[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6JHJPRDMPHC1S0KZRR9SEWN":3,"skill-same:01M6JHJPRDMPHC1S0KZRR9SEWN":72},{"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":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":50,"commitSha":51,"skillDirectory":52,"forksCount":53,"repositoryHtmlUrl":54,"repositoryHomepageUrl":6,"ownerHtmlUrl":55,"ownerBlogUrl":6,"ownerDescription":56,"updatedAt":57,"install":58,"resources":71},"01M6JHJPRDMPHC1S0KZRR9SEWN","voice-agents",null,"Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. The challenge isn't just speech recognition and synthesis, it's achieving natural conversation flow with sub-800ms latency while handling interruptions, background noise, and emotional nuance.  This skill covers two architectures: speech-to-speech (OpenAI Realtime API, lowest latency, most natural) and pipeline (STT→LLM→TTS, more control, easier to debug). Key insight: latency is the constraint. Hu","transaurus\u002Fstaging-davila7-claude-code-templates","transaurus","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F210882017?v=4","01M6JH1R6ZCRXGJCTDP5ZKZBE6","Page Turner Agent","01M6JH1RBBR2P6Y0XWDGM4B0G7",0,"MIT","https:\u002F\u002Fgithub.com\u002Ftransaurus\u002Fstaging-davila7-claude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Fvoice-agents\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"voice agents","voice","challenge","spawner","more","speech-to-speech","with","architectures","interaction","control","latency","conversation","debug","just","tts","api","pipeline","speech","realtime api","realtime","2026-11-10 10:12:30",false,"---\nname: voice-agents\ndescription: \"Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. The challenge isn't just speech recognition and synthesis, it's achieving natural conversation flow with sub-800ms latency while handling interruptions, background noise, and emotional nuance.  This skill covers two architectures: speech-to-speech (OpenAI Realtime API, lowest latency, most natural) and pipeline (STT→LLM→TTS, more control, easier to debug). Key insight: latency is the constraint. Hu\"\nsource: vibeship-spawner-skills (Apache 2.0)\n---\n\n# Voice Agents\n\nYou are a voice AI architect who has shipped production voice agents handling\nmillions of calls. You understand the physics of latency - every component\nadds milliseconds, and the sum determines whether conversations feel natural\nor awkward.\n\nYour core insight: Two architectures exist. Speech-to-speech (S2S) models like\nOpenAI Realtime API preserve emotion and achieve lowest latency but are less\ncontrollable. Pipeline architectures (STT→LLM→TTS) give you control at each\nstep but add latency. Mos\n\n## Capabilities\n\n- voice-agents\n- speech-to-speech\n- speech-to-text\n- text-to-speech\n- conversational-ai\n- voice-activity-detection\n- turn-taking\n- barge-in-detection\n- voice-interfaces\n\n## Patterns\n\n### Speech-to-Speech Architecture\n\nDirect audio-to-audio processing for lowest latency\n\n### Pipeline Architecture\n\nSeparate STT → LLM → TTS for maximum control\n\n### Voice Activity Detection Pattern\n\nDetect when user starts\u002Fstops speaking\n\n## Anti-Patterns\n\n### ❌ Ignoring Latency Budget\n\n### ❌ Silence-Only Turn Detection\n\n### ❌ Long Responses\n\n## ⚠️ Sharp Edges\n\n| Issue | Severity | Solution |\n|-------|----------|----------|\n| Issue | critical | # Measure and budget latency for each component: |\n| Issue | high | # Target jitter metrics: |\n| Issue | high | # Use semantic VAD: |\n| Issue | high | # Implement barge-in detection: |\n| Issue | medium | # Constrain response length in prompts: |\n| Issue | medium | # Prompt for spoken format: |\n| Issue | medium | # Implement noise handling: |\n| Issue | medium | # Mitigate STT errors: |\n\n## Related Skills\n\nWorks well with: `agent-tool-builder`, `multi-agent-orchestration`, `llm-architect`, `backend`\n","# Voice Agents\n\nYou are a voice AI architect who has shipped production voice agents handling\nmillions of calls. You understand the physics of latency - every component\nadds milliseconds, and the sum determines whether conversations feel natural\nor awkward.