[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7913QBFF7WJ3JYFSM35N1AT":3,"skill-same:01M7913QBFF7WJ3JYFSM35N1AT":56},{"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":33,"commitSha":34,"skillDirectory":35,"forksCount":36,"repositoryHtmlUrl":37,"repositoryHomepageUrl":6,"ownerHtmlUrl":38,"ownerBlogUrl":39,"ownerDescription":40,"updatedAt":41,"install":42,"resources":55},"01M7913QBFF7WJ3JYFSM35N1AT","groq-reference-architecture",null,"Implement Groq reference architecture with model routing, streaming pipelines, and fallbacks.\nUse when designing new Groq integrations, reviewing project structure,\nor establishing architecture standards for Groq applications.\nTrigger with phrases like \"groq architecture\", \"groq best practices\",\n\"groq project structure\", \"how to organize groq\", \"groq design\".","jukeyman\u002Fjukeyman-skills","jukeyman","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F142960420?v=4","01M78FR4Y3DHMMCBCC0GXXNB3F","RICK JEFFERSON","01M78FR4Z8RVQRAD31Y5J7V6EB",1,"MIT","https:\u002F\u002Fgithub.com\u002Fjukeyman\u002Fjukeyman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsaas-packs--groq-pack--groq-reference-architecture\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: groq-reference-architecture\ndescription: |\n  Implement Groq reference architecture with model routing, streaming pipelines, and fallbacks.\n  Use when designing new Groq integrations, reviewing project structure,\n  or establishing architecture standards for Groq applications.\n  Trigger with phrases like \"groq architecture\", \"groq best practices\",\n  \"groq project structure\", \"how to organize groq\", \"groq design\".\nallowed-tools: Read, Grep\nversion: 1.0.0\nlicense: MIT\nauthor: Jeremy Longshore \u003Cjeremy@intentsolutions.io>\ncompatible-with: claude-code, codex, openclaw\ntags: [saas, groq, groq-reference]\n---\n# Groq Reference Architecture\n\n## Overview\nProduction architecture for applications built on Groq's LPU inference API. Covers model routing by latency requirements, streaming pipelines, multi-provider fallback, and the middleware layer that ties it together.\n\n## Architecture Diagram\n\n```\n┌──────────────────────────────────────────────────────────────┐\n│                     Application Layer                         │\n│  Chat UI  │  API Backend  │  Batch Processor  │  Agent       │\n└─────┬─────┴──────┬────────┴────────┬──────────┴──────┬───────┘\n      │            │                 │                 │\n      ▼            ▼                 ▼                 ▼\n┌──────────────────────────────────────────────────────────────┐\n│                    Groq Service Layer                         │\n│  ┌─────────────┐  ┌────────────┐  ┌─────────────────────┐   │\n│  │ Model Router │  │ Middleware │  │ Fallback Chain      │   │\n│  │             │  │            │  │                     │   │\n│  │ speed →     │  │ Cache      │  │ Groq (primary)      │   │\n│  │   8b-instant│  │ Rate Guard │  │   ↓ 429\u002F5xx         │   │\n│  │ quality →   │  │ Metrics    │  │ Groq (fallback model)│  │\n│  │   70b-versa.│  │ Logging    │  │   ↓ still failing    │   │\n│  │ vision →    │  │ Retry      │  │ OpenAI (backup)     │   │\n│  │   llama-4   │  │            │  │   ↓ also failing     │   │\n│  │ audio →     │  │            │  │ Graceful degrade    │   │\n│  │   whisper   │  │            │  │                     │   │\n│  └─────────────┘  └────────────┘  └─────────────────────┘   │\n└──────────────────────────────────────────────────────────────┘\n```\n\n## Project Structure\n```\nsrc\u002F\n├── groq\u002F\n│   ├── client.ts            # Singleton Groq client\n│   ├── models.ts            # Model constants and capabilities\n│   ├── router.ts            # Model selection logic\n│   ├── middleware.ts         # Cache, rate limit, metrics\n│   ├── fallback.ts          # Multi-provider fallback chain\n│   └── types.ts             # Shared types\n├── services\u002F\n│   ├── chat.ts              # Chat completion service\n│   ├── transcription.ts     # Audio transcription (Whisper)\n│   ├── extraction.ts        # Structured data extraction\n│   └── batch.ts             # Batch processing service\n└── api\u002F\n    ├── chat.ts              # HTTP endpoint\n    ├── transcribe.ts        # Audio endpoint\n    └── health.ts            # Health check\n```\n\n## Instructions\n\n### Step 1: Model Registry\n```typescript\n\u002F\u002F src\u002Fgroq\u002Fmodels.ts\nexport interface ModelSpec {\n  id: string;\n  