[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7589SYXG341ASXWMMF0WMC0":3,"skill-same:01M7589SYXG341ASXWMMF0WMC0":49},{"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":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":29,"commitSha":30,"skillDirectory":5,"forksCount":14,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":6,"updatedAt":34,"install":35,"resources":48},"01M7589SYXG341ASXWMMF0WMC0","retellai-performance-tuning",null,"Optimize Retell AI API performance with caching, batching, and connection pooling.\nUse when experiencing slow API responses, implementing caching strategies,\nor optimizing request throughput for Retell AI integrations.\nTrigger with phrases like \"retellai performance\", \"optimize retellai\",\n\"retellai latency\", \"retellai caching\", \"retellai slow\", \"retellai batch\".","SamuelChien\u002Fmega-skills-collection","SamuelChien","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F4652114?v=4","01M74KK34WVHA0P5ZYSJRDDFMG","Samuel Chien","01M74KK35FQN1N9VZ9EPTH3P2S",0,"MIT","https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fretellai-performance-tuning\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: retellai-performance-tuning\ndescription: |\n  Optimize Retell AI API performance with caching, batching, and connection pooling.\n  Use when experiencing slow API responses, implementing caching strategies,\n  or optimizing request throughput for Retell AI integrations.\n  Trigger with phrases like \"retellai performance\", \"optimize retellai\",\n  \"retellai latency\", \"retellai caching\", \"retellai slow\", \"retellai batch\".\nallowed-tools: Read, Write, Edit\nversion: 1.0.0\nlicense: MIT\nauthor: Jeremy Longshore \u003Cjeremy@intentsolutions.io>\ncompatible-with: claude-code, codex, openclaw\n---\n# Retell AI Performance Tuning\n\n## Overview\nOptimize Retell AI voice agent latency and call quality. Focus on reducing voice-to-voice latency, LLM response time, WebSocket connection management, and agent configuration tuning for natural conversations.\n\n## Prerequisites\n- Retell AI account with API key\n- `retell-sdk` npm package installed\n- WebSocket infrastructure for real-time calls\n- Understanding of voice agent architecture\n\n## Instructions\n\n### Step 1: Optimize Agent LLM Configuration\n```typescript\nimport Retell from 'retell-sdk';\n\nconst retell = new Retell({ apiKey: process.env.RETELL_API_KEY! });\n\n\u002F\u002F Configure agent for low latency\nasync function createOptimizedAgent() {\n  return retell.agent.create({\n    agent_name: 'fast-responder',\n    response_engine: {\n      type: 'retell-llm',\n      llm_id: process.env.RETELL_LLM_ID!,\n    },\n    voice_id: 'eleven_labs_rachel', \u002F\u002F Pre-cached voice\n    language: 'en-US',\n    interruption_sensitivity: 0.8, \u002F\u002F Higher = faster interrupt detection\n    ambient_sound: null,           \u002F\u002F Disable for lower latency\n    responsiveness: 0.9,           \u002F\u002F Higher = responds faster\n    voice_speed: 1.1,              \u002F\u002F Slightly faster speech\n    voice_temperature: 0.3,        \u002F\u002F Lower = more deterministic\n    enable_backchannel: true,      \u002F\u002F \"uh-huh\" for natural flow\n    boosted_keywords: ['appointment', 'schedule', 'callback'],\n  });\n}\n```\n\n### Step 2: Optimize LLM Prompt for Speed\n```typescript\nasync function createOptimizedLLM() {\n  return retell.llm.create({\n    general_prompt: `You are a fast, helpful phone agent.\nRules for speed:\n- Keep responses under 2 sentences\n- Never use filler words\n- Ask one question at a time\n- Confirm details immediately\n- Use short acknowledgments`,\n    begin_message: 'Hi, how can I help you today?',\n    model: 'gpt-4o-mini',     \u002F\u002F Faster than gpt-4o\n    general_tools: [\n      {\n        type: 'end_call',\n        name: 'end_call',\n        description: 'End the call when conversation is complete',\n      },\n      {\n        type: 'custom',\n        name: 'book_appointment',\n        description: 'Book an appointment for the caller',\n        parameters: {\n          type: 'object',\n          properties: {\n            date: { type: 'string' },\n            time: { type: 'string' },\n            name: { type: 'string' },\n          },\n          required: ['date', 'time', 'name'],\n        },\n        url: process.env.BOOKING_WEBHOOK_URL!,\n      },\n    ],\n  });\n}\n```\n\n### Step 3: WebSocket Connection Pooling\n```typescript\nimport WebSocket from 'ws';\n\nconst connectionPool: Map\u003Cstring, WebSocket> = new Map();\n\nasync function getWebSocketConnection(callId: string): Promise\u003CWebSocket> {\n  const existing = connectionPool.get(callId);\n  if (existing?.readyState === WebSocket.OPEN) return existing;\n\n  const ws = new WebSocket(\n    `wss:\u002F\u002Fapi.retellai.com\u002Faudio-websocket\u002F${callId}`,\n    { headers: { Authorization: `Bearer ${process.env.RETELL_API_KEY}` } }\n  );\n\n  return new Promise((resolve, reject) => {\n    ws.on('open', () => {\n      connectionPool.set(callId, ws);\n      resolve(ws);\n    });\n    ws.on('error', reject);\n    ws.on('close', () => connectionPool.delete(callId));\n  });\n}\n```\n\n### Step 4: Call Analytics Caching\n```typescript\nimport { LRUCache } from 'lru-cache';\n\nconst callCache = new LRUCache\u003Cstring, any>({\n  max: 500,  # HTTP 500 Internal Server Error\n  ttl: 1000 * 60 * 15, \u002F\u002F 15 min - completed calls don't change  # 1000: 1 second in ms\n});\n\nasync function getCallDetails(callId: string) {\n  const cached = callCache.get(callId);\n  if (cached) return cached;\n\n  const call = await retell.call.retrieve(callId);\n  if (call.call_status === 'ended') {\n    callCache.set(callId, call); \u002F\u002F Only cache completed calls\n  }\n  return call;\n}\n\nasync function getCallMetrics(callIds: string[]) {\n  const calls = await Promise.all(callIds.map(getCallDetails));\n  return {\n    avgDuration: calls.reduce((s, c) => s + (c.end_timestamp - c.start_timestamp), 0) \u002F calls.length,\n    avgLatency: calls.reduce((s, c) => s + (c.latency_p50 || 0), 0) \u002F calls.length,\n    successRate: calls.filter(c => c.disconnection_reason === 'agent_goodbye').length \u002F calls.length,\n  };\n}\n```\n\n## Error Handling\n| Issue | Cause | Solution |\n|-------|-------|----------|\n| High voice latency | Complex LLM prompt | Shorten prompt, use gpt-4o-mini |\n| WebSocket disconnect | Network instability | Implement reconnection logic |\n| Unnatural pauses | Low responsiveness setting | Increase responsiveness to 0.8+ |\n| Missed interrupts | Low sensitivity | Increase interruption_sensitivity |\n\n## Examples\n\n### Latency Monitoring\n```typescript\nretell.on('call_analyzed', (event) => {\n  const latency = event.call_analysis?.latency_p95;\n  if (latency && latency > 1500) {  # 1500 = configured value\n    console.warn(`High latency call ${event.call_id}: ${latency}ms p95`);\n  }\n});\n```\n\n## Resources\n- [Retell AI API Reference](https:\u002F\u002Fdocs.retellai.com\u002Fapi-references)\n- [Retell Agent Configuration](https:\u002F\u002Fdocs.retellai.com\u002Fbuild-agent)\n- [Voice Latency Optimization](https:\u002F\u002Fdocs.retellai.com\u002Foptimize-latency)\n\n## Output\n\n- Configuration files or code changes applied to the project\n- Validation report confirming correct implementation\n- Summary of changes made and their rationale","# Retell AI Performance Tuning\n\n## Overview\nOptimize Retell AI voice agent latency and call quality. Focus on reducing voice-to-voice latency, LLM response time, WebSocket connection management, and agent configuration tuning for natural conversations.\n\n## Prerequisites\n- Retell AI account with API key\n- `retell-sdk` npm package installed\n- WebSocket infrastructure for real-time calls\n- Understanding of voice agent architecture\n\n## Instructions\n\n### Step 1: Optimize Agent LLM Configuration\n```typescript\nimport Retell from 'retell-sdk';\n\nconst retell = new Retell({ apiKey: process.env.RETELL_API_KEY! });\n\n\u002F\u002F Configure agent for low latency\nasync function createOptimizedAgent() {\n  return retell.agent.create({\n    agent_name: 'fast-responder',\n    response_engine: {\n      type: 'retell-llm',\n      llm_id: process.env.RETELL_LLM_ID!,\n    },\n    voice_id: 'eleven_labs_rachel', \u002F\u002F Pre-cached voice\n    language: 'en-US',\n    interruption_sensitivity: 0.8, \u002F\u002F Higher = faster interrupt detection\n    ambient_sound: null,           \u002F\u002F Disable for lower latency\n    responsiveness: 0.9,           \u002F\u002F Higher = responds faster\n    voice_speed: 1.1,              \u002F\u002F Slightly faster speech\n    voice_temperature: 0.3,        \u002F\u002F Lower = more deterministic\n    enable_backchannel: true,      \u002F\u002F \"uh-huh\" for natural flow\n    boosted_keywords: ['appointment', 'schedule', 'callback'],\n  });\n}\n```\n\n### Step 2: Optimize LLM Prompt for Speed\n```typescript\nasync function createOptimizedLLM() {\n  return retell.llm.create({\n    general_prompt: `You are a fast, helpful phone agent.