[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7563JFS97EVFHKSAM20GSYM":3,"skill-same:01M7563JFS97EVFHKSAM20GSYM":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},"01M7563JFS97EVFHKSAM20GSYM","perplexity-multi-env-setup",null,"Configure Perplexity Sonar API across development, staging, and production environments.\nUse when setting up multi-environment search integrations, managing model selection\nper environment, or controlling cost through sonar vs sonar-pro routing by env.\nTrigger with phrases like \"perplexity environments\", \"perplexity staging\",\n\"perplexity dev prod\", \"perplexity environment setup\", \"perplexity model by env\".","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\u002Fperplexity-multi-env-setup\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: perplexity-multi-env-setup\ndescription: |\n  Configure Perplexity Sonar API across development, staging, and production environments.\n  Use when setting up multi-environment search integrations, managing model selection\n  per environment, or controlling cost through sonar vs sonar-pro routing by env.\n  Trigger with phrases like \"perplexity environments\", \"perplexity staging\",\n  \"perplexity dev prod\", \"perplexity environment setup\", \"perplexity model by env\".\nallowed-tools: Read, Write, Edit, Bash(aws:*), Bash(gcloud:*), Bash(vault:*)\nversion: 1.0.0\nlicense: MIT\nauthor: Jeremy Longshore \u003Cjeremy@intentsolutions.io>\ncompatible-with: claude-code, codex, openclaw\n---\n# Perplexity Multi-Environment Setup\n\n## Overview\nPerplexity's OpenAI-compatible API uses the base URL `https:\u002F\u002Fapi.perplexity.ai`. The key per-environment configuration decisions are model selection and request limits.\n\n## Prerequisites\n- Perplexity API key from perplexity.ai\u002Fsettings\u002Fapi\n- OpenAI-compatible client library (`openai` npm package or equivalent)\n- Understanding of Sonar model tiers and their cost tradeoffs\n\n## Environment Strategy\n\n| Environment | Model | Cost\u002F1K requests | Rate Limit | Key Source |\n|-------------|-------|-----------------|------------|------------|\n| Development | `sonar` | ~$1 | 5 RPM (free tier) | `.env.local` |\n| Staging | `sonar` | ~$1 | 5-20 RPM | CI\u002FCD secrets |\n| Production | `sonar-pro` (deep), `sonar` (quick) | $1-$5 | 50+ RPM | Secret manager |\n\n## Instructions\n\n### Step 1: Configuration Structure\n```\nconfig\u002F\n  perplexity\u002F\n    base.ts           # OpenAI client pointing to Perplexity\n    development.ts    # Dev: sonar model, low rate limit\n    staging.ts        # Staging: sonar model, moderate limits\n    production.ts     # Prod: sonar-pro for deep queries, sonar for quick\n    index.ts          # Environment resolver + model router\n```\n\n### Step 2: Base Configuration with OpenAI SDK\n```typescript\n\u002F\u002F config\u002Fperplexity\u002Fbase.ts\nimport OpenAI from \"openai\";\n\nexport const PERPLEXITY_BASE_URL = \"https:\u002F\u002Fapi.perplexity.ai\";\n\nexport function createPerplexityClient(apiKey: string): OpenAI {\n  return new OpenAI({\n    apiKey,\n    baseURL: PERPLEXITY_BASE_URL,\n  });\n}\n```\n\n### Step 3: Environment-Specific Configs\n```typescript\n\u002F\u002F config\u002Fperplexity\u002Fdevelopment.ts\nexport const devConfig = {\n  apiKey: process.env.PERPLEXITY_API_KEY!,\n  defaultModel: \"sonar\",          \u002F\u002F always use cheapest model in dev\n  deepModel: \"sonar\",             \u002F\u002F no sonar-pro in dev (cost)\n  maxTokens: 512,  # 512 bytes\n  maxConcurrentRequests: 1,       \u002F\u002F stay within free tier 5 RPM\n};\n\n\u002F\u002F config\u002Fperplexity\u002Fstaging.ts\nexport