[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7564MPF04Y12MFS5ZCQGHD5":3,"skill-same:01M7564MPF04Y12MFS5ZCQGHD5":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},"01M7564MPF04Y12MFS5ZCQGHD5","perplexity-reliability-patterns",null,"Implement Perplexity reliability patterns including circuit breakers, idempotency, and graceful degradation.\nUse when building fault-tolerant Perplexity integrations, implementing retry strategies,\nor adding resilience to production Perplexity services.\nTrigger with phrases like \"perplexity reliability\", \"perplexity circuit breaker\",\n\"perplexity idempotent\", \"perplexity resilience\", \"perplexity fallback\", \"perplexity bulkhead\".","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-reliability-patterns\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: perplexity-reliability-patterns\ndescription: |\n  Implement Perplexity reliability patterns including circuit breakers, idempotency, and graceful degradation.\n  Use when building fault-tolerant Perplexity integrations, implementing retry strategies,\n  or adding resilience to production Perplexity services.\n  Trigger with phrases like \"perplexity reliability\", \"perplexity circuit breaker\",\n  \"perplexity idempotent\", \"perplexity resilience\", \"perplexity fallback\", \"perplexity bulkhead\".\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# Perplexity Reliability Patterns\n\n## Overview\nProduction reliability patterns for Perplexity Sonar API integrations. Perplexity performs live web searches per request, making response times variable and dependent on search complexity -- unlike static LLM inference.\n\n## Prerequisites\n- Perplexity API key configured\n- Caching layer (Redis recommended)\n- Understanding of search-augmented generation latency\n\n## Instructions\n\n### Step 1: Cache Identical Queries\n\nPerplexity's web search is expensive per call. Cache results for repeated queries within a time window.\n\n```python\nimport hashlib, json\n\nclass PerplexityCache:\n    def __init__(self, redis_client, ttl=600):  # 600: timeout: 10 minutes\n        self.r = redis_client\n        self.ttl = ttl\n\n    def get_or_search(self, client, messages, model=\"sonar\", **kwargs):\n        key = self._cache_key(messages, model, **kwargs)\n        cached = self.r.get(key)\n        if cached:\n            return json.loads(cached)\n        result = client.chat.completions.create(\n            model=model, messages=messages, **kwargs\n        )\n        self.r.setex(key, self.ttl, json.dumps(result.to_dict()))\n        return result\n\n    def _cache_key(self, messages, model, **kwargs):\n        data = json.dumps({\"m\": messages, \"model\": model, **kwargs}, sort_keys=True)\n        return f\"pplx:{hashlib.sha256(data.encode()).hexdigest()}\"\n```\n\n### Step 2: Model Tier Fallback\n\nIf `sonar-pro` times out or errors, fall back to `sonar` for a faster but shallower response.\n\n```python\ndef resilient_search(client, messages, timeout=30):\n    try:\n        return client.chat.completions.create(\n            model=\"sonar-pro\", messages=messages, timeout=timeout\n        )\n    except Exception:\n        return client.chat.completions.create(\n            model=\"sonar\", messages=messages, timeout=15\n        )\n```\n\n### Step 3: Streaming with Timeout Protection\n\nPerplexity streams can stall on complex searches. Set per-chunk timeouts.\n\n```python\nimport time\n\ndef stream_with_timeout(client, messages, chunk_timeout=10):\n    stream = client.chat.completions.create(\n        model=\"sonar\", messages=messages, stream=True\n    )\n    last_chunk = time.time()\n    full_response = \"\"\n    citations = []\n\n    for chunk in stream:\n        if time.time() - last_chunk > chunk_timeout:\n            raise TimeoutError(\"Stream stalled\")\n        last_chunk = time.time()\n        delta = chunk.choices[0].delta.content or \"\"\n        full_response += delta\n        if hasattr(chunk, 'citations'):\n            citations = chunk.citations\n        yield delta\n\n    return full_response, citations\n```\n\n### Step 4: Citation Validation\n\nVerify cited URLs are accessible before presenting to users.\n\n```python\nimport aiohttp\n\nasync def validate_citations(citations: list[str]) -> list[dict]:\n    validated = []\n    async with aiohttp.ClientSession() as session:\n        for url in citations[:5]:  # limit to top 5\n            try:\n                async with session.head(url, timeout=aiohttp.ClientTimeout(total=5)) as r:\n                    validated.append({\"url\": url, \"status\": r.status, \"valid\": r.status \u003C 400})  # HTTP 400 Bad Request\n            except:\n                validated.append({\"url\": url, \"status\": 0, \"valid\": False})\n    return validated\n```\n\n## Error Handling\n| Issue | Cause | Solution |\n|-------|-------|----------|\n| Slow responses (>15s) | Complex search query | Use sonar instead of sonar-pro |\n| Stream stalls | Search taking too long | Per-chunk timeout detection |\n| Stale results | Cached data too old | Reduce TTL for time-sensitive queries |\n| Broken citation links | Source pages moved | Validate URLs before displaying |\n\n## Examples\n\n\n**Basic usage**: Apply perplexity reliability patterns to a standard project setup with default configuration options.