[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7589YVQBGA2PWM6G6KBFAXT":3,"skill-same:01M7589YVQBGA2PWM6G6KBFAXT":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},"01M7589YVQBGA2PWM6G6KBFAXT","retellai-policy-guardrails",null,"Implement Retell AI lint rules, policy enforcement, and automated guardrails.\nUse when setting up code quality rules for Retell AI integrations, implementing\npre-commit hooks, or configuring CI policy checks for Retell AI best practices.\nTrigger with phrases like \"retellai policy\", \"retellai lint\",\n\"retellai guardrails\", \"retellai best practices check\", \"retellai eslint\".","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-policy-guardrails\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: retellai-policy-guardrails\ndescription: |\n  Implement Retell AI lint rules, policy enforcement, and automated guardrails.\n  Use when setting up code quality rules for Retell AI integrations, implementing\n  pre-commit hooks, or configuring CI policy checks for Retell AI best practices.\n  Trigger with phrases like \"retellai policy\", \"retellai lint\",\n  \"retellai guardrails\", \"retellai best practices check\", \"retellai eslint\".\nallowed-tools: Read, Write, Edit, Bash(npx:*)\nversion: 1.0.0\nlicense: MIT\nauthor: Jeremy Longshore \u003Cjeremy@intentsolutions.io>\ncompatible-with: claude-code, codex, openclaw\n---\n# Retell AI Policy Guardrails\n\n## Overview\nPolicy enforcement for Retell AI voice agent deployments. Voice AI agents interact with real people over phone calls, requiring strict controls around conversation content, call recording consent, data handling, and cost management.\n\n## Prerequisites\n- Retell AI agent configured\n- Understanding of telephony compliance (TCPA, GDPR)\n- Call recording consent requirements for your jurisdiction\n\n## Instructions\n\n### Step 1: Conversation Content Boundaries\n\nDefine what the agent can and cannot discuss to prevent liability.\n\n```typescript\nconst CONVERSATION_POLICY = {\n  blockedTopics: [\n    'medical advice', 'legal advice', 'financial advice',\n    'political opinions', 'competitor pricing'\n  ],\n  requiredDisclosures: [\n    'This is an AI assistant',\n    'This call may be recorded'\n  ],\n  maxCallDuration: 600,  \u002F\u002F 10 minutes  # 600: timeout: 10 minutes\n  escalationTriggers: ['speak to a human', 'talk to manager', 'real person']\n};\n\nfunction enforceContentPolicy(agentResponse: string): string {\n  for (const topic of CONVERSATION_POLICY.blockedTopics) {\n    if (agentResponse.toLowerCase().includes(topic)) {\n      return \"I'm not able to advise on that topic. Let me connect you with a specialist.\";\n    }\n  }\n  return agentResponse;\n}\n```\n\n### Step 2: Call Recording Consent\n\nMany jurisdictions require two-party consent for recording. Enforce upfront disclosure.\n\n```typescript\nconst CONSENT_SCRIPT = {\n  opening: \"Hi, this is an AI assistant calling from [Company]. This call may be recorded for quality purposes. Is that okay?\",\n  noConsent: \"I understand. I'll continue without recording. How can I help you today?\",\n  consentReceived: true\n};\n\napp.post('\u002Fretell-webhook', async (req, res) => {\n  const { call_id, turn_number, transcript } = req.body;\n\n  \u002F\u002F First turn: always deliver consent disclosure\n  if (turn_number === 0) {\n    return res.json({ response: CONSENT_SCRIPT.opening });\n  }\n\n  \u002F\u002F Second turn: check for consent\n  if (turn_number === 1) {\n    const consented = \u002Fyes|okay|sure|that's fine\u002Fi.test(transcript);\n    if (!consented) {\n      await retell.call.update(call_id, { recording_enabled: false });\n      return res.json({ response: CONSENT_SCRIPT.noConsent });\n    }\n  }\n\n  \u002F\u002F Normal processing\n  const response = await generateResponse(req.body);\n  return res.json({ response: enforceContentPolicy(response) });\n});\n```\n\n### Step 3: Cost Controls\n\nVoice calls cost per minute. Cap concurrent calls and duration.