const stagingConfig = {\n  apiKey: process.env.PERPLEXITY_API_KEY_STAGING!,\n  defaultModel: \"sonar\",\n  deepModel: \"sonar\",             \u002F\u002F keep sonar in staging to test cost behavior\n  maxTokens: 1024,  # 1024: 1 KB\n  maxConcurrentRequests: 2,\n};\n\n\u002F\u002F config\u002Fperplexity\u002Fproduction.ts\nexport const productionConfig = {\n  apiKey: process.env.PERPLEXITY_API_KEY_PROD!,\n  defaultModel: \"sonar\",          \u002F\u002F fast queries use sonar\n  deepModel: \"sonar-pro\",         \u002F\u002F research queries use sonar-pro\n  maxTokens: 4096,  # 4096: 4 KB\n  maxConcurrentRequests: 10,\n};\n```\n\n### Step 4: Environment Resolver with Model Router\n```typescript\n\u002F\u002F config\u002Fperplexity\u002Findex.ts\nimport { createPerplexityClient } from \".\u002Fbase\";\n\ntype SearchDepth = \"quick\" | \"deep\";\n\nexport function getPerplexityConfig() {\n  const env = process.env.NODE_ENV || \"development\";\n  const configs = { development: devConfig, staging: stagingConfig, production: productionConfig };\n  const config = configs[env as keyof typeof configs] || devConfig;\n\n  if (!config.apiKey) {\n    throw new Error(`PERPLEXITY_API_KEY not set for ${env}`);\n  }\n\n  return config;\n}\n\nexport function getPerplexityClient() {\n  const cfg = getPerplexityConfig();\n  return createPerplexityClient(cfg.apiKey);\n}\n\nexport function getModelForDepth(depth: SearchDepth): string {\n  const cfg = getPerplexityConfig();\n  return depth === \"deep\" ? cfg.deepModel : cfg.defaultModel;\n}\n```\n\n### Step 5: Usage with Environment-Aware Model Selection\n```typescript\n\u002F\u002F lib\u002Fsearch.ts\nimport { getPerplexityClient, getModelForDepth } from \"..\u002Fconfig\u002Fperplexity\";\n\nexport async function search(query: string, depth: \"quick\" | \"deep\" = \"quick\") {\n  const client = getPerplexityClient();\n  const model = getModelForDepth(depth);\n\n  const result = await client.chat.completions.create({\n    model,\n    messages: [\n      { role: \"system\", content: \"Provide accurate, well-sourced answers.\" },\n      { role: \"user\", content: query },\n    ],\n    max_tokens: depth === \"deep\" ? 2048 : 512,  # 512: 2048: 2 KB\n  });\n\n  return {\n    answer: result.choices[0].message.content,\n    model,\n    usage: result.usage,\n  };\n}\n```\n\n## Error Handling\n| Issue | Cause | Solution |\n|-------|-------|----------|\n| `401 Unauthorized` | Wrong API key for environment | Verify `PERPLEXITY_API_KEY` in `.env.local` |\n| `429 Too Many Requests` | Exceeding 5 RPM on free tier | Add request queuing or upgrade to paid plan |\n| `sonar-pro` errors in staging | Config sending deep queries to sonar-pro | Set `deepModel: \"sonar\"` in staging config |\n| High costs in dev | Using sonar-pro accidentally | Hardcode `defaultModel: \"sonar\"` in dev config |\n\n## Examples\n\n### Verify Which Model Is Active Per Environment\n```typescript\nimport { getModelForDepth, getPerplexityConfig } from \".\u002Fconfig\u002Fperplexity\";\n\nconst cfg = getPerplexityConfig();\nconsole.log(`Default model: ${cfg.defaultModel}`);\nconsole.log(`Deep search model: ${cfg.deepModel}`);\nconsole.log(`Max concurrent: ${cfg.maxConcurrentRequests}`);\n```\n\n### Cost Estimate Before Production Deploy\n```bash\n# Estimate cost: 10K quick queries\u002Fday at $1\u002F1K = $10\u002Fday\n# Estimate cost: 1K deep queries\u002Fday at $5\u002F1K = $5\u002Fday\necho \"Estimated daily cost: $15\"\n```\n\n## Resources\n- [Perplexity API Documentation](https:\u002F\u002Fdocs.perplexity.ai)\n- [Perplexity Models and Pricing](https:\u002F\u002Fdocs.perplexity.ai\u002Fguides\u002Fmodel-cards)\n- [Perplexity Rate Limits](https:\u002F\u002Fdocs.perplexity.ai\u002Fguides\u002Frate-limits)\n\n## Next Steps\nFor deployment configuration, see `perplexity-deploy-integration`.