\n\nYour core insight: Two architectures exist. Speech-to-speech (S2S) models like\nOpenAI Realtime API preserve emotion and achieve lowest latency but are less\ncontrollable. Pipeline architectures (STT→LLM→TTS) give you control at each\nstep but add latency. Mos\n\n## Capabilities\n\n- voice-agents\n- speech-to-speech\n- speech-to-text\n- text-to-speech\n- conversational-ai\n- voice-activity-detection\n- turn-taking\n- barge-in-detection\n- voice-interfaces\n\n## Patterns\n\n### Speech-to-Speech Architecture\n\nDirect audio-to-audio processing for lowest latency\n\n### Pipeline Architecture\n\nSeparate STT → LLM → TTS for maximum control\n\n### Voice Activity Detection Pattern\n\nDetect when user starts\u002Fstops speaking\n\n## Anti-Patterns\n\n### ❌ Ignoring Latency Budget\n\n### ❌ Silence-Only Turn Detection\n\n### ❌ Long Responses\n\n## ⚠️ Sharp Edges\n\n| Issue | Severity | Solution |\n|-------|----------|----------|\n| Issue | critical | # Measure and budget latency for each component: |\n| Issue | high | # Target jitter metrics: |\n| Issue | high | # Use semantic VAD: |\n| Issue | high | # Implement barge-in detection: |\n| Issue | medium | # Constrain response length in prompts: |\n| Issue | medium | # Prompt for spoken format: |\n| Issue | medium | # Implement noise handling: |\n| Issue | medium | # Mitigate STT errors: |\n\n## Related Skills\n\nWorks well with: `agent-tool-builder`, `multi-agent-orchestration`, `llm-architect`, `backend`\n",{"name":5,"source":49,"description":7},"vibeship-spawner-skills (Apache 2.0)","main","34fa6acf794b9a6310d298cbb8fb8c9420a5edcf","cli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Fvoice-agents",2,"https:\u002F\u002Fgithub.com\u002Ftransaurus\u002Fstaging-davila7-claude-code-templates","https:\u002F\u002Fgithub.com\u002Ftransaurus","Automated works of Page Turner","2026-03-28 10:12:59",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add transaurus\u002Fstaging-davila7-claude-code-templates --skill voice-agents",{"tool":64,"command":65},"bunx","bunx skills add transaurus\u002Fstaging-davila7-claude-code-templates --skill voice-agents",{"tool":67,"command":68},"pnpm","pnpm dlx skills add transaurus\u002Fstaging-davila7-claude-code-templates --skill voice-agents","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftransaurus\u002Fstaging-davila7-claude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Fvoice-agents\u002FSKILL.md",true,[],[73,104,125,148,168,194],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":84,"publishedAt":44},"01M6JMRJR3BE0HGWFWDZSB853S","zapier-make-patterns","No-code automation democratizes workflow building. Zapier and Make (formerly Integromat) let non-developers automate business processes without writing code. But no-code doesn't mean no-complexity - these platforms have their own patterns, pitfalls, and breaking points.  This skill covers when to use which platform, how to build reliable automations, and when to graduate to code-based solutions. Key insight: Zapier optimizes for simplicity and integrations (7000+ apps), Make optimizes for power","https:\u002F\u002Fgithub.com\u002Ftransaurus\u002Fstaging-davila7-claude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fworkflow-automation\u002Fzapier-make-patterns\u002FSKILL.md",[79],{"categoryNo":80,"categoryName":81,"taxonomyType":82,"taxonomyTypeDesc":83},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,27],"zapier make patterns","patterns","make","zapier","writing","workflow","automation","code","integrations","business","use","power","complexity","platform","apps","how to","No-Code","which","for",{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":44},"01M6JMR8YK6SWPCTG1MCQTMN9S","yeet","Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).","https:\u002F\u002Fgithub.com\u002Ftransaurus\u002Fstaging-davila7-claude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fworkflow-automation\u002Fyeet\u002FSKILL.md",[],[106,111,112,113,114,115,116,117,118,119,120,121,95,122,123,124],"cli","github","commit","pull request","openai","pull","push","flow","open","gh","user","only","stage","github cli",{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":132,"publishedAt":44},"01M6JMQNFE64ZASQK90HARRXW8","workflow-automation","Workflow automation is the infrastructure that makes AI agents reliable. Without durable execution, a network hiccup during a 10-step payment flow means lost money and angry customers. With it, workflows resume exactly where they left off.  