\n\n**Advanced scenario**: Customize perplexity reliability patterns for production environments with multiple constraints and team-specific requirements.\n\n## Resources\n- [Perplexity API Docs](https:\u002F\u002Fdocs.perplexity.ai)\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 Reliability Patterns\n\n## Overview\nProduction reliability patterns for Perplexity Sonar API integrations. Perplexity performs live web searches per request, making response times variable and dependent on search complexity -- unlike static LLM inference.\n\n## Prerequisites\n- Perplexity API key configured\n- Caching layer (Redis recommended)\n- Understanding of search-augmented generation latency\n\n## Instructions\n\n### Step 1: Cache Identical Queries\n\nPerplexity's web search is expensive per call. Cache results for repeated queries within a time window.\n\n```python\nimport hashlib, json\n\nclass PerplexityCache:\n    def __init__(self, redis_client, ttl=600):  # 600: timeout: 10 minutes\n        self.r = redis_client\n        self.ttl = ttl\n\n    def get_or_search(self, client, messages, model=\"sonar\", **kwargs):\n        key = self._cache_key(messages, model, **kwargs)\n        cached = self.r.get(key)\n        if cached:\n            return json.loads(cached)\n        result = client.chat.completions.create(\n            model=model, messages=messages, **kwargs\n        )\n        self.r.setex(key, self.ttl, json.dumps(result.to_dict()))\n        return result\n\n    def _cache_key(self, messages, model, **kwargs):\n        data = json.dumps({\"m\": messages, \"model\": model, **kwargs}, sort_keys=True)\n        return f\"pplx:{hashlib.sha256(data.encode()).hexdigest()}\"\n```\n\n### Step 2: Model Tier Fallback\n\nIf `sonar-pro` times out or errors, fall back to `sonar` for a faster but shallower response.\n\n```python\ndef resilient_search(client, messages, timeout=30):\n    try:\n        return client.chat.completions.create(\n            model=\"sonar-pro\", messages=messages, timeout=timeout\n        )\n    except Exception:\n        return client.chat.completions.create(\n            model=\"sonar\", messages=messages, timeout=15\n        )\n```\n\n### Step 3: Streaming with Timeout Protection\n\nPerplexity streams can stall on complex searches. Set per-chunk timeouts.\n\n```python\nimport time\n\ndef stream_with_timeout(client, messages, chunk_timeout=10):\n    stream = client.chat.completions.create(\n        model=\"sonar\", messages=messages, stream=True\n    )\n    last_chunk = time.time()\n    full_response = \"\"\n    citations = []\n\n    for chunk in stream:\n        if time.time() - last_chunk > chunk_timeout:\n            raise TimeoutError(\"Stream stalled\")\n        last_chunk = time.time()\n        delta = chunk.choices[0].delta.content or \"\"\n        full_response += delta\n        if hasattr(chunk, 'citations'):\n            citations = chunk.citations\n        yield delta\n\n    return full_response, citations\n```\n\n### Step 4: Citation Validation\n\nVerify cited URLs are accessible before presenting to users.\n\n```python\nimport aiohttp\n\nasync def validate_citations(citations: list[str]) -> list[dict]:\n    validated = []\n    async with aiohttp.ClientSession() as session:\n        for url in citations[:5]:  # limit to top 5\n            try:\n                async with session.head(url, timeout=aiohttp.ClientTimeout(total=5)) as r:\n                    validated.append({\"url\": url, \"status\": r.status, \"valid\": r.status \u003C 400})  # HTTP 400 Bad Request\n            except:\n                validated.append({\"url\": url, \"status\": 0, \"valid\": False})\n    return validated\n```\n\n## Error Handling\n| Issue | Cause | Solution |\n|-------|-------|----------|\n| Slow responses (>15s) | Complex search query | Use sonar instead of sonar-pro |\n| Stream stalls | Search taking too long | Per-chunk timeout detection |\n| Stale results | Cached data too old | Reduce TTL for time-sensitive queries |\n| Broken citation links | Source pages moved | Validate URLs before displaying |\n\n## Examples\n\n\n**Basic usage**: Apply perplexity reliability patterns to a standard project setup with default configuration options.\n\n**Advanced scenario**: Customize perplexity reliability patterns for production environments with multiple constraints and team-specific requirements.\n\n## Resources\n- [Perplexity API Docs](https:\u002F\u002Fdocs.perplexity.ai)\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 Perplexity reliability patterns including circuit breakers, idempotency, and graceful degradation.\nUse when building fault-tolerant Perplexity integrations, implementing retry strategies,\nor adding resilience to production Perplexity services.\nTrigger with phrases like \"perplexity reliability\", \"perplexity circuit breaker\",\n\"perplexity idempotent\", \"perplexity resilience\", \"perplexity fallback\", \"perplexity bulkhead\".\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 perplexity-reliability-patterns",{"tool":41,"command":42},"bunx","bunx skills add SamuelChien\u002Fmega-skills-collection --skill perplexity-reliability-patterns",{"tool":44,"command":45},"pnpm","pnpm dlx skills add SamuelChien\u002Fmega-skills-collection --skill perplexity-reliability-patterns","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fperplexity-reliability-patterns\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",[],[]]