\nRules for speed:\n- Keep responses under 2 sentences\n- Never use filler words\n- Ask one question at a time\n- Confirm details immediately\n- Use short acknowledgments`,\n    begin_message: 'Hi, how can I help you today?',\n    model: 'gpt-4o-mini',     \u002F\u002F Faster than gpt-4o\n    general_tools: [\n      {\n        type: 'end_call',\n        name: 'end_call',\n        description: 'End the call when conversation is complete',\n      },\n      {\n        type: 'custom',\n        name: 'book_appointment',\n        description: 'Book an appointment for the caller',\n        parameters: {\n          type: 'object',\n          properties: {\n            date: { type: 'string' },\n            time: { type: 'string' },\n            name: { type: 'string' },\n          },\n          required: ['date', 'time', 'name'],\n        },\n        url: process.env.BOOKING_WEBHOOK_URL!,\n      },\n    ],\n  });\n}\n```\n\n### Step 3: WebSocket Connection Pooling\n```typescript\nimport WebSocket from 'ws';\n\nconst connectionPool: Map\u003Cstring, WebSocket> = new Map();\n\nasync function getWebSocketConnection(callId: string): Promise\u003CWebSocket> {\n  const existing = connectionPool.get(callId);\n  if (existing?.readyState === WebSocket.OPEN) return existing;\n\n  const ws = new WebSocket(\n    `wss:\u002F\u002Fapi.retellai.com\u002Faudio-websocket\u002F${callId}`,\n    { headers: { Authorization: `Bearer ${process.env.RETELL_API_KEY}` } }\n  );\n\n  return new Promise((resolve, reject) => {\n    ws.on('open', () => {\n      connectionPool.set(callId, ws);\n      resolve(ws);\n    });\n    ws.on('error', reject);\n    ws.on('close', () => connectionPool.delete(callId));\n  });\n}\n```\n\n### Step 4: Call Analytics Caching\n```typescript\nimport { LRUCache } from 'lru-cache';\n\nconst callCache = new LRUCache\u003Cstring, any>({\n  max: 500,  # HTTP 500 Internal Server Error\n  ttl: 1000 * 60 * 15, \u002F\u002F 15 min - completed calls don't change  # 1000: 1 second in ms\n});\n\nasync function getCallDetails(callId: string) {\n  const cached = callCache.get(callId);\n  if (cached) return cached;\n\n  const call = await retell.call.retrieve(callId);\n  if (call.call_status === 'ended') {\n    callCache.set(callId, call); \u002F\u002F Only cache completed calls\n  }\n  return call;\n}\n\nasync function getCallMetrics(callIds: string[]) {\n  const calls = await Promise.all(callIds.map(getCallDetails));\n  return {\n    avgDuration: calls.reduce((s, c) => s + (c.end_timestamp - c.start_timestamp), 0) \u002F calls.length,\n    avgLatency: calls.reduce((s, c) => s + (c.latency_p50 || 0), 0) \u002F calls.length,\n    successRate: calls.filter(c => c.disconnection_reason === 'agent_goodbye').length \u002F calls.length,\n  };\n}\n```\n\n## Error Handling\n| Issue | Cause | Solution |\n|-------|-------|----------|\n| High voice latency | Complex LLM prompt | Shorten prompt, use gpt-4o-mini |\n| WebSocket disconnect | Network instability | Implement reconnection logic |\n| Unnatural pauses | Low responsiveness setting | Increase responsiveness to 0.8+ |\n| Missed interrupts | Low sensitivity | Increase interruption_sensitivity |\n\n## Examples\n\n### Latency Monitoring\n```typescript\nretell.on('call_analyzed', (event) => {\n  const latency = event.call_analysis?.latency_p95;\n  if (latency && latency > 1500) {  # 1500 = configured value\n    console.warn(`High latency call ${event.call_id}: ${latency}ms p95`);\n  }\n});\n```\n\n## Resources\n- [Retell AI API Reference](https:\u002F\u002Fdocs.retellai.com\u002Fapi-references)\n- [Retell Agent Configuration](https:\u002F\u002Fdocs.retellai.com\u002Fbuild-agent)\n- [Voice Latency Optimization](https:\u002F\u002Fdocs.retellai.com\u002Foptimize-latency)\n\n## Output\n\n- Configuration files or code changes applied to the project\n- Validation report confirming correct implementation\n- Summary of changes made and their rationale",{"name":5,"author":24,"license":15,"version":25,"description":26,"allowed-tools":27,"compatible-with":28},"Jeremy Longshore \u003Cjeremy@intentsolutions.io>","1.0.0","Optimize Retell AI API performance with caching, batching, and connection pooling.