\n\n```typescript\nclass CallCostPolicy {\n  private activeCalls = new Map\u003Cstring, number>();\n  private maxConcurrent = 10;\n  private maxDurationSec = 600;  # 600: timeout: 10 minutes\n  private dailyBudget = 100;  \u002F\u002F dollars\n  private costPerMinute = 0.10;\n\n  canInitiateCall(): boolean {\n    if (this.activeCalls.size >= this.maxConcurrent) return false;\n    if (this.getDailySpend() >= this.dailyBudget) return false;\n    return true;\n  }\n\n  monitorDuration(callId: string) {\n    const started = this.activeCalls.get(callId);\n    if (started && (Date.now() - started) \u002F 1000 > this.maxDurationSec) {  # 1000: 1 second in ms\n      return { action: 'end', reason: 'Maximum call duration exceeded' };\n    }\n    return { action: 'continue' };\n  }\n\n  getDailySpend(): number {\n    let totalMinutes = 0;\n    for (const started of this.activeCalls.values()) {\n      totalMinutes += (Date.now() - started) \u002F 60000;  # 60000: 1 minute in ms\n    }\n    return totalMinutes * this.costPerMinute;\n  }\n}\n```\n\n### Step 4: Human Escalation Triggers\n\nDetect when callers want a human and transfer gracefully.\n\n```typescript\nfunction checkEscalation(transcript: string): boolean {\n  const triggers = ['speak to a human', 'real person', 'talk to someone', 'supervisor', 'manager'];\n  return triggers.some(t => transcript.toLowerCase().includes(t));\n}\n```\n\n## Error Handling\n| Issue | Cause | Solution |\n|-------|-------|----------|\n| Compliance violation | Agent gives restricted advice | Content filtering on responses |\n| Recording without consent | Missing disclosure | Enforce consent script on first turn |\n| Runaway call costs | No duration\u002Fbudget limits | Implement cost controls |\n| Frustrated caller | No human escalation | Detect escalation triggers, transfer |\n\n## Examples\n\n### Policy Dashboard\n```typescript\nconst dashboard = {\n  activeCalls: costPolicy.activeCalls.size,\n  dailySpend: costPolicy.getDailySpend().toFixed(2),\n  escalationRate: metrics.rate('escalations'),\n  avgCallDuration: metrics.avg('call_duration_sec')\n};\n```\n\n## Resources\n- [Retell AI Docs](https:\u002F\u002Fdocs.retellai.com)\n- [TCPA Compliance](https:\u002F\u002Fwww.fcc.gov\u002Fgeneral\u002Ftelemarketing-and-robocalls)\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 Policy Guardrails\n\n## Overview\nPolicy enforcement for Retell AI voice agent deployments. Voice AI agents interact with real people over phone calls, requiring strict controls around conversation content, call recording consent, data handling, and cost management.\n\n## Prerequisites\n- Retell AI agent configured\n- Understanding of telephony compliance (TCPA, GDPR)\n- Call recording consent requirements for your jurisdiction\n\n## Instructions\n\n### Step 1: Conversation Content Boundaries\n\nDefine what the agent can and cannot discuss to prevent liability.\n\n```typescript\nconst CONVERSATION_POLICY = {\n  blockedTopics: [\n    'medical advice', 'legal advice', 'financial advice',\n    'political opinions', 'competitor pricing'\n  ],\n  requiredDisclosures: [\n    'This is an AI assistant',\n    'This call may be recorded'\n  ],\n  maxCallDuration: 600,  \u002F\u002F 10 minutes  # 600: timeout: 10 minutes\n  escalationTriggers: ['speak to a human', 'talk to manager', 'real person']\n};\n\nfunction enforceContentPolicy(agentResponse: string): string {\n  for (const topic of CONVERSATION_POLICY.blockedTopics) {\n    if (agentResponse.toLowerCase().includes(topic)) {\n      return \"I'm not able to advise on that topic. Let me connect you with a specialist.\";\n    }\n  }\n  return agentResponse;\n}\n```\n\n### Step 2: Call Recording Consent\n\nMany jurisdictions require two-party consent for recording. Enforce upfront disclosure.\n\n```typescript\nconst CONSENT_SCRIPT = {\n  opening: \"Hi, this is an AI assistant calling from [Company]. This call may be recorded for quality purposes. Is that okay?\",\n  noConsent: \"I understand. I'll continue without recording. How can I help you today?