\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","# Perplexity Multi-Environment Setup\n\n## Overview\nPerplexity's OpenAI-compatible API uses the base URL `https:\u002F\u002Fapi.perplexity.ai`. The key per-environment configuration decisions are model selection and request limits.\n\n## Prerequisites\n- Perplexity API key from perplexity.ai\u002Fsettings\u002Fapi\n- OpenAI-compatible client library (`openai` npm package or equivalent)\n- Understanding of Sonar model tiers and their cost tradeoffs\n\n## Environment Strategy\n\n| Environment | Model | Cost\u002F1K requests | Rate Limit | Key Source |\n|-------------|-------|-----------------|------------|------------|\n| Development | `sonar` | ~$1 | 5 RPM (free tier) | `.env.local` |\n| Staging | `sonar` | ~$1 | 5-20 RPM | CI\u002FCD secrets |\n| Production | `sonar-pro` (deep), `sonar` (quick) | $1-$5 | 50+ RPM | Secret manager |\n\n## Instructions\n\n### Step 1: Configuration Structure\n```\nconfig\u002F\n  perplexity\u002F\n    base.ts           # OpenAI client pointing to Perplexity\n    development.ts    # Dev: sonar model, low rate limit\n    staging.ts        # Staging: sonar model, moderate limits\n    production.ts     # Prod: sonar-pro for deep queries, sonar for quick\n    index.ts          # Environment resolver + model router\n```\n\n### Step 2: Base Configuration with OpenAI SDK\n```typescript\n\u002F\u002F config\u002Fperplexity\u002Fbase.ts\nimport OpenAI from \"openai\";\n\nexport const PERPLEXITY_BASE_URL = \"https:\u002F\u002Fapi.perplexity.ai\";\n\nexport function createPerplexityClient(apiKey: string): OpenAI {\n  return new OpenAI({\n    apiKey,\n    baseURL: PERPLEXITY_BASE_URL,\n  });\n}\n```\n\n### Step 3: Environment-Specific Configs\n```typescript\n\u002F\u002F config\u002Fperplexity\u002Fdevelopment.ts\nexport const devConfig = {\n  apiKey: process.env.PERPLEXITY_API_KEY!,\n  defaultModel: \"sonar\",          \u002F\u002F always use cheapest model in dev\n  deepModel: \"sonar\",             \u002F\u002F no sonar-pro in dev (cost)\n  maxTokens: 512,  # 512 bytes\n  maxConcurrentRequests: 1,       \u002F\u002F stay within free tier 5 RPM\n};\n\n\u002F\u002F config\u002Fperplexity\u002Fstaging.ts\nexport const stagingConfig = {\n  apiKey: process.env.PERPLEXITY_API_KEY_STAGING!,\n  defaultModel: \"sonar\",\n  deepModel: \"sonar\",             \u002F\u002F keep sonar in staging to test cost behavior\n  maxTokens: 1024,  # 1024: 1 KB\n  maxConcurrentRequests: 2,\n};\n\n\u002F\u002F config\u002Fperplexity\u002Fproduction.ts\nexport const productionConfig = {\n  apiKey: process.env.PERPLEXITY_API_KEY_PROD!,\n  defaultModel: \"sonar\",          \u002F\u002F fast queries use sonar\n  deepModel: \"sonar-pro\",         \u002F\u002F research queries use sonar-pro\n  maxTokens: 4096,  # 4096: 4 KB\n  maxConcurrentRequests: 10,\n};\n```\n\n### Step 4: Environment Resolver with Model Router\n```typescript\n\u002F\u002F config\u002Fperplexity\u002Findex.ts\nimport { createPerplexityClient } from \".