98,"taxonomyType":99,"taxonomyTypeDesc":100},{"categoryNo":102,"categoryName":103,"taxonomyType":99,"taxonomyTypeDesc":100},{"categoryNo":105,"categoryName":106,"taxonomyType":107,"taxonomyTypeDesc":108},[113,110,147,111,112,114,115,76,117,80,118,119,120,121,122,123,124,125,126],"zerion api mcp",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":157,"publishedAt":32},"01M6Q5QQYZB7A501BDEQWKGSJT","yahoo-finance-forex","Fetches real-time FOREX news and market data from Yahoo Finance for major currency pairs (EUR\u002FUSD, GBP\u002FUSD, USD\u002FJPY, etc.). Analyzes sentiment and provides trading context.","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fyahoo-finance-forex\u002FSKILL.md",[154],{"categoryNo":155,"categoryName":156,"taxonomyType":107,"taxonomyTypeDesc":108},"01JBSEEDCAT000000000000040","财务",[158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177],"finance","yahoo finance","forex","yahoo","yahoo finance forex","github","https","sentiment","real-time","python3","install","Market","usd","news","time","currency","gbp","pip","market data","for",{"skillNo":179,"name":180,"nameZh":6,"description":181,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":182,"categories":183,"keywords":185,"publishedAt":32},"01M6Q5QM6VS84WZVM7BKXXPF32","yahoo-finance","This skill should be used when the user asks to \"get stock prices\", \"check stock quotes\", \"look up earnings\", \"get financial data\", \"find trending stocks\", or needs stock market data from Yahoo Finance.","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fyahoo-finance-cli\u002FSKILL.md",[184],{"categoryNo":155,"categoryName":156,"taxonomyType":107,"taxonomyTypeDesc":108},[158,159,161,186,187,188,189,190,191,169,192,193,194,195,196,197,198,199,126,176],"cli","homebrew","find","check","brew","up","local","get","stock","link","trending","sf","quotes","ln"]