\",\n  consentReceived: true\n};\n\napp.post('\u002Fretell-webhook', async (req, res) => {\n  const { call_id, turn_number, transcript } = req.body;\n\n  \u002F\u002F First turn: always deliver consent disclosure\n  if (turn_number === 0) {\n    return res.json({ response: CONSENT_SCRIPT.opening });\n  }\n\n  \u002F\u002F Second turn: check for consent\n  if (turn_number === 1) {\n    const consented = \u002Fyes|okay|sure|that's fine\u002Fi.test(transcript);\n    if (!consented) {\n      await retell.call.update(call_id, { recording_enabled: false });\n      return res.json({ response: CONSENT_SCRIPT.noConsent });\n    }\n  }\n\n  \u002F\u002F Normal processing\n  const response = await generateResponse(req.body);\n  return res.json({ response: enforceContentPolicy(response) });\n});\n```\n\n### Step 3: Cost Controls\n\nVoice calls cost per minute. Cap concurrent calls and duration.\n\n```typescript\nclass CallCostPolicy {\n  private activeCalls = new Map\u003Cstring, number>();\n  private maxConcurrent = 10;\n  private maxDurationSec = 600;  # 600: timeout: 10 minutes\n  private dailyBudget = 100;  \u002F\u002F dollars\n  private costPerMinute = 0.10;\n\n  canInitiateCall(): boolean {\n    if (this.activeCalls.size >= this.maxConcurrent) return false;\n    if (this.getDailySpend() >= this.dailyBudget) return false;\n    return true;\n  }\n\n  monitorDuration(callId: string) {\n    const started = this.activeCalls.get(callId);\n    if (started && (Date.now() - started) \u002F 1000 > this.maxDurationSec) {  # 1000: 1 second in ms\n      return { action: 'end', reason: 'Maximum call duration exceeded' };\n    }\n    return { action: 'continue' };\n  }\n\n  getDailySpend(): number {\n    let totalMinutes = 0;\n    for (const started of this.activeCalls.values()) {\n      totalMinutes += (Date.now() - started) \u002F 60000;  # 60000: 1 minute in ms\n    }\n    return totalMinutes * this.costPerMinute;\n  }\n}\n```\n\n### Step 4: Human Escalation Triggers\n\nDetect when callers want a human and transfer gracefully.\n\n```typescript\nfunction checkEscalation(transcript: string): boolean {\n  const triggers = ['speak to a human', 'real person', 'talk to someone', 'supervisor', 'manager'];\n  return triggers.some(t => transcript.toLowerCase().includes(t));\n}\n```\n\n## Error Handling\n| Issue | Cause | Solution |\n|-------|-------|----------|\n| Compliance violation | Agent gives restricted advice | Content filtering on responses |\n| Recording without consent | Missing disclosure | Enforce consent script on first turn |\n| Runaway call costs | No duration\u002Fbudget limits | Implement cost controls |\n| Frustrated caller | No human escalation | Detect escalation triggers, transfer |\n\n## Examples\n\n### Policy Dashboard\n```typescript\nconst dashboard = {\n  activeCalls: costPolicy.activeCalls.size,\n  dailySpend: costPolicy.getDailySpend().toFixed(2),\n  escalationRate: metrics.rate('escalations'),\n  avgCallDuration: metrics.avg('call_duration_sec')\n};\n```\n\n## Resources\n- [Retell AI Docs](https:\u002F\u002Fdocs.retellai.com)\n- [TCPA Compliance](https:\u002F\u002Fwww.fcc.gov\u002Fgeneral\u002Ftelemarketing-and-robocalls)\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","Implement Retell AI lint rules, policy enforcement, and automated guardrails.\nUse when setting up code quality rules for Retell AI integrations, implementing\npre-commit hooks, or configuring CI policy checks for Retell AI best practices.\nTrigger with phrases like \"retellai policy\", \"retellai lint\",\n\"retellai guardrails\", \"retellai best practices check\", \"retellai eslint\".\n","Read, Write, Edit, Bash(npx:*)","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-policy-guardrails",{"tool":41,"command":42},"bunx","bunx skills add SamuelChien\u002Fmega-skills-collection --skill retellai-policy-guardrails",{"tool":44,"command":45},"pnpm","pnpm dlx skills add SamuelChien\u002Fmega-skills-collection --skill retellai-policy-guardrails","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fretellai-policy-guardrails\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",[],[]]