\u002Fbase\";\n\ntype SearchDepth = \"quick\" | \"deep\";\n\nexport function getPerplexityConfig() {\n  const env = process.env.NODE_ENV || \"development\";\n  const configs = { development: devConfig, staging: stagingConfig, production: productionConfig };\n  const config = configs[env as keyof typeof configs] || devConfig;\n\n  if (!config.apiKey) {\n    throw new Error(`PERPLEXITY_API_KEY not set for ${env}`);\n  }\n\n  return config;\n}\n\nexport function getPerplexityClient() {\n  const cfg = getPerplexityConfig();\n  return createPerplexityClient(cfg.apiKey);\n}\n\nexport function getModelForDepth(depth: SearchDepth): string {\n  const cfg = getPerplexityConfig();\n  return depth === \"deep\" ? cfg.deepModel : cfg.defaultModel;\n}\n```\n\n### Step 5: Usage with Environment-Aware Model Selection\n```typescript\n\u002F\u002F lib\u002Fsearch.ts\nimport { getPerplexityClient, getModelForDepth } from \"..\u002Fconfig\u002Fperplexity\";\n\nexport async function search(query: string, depth: \"quick\" | \"deep\" = \"quick\") {\n  const client = getPerplexityClient();\n  const model = getModelForDepth(depth);\n\n  const result = await client.chat.completions.create({\n    model,\n    messages: [\n      { role: \"system\", content: \"Provide accurate, well-sourced answers.\" },\n      { role: \"user\", content: query },\n    ],\n    max_tokens: depth === \"deep\" ? 2048 : 512,  # 512: 2048: 2 KB\n  });\n\n  return {\n    answer: result.choices[0].message.content,\n    model,\n    usage: result.usage,\n  };\n}\n```\n\n## Error Handling\n| Issue | Cause | Solution |\n|-------|-------|----------|\n| `401 Unauthorized` | Wrong API key for environment | Verify `PERPLEXITY_API_KEY` in `.env.local` |\n| `429 Too Many Requests` | Exceeding 5 RPM on free tier | Add request queuing or upgrade to paid plan |\n| `sonar-pro` errors in staging | Config sending deep queries to sonar-pro | Set `deepModel: \"sonar\"` in staging config |\n| High costs in dev | Using sonar-pro accidentally | Hardcode `defaultModel: \"sonar\"` in dev config |\n\n## Examples\n\n### Verify Which Model Is Active Per Environment\n```typescript\nimport { getModelForDepth, getPerplexityConfig } from \".\u002Fconfig\u002Fperplexity\";\n\nconst cfg = getPerplexityConfig();\nconsole.log(`Default model: ${cfg.defaultModel}`);\nconsole.log(`Deep search model: ${cfg.deepModel}`);\nconsole.log(`Max concurrent: ${cfg.maxConcurrentRequests}`);\n```\n\n### Cost Estimate Before Production Deploy\n```bash\n# Estimate cost: 10K quick queries\u002Fday at $1\u002F1K = $10\u002Fday\n# Estimate cost: 1K deep queries\u002Fday at $5\u002F1K = $5\u002Fday\necho \"Estimated daily cost: $15\"\n```\n\n## Resources\n- [Perplexity API Documentation](https:\u002F\u002Fdocs.perplexity.ai)\n- [Perplexity Models and Pricing](https:\u002F\u002Fdocs.perplexity.ai\u002Fguides\u002Fmodel-cards)\n- [Perplexity Rate Limits](https:\u002F\u002Fdocs.perplexity.ai\u002Fguides\u002Frate-limits)\n\n## Next Steps\nFor deployment configuration, see `perplexity-deploy-integration`.\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","Configure Perplexity Sonar API across development, staging, and production environments.\nUse when setting up multi-environment search integrations, managing model selection\nper environment, or controlling cost through sonar vs sonar-pro routing by env.\nTrigger with phrases like \"perplexity environments\", \"perplexity staging\",\n\"perplexity dev prod\", \"perplexity environment setup\", \"perplexity model by env\".\n","Read, Write, Edit, Bash(aws:*), Bash(gcloud:*), Bash(vault:*)","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 perplexity-multi-env-setup",{"tool":41,"command":42},"bunx","bunx skills add SamuelChien\u002Fmega-skills-collection --skill perplexity-multi-env-setup",{"tool":44,"command":45},"pnpm","pnpm dlx skills add SamuelChien\u002Fmega-skills-collection --skill perplexity-multi-env-setup","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fperplexity-multi-env-setup\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",[],[]]