\nUse when experiencing slow API responses, implementing caching strategies,\nor optimizing request throughput for Retell AI integrations.\nTrigger with phrases like \"retellai performance\", \"optimize retellai\",\n\"retellai latency\", \"retellai caching\", \"retellai slow\", \"retellai batch\".\n","Read, Write, Edit","claude-code, codex, openclaw","main","c2b1fdccc779e99ac814e55fb69ca8d71215dd0f","https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection","https:\u002F\u002Fgithub.com\u002FSamuelChien","http:\u002F\u002Fsamuelchien.com\u002F","2026-05-26 08:27:14",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add SamuelChien\u002Fmega-skills-collection --skill retellai-performance-tuning",{"tool":41,"command":42},"bunx","bunx skills add SamuelChien\u002Fmega-skills-collection --skill retellai-performance-tuning",{"tool":44,"command":45},"pnpm","pnpm dlx skills add SamuelChien\u002Fmega-skills-collection --skill retellai-performance-tuning","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fretellai-performance-tuning\u002FSKILL.md",true,[],[50,57,64,71,78,86],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M76R4WZQZAXGGXMQCA0FZ716","zustand-store-ts","Create Zustand stores with TypeScript, subscribeWithSelector middleware, and proper state\u002Faction separation. Use when building React state management, creating global stores, or implementing reactive state patterns with Zustand.","https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fzustand-store-ts\u002FSKILL.md",[],[],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M76R4T9KENDH7FENGZQHBW4G","zustand-store-creator","Zustand Store Creator - Auto-activating skill for Frontend Development.\nTriggers on: zustand store creator, zustand store creator\nPart of the Frontend Development skill category.","https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fzustand-store-creator\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M76R3YWN84B7SANJ52X799ZE","zero-trust-config-helper","Zero Trust Config Helper - Auto-activating skill for Security Advanced.\nTriggers on: zero trust config helper, zero trust config helper\nPart of the Security Advanced skill category.","https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fzero-trust-config-helper\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M76R3HNSV2AEYSKHM915GJ58","zapier-integration-helper","Zapier Integration Helper - Auto-activating skill for Business Automation.\nTriggers on: zapier integration helper, zapier integration helper\nPart of the Business Automation skill category.","https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fzapier-integration-helper\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M76R3DJSKAT4FA7DV4BF3GCE","zai-cli","Execute z.AI CLI providing vision, search, reader, and GitHub exploration via CLI and MCP.\nUse when user needs image\u002Fvideo analysis, OCR, UI-to-code conversion, error diagnosis,\nreal-time web search, web page to markdown extraction, or GitHub code exploration.\nTrigger with phrases like \"analyze this image\", \"search the web for\", \"read this page\",\n\"explore this repo\", or \"use zai\". Requires Z_AI_API_KEY.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fzai-cli\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M76R2KAM699XE9AJVAWE4H2E","yt-research","Research competitor YouTube channels, niches, and trending topics for your content strategy.\nUse this skill whenever the user says \"research channels\", \"analyze competitors\", \"find trending topics\",\n\"niche analysis\", \"competitive research\", \"what are other creators doing\", \"scrape YouTube channels\",\nor wants to understand the competitive landscape for a specific tool or topic area. Use when working with yt research. Trigger with 'yt', 'research'.","https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fyt-research\u002FSKILL.md",[],[]]