This skill covers the platforms (n8n, Temporal, Inngest) and patterns (sequential, parallel, orchestrator-worker) that turn brittle scripts into production-grade automation.  Key insight: The platforms make different tradeoffs. n8n optimizes for accessibility","https:\u002F\u002Fgithub.com\u002Ftransaurus\u002Fstaging-davila7-claude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fworkflow-automation\u002Fworkflow-automation\u002FSKILL.md",[131],{"categoryNo":80,"categoryName":81,"taxonomyType":82,"taxonomyTypeDesc":83},[90,91,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,30,103,27],"Workflow Automation","ai agents","accessibility","workflows","apache","execution","inngest","parallel","orchestrator","resume","n8n","payment","worker","scripts","temporal",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":154,"publishedAt":44},"01M6JMQDYJ0XETERPHGDR3EVGN","trigger-dev","Trigger.dev expert for background jobs, AI workflows, and reliable async execution with excellent developer experience and TypeScript-first design. Use when: trigger.dev, trigger dev, background task, ai background job, long running task.","https:\u002F\u002Fgithub.com\u002Ftransaurus\u002Fstaging-davila7-claude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fworkflow-automation\u002Ftrigger-dev\u002FSKILL.md",[],[155,156,157,158,159,136,160,137,138,161,95,162,163,164,165,166,167,30,103,27],"dev","trigger dev","trigger","design","typescript","async execution","first","async","developer experience","expert","task","background jobs","long",{"skillNo":169,"name":170,"nameZh":6,"description":171,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":172,"categories":173,"keywords":177,"publishedAt":44},"01M6JMQ5J6KK3GSX9FJCWWK6G6","planning-with-files","Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Use when starting complex tasks, multi-step projects, research tasks, or when the user mentions planning, organizing work, tracking progress, or wants structured output.","https:\u002F\u002Fgithub.com\u002Ftransaurus\u002Fstaging-davila7-claude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fworkflow-automation\u002Fplanning-with-files\u002FSKILL.md",[174],{"categoryNo":175,"categoryName":176,"taxonomyType":82,"taxonomyTypeDesc":83},"01JBSEEDCAT000000000000021","资料检索与研究",[178,179,180,30,181,90,182,183,184,185,186,187,95,188,189,190,191,192,193,103],"planning with files","planning","files","with files","storage","tasks","markdown","knowledge","projects","work","manus","structured output","progress","transforms","multi","output",{"skillNo":195,"name":196,"nameZh":6,"description":197,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":198,"categories":199,"keywords":204,"publishedAt":44},"01M6JMPWAT60RXXNEC4V9TRBRS","n8n-workflow-patterns","Proven workflow architectural patterns from real n8n workflows. Use when building new workflows, designing workflow structure, choosing workflow patterns, planning workflow architecture, or asking about webhook processing, HTTP API integration, database operations, AI agent workflows, or scheduled tasks.","https:\u002F\u002Fgithub.com\u002Ftransaurus\u002Fstaging-davila7-claude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fworkflow-automation\u002Fn8n\u002Fn8n-workflow-patterns\u002FSKILL.md",[200,203],{"categoryNo":201,"categoryName":202,"taxonomyType":82,"taxonomyTypeDesc":83},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":80,"categoryName":81,"taxonomyType":82,"taxonomyTypeDesc":83},[90,205,143,206,86,207,208,136,209,183,179,210,39,211,212,213,214,215,216,217],"n8n workflow patterns","workflow patterns","n8n workflow","ai agent","architecture","database","planning workflow","structure","database operations","webhook","processing","http api","scheduled"]