tier: \"speed\" | \"quality\" | \"vision\" | \"audio\";\n  contextWindow: number;\n  maxOutput: number;\n  speedTokPerSec: number;\n  inputCostPer1M: number;\n  outputCostPer1M: number;\n  capabilities: (\"text\" | \"tools\" | \"json\" | \"vision\" | \"audio\")[];\n}\n\nexport const MODELS: Record\u003Cstring, ModelSpec> = {\n  \"llama-3.1-8b-instant\": {\n    id: \"llama-3.1-8b-instant\",\n    tier: \"speed\",\n    contextWindow: 131_072,\n    maxOutput: 8_192,\n    speedTokPerSec: 560,\n    inputCostPer1M: 0.05,\n    outputCostPer1M: 0.08,\n    capabilities: [\"text\", \"tools\", \"json\"],\n  },\n  \"llama-3.3-70b-versatile\": {\n    id: \"llama-3.3-70b-versatile\",\n    tier: \"quality\",\n    contextWindow: 131_072,\n    maxOutput: 32_768,\n    speedTokPerSec: 280,\n    inputCostPer1M: 0.59,\n    outputCostPer1M: 0.79,\n    capabilities: [\"text\", \"tools\", \"json\"],\n  },\n  \"meta-llama\u002Fllama-4-scout-17b-16e-instruct\": {\n    id: \"meta-llama\u002Fllama-4-scout-17b-16e-instruct\",\n    tier: \"vision\",\n    contextWindow: 131_072,\n    maxOutput: 8_192,\n    speedTokPerSec: 460,\n    inputCostPer1M: 0.11,\n    outputCostPer1M: 0.34,\n    capabilities: [\"text\", \"tools\", \"json\", \"vision\"],\n  },\n  \"whisper-large-v3-turbo\": {\n    id: \"whisper-large-v3-turbo\",\n    tier: \"audio\",\n    contextWindow: 0,\n    maxOutput: 0,\n    speedTokPerSec: 0,\n    inputCostPer1M: 0,\n    outputCostPer1M: 0,\n    capabilities: [\"audio\"],\n  },\n};\n```\n\n### Step 2: Model Router\n```typescript\n\u002F\u002F src\u002Fgroq\u002Frouter.ts\nimport { MODELS, ModelSpec } from \".\u002Fmodels\";\n\ninterface RoutingRequest {\n  maxLatencyMs?: number;\n  needsVision?: boolean;\n  needsTools?: boolean;\n  needsJSON?: boolean;\n  contextLength?: number;\n  costSensitive?: boolean;\n}\n\nexport function selectModel(req: RoutingRequest): ModelSpec {\n  if (req.needsVision) return MODELS[\"meta-llama\u002Fllama-4-scout-17b-16e-instruct\"];\n\n  if (req.costSensitive || (req.maxLatencyMs && req.maxLatencyMs \u003C 100)) {\n    return MODELS[\"llama-3.1-8b-instant\"];\n  }\n\n  if (req.needsTools || req.needsJSON) {\n    return MODELS[\"llama-3.3-70b-versatile\"];\n  }\n\n  \u002F\u002F Default: speed tier\n  return MODELS[\"llama-3.1-8b-instant\"];\n}\n```\n\n### Step 3: Middleware Layer\n```typescript\n\u002F\u002F src\u002Fgroq\u002Fmiddleware.ts\nimport Groq from \"groq-sdk\";\nimport { LRUCache } from \"lru-cache\";\nimport { createHash } from \"crypto\";\n\nconst cache = new LRUCache\u003Cstring, any>({ max: 500, ttl: 10 * 60_000 });\n\nexport async function completionWithMiddleware(\n  groq: Groq,\n  model: string,\n  messages: any[],\n  options?: { maxTokens?: number; temperature?: number; stream?: boolean }\n) {\n  const temp = options?.temperature ?? 0.7;\n\n  \u002F\u002F Cache check (only for deterministic requests)\n  if (temp === 0 && !options?.stream) {\n    const key = createHash(\"sha256\").update(JSON.stringify({ model, messages })).digest(\"hex\");\n    const cached = cache.get(key);\n    if (cached) return cached;\n  }\n\n  \u002F\u002F Metrics\n  const start = performance.now();\n\n  const response = await groq.chat.completions.create({\n    model,\n    messages,\n    max_tokens: options?.maxTokens ?? 1024,\n    temperature: temp,\n    stream: options?.stream ?? false,\n  });\n\n  const latency = performance.now() - start;\n\n  \u002F\u002F Emit metrics\n  emitMetrics({\n    model,\n    latencyMs: Math.round(latency),\n    tokens: (response as any).usage?.total_tokens ?? 0,\n    cached: false,\n  });\n\n  \u002F\u002F Cache deterministic responses\n  if (temp === 0 && !options?.stream) {\n    const key = createHash(\"sha256\").update(JSON.stringify({ model, messages })).digest(\"hex\");\n    cache.set(key, response);\n  }\n\n  return response;\n}\n\nfunction emitMetrics(data: any) {\n  \u002F\u002F Plug in your metrics system: Prometheus, Datadog, etc.\n  console.log(`[groq-metrics] ${JSON.stringify(data)}`);\n}\n```\n\n### Step 4: Fallback Chain\n```typescript\n\u002F\u002F src\u002Fgroq\u002Ffallback.ts\nimport Groq from \"groq-sdk\";\n\nexport async function completionWithFallback(\n  groq: Groq,\n  messages: any[],\n  options?: { primaryModel?: string; maxTokens?: number }\n) {\n  const primary = options?.primaryModel || \"llama-3.3-70b-versatile\";\n  const fallbackModel = \"llama-3.1-8b-instant\";\n\n  \u002F\u002F Attempt 1: Primary model\n  try {\n    return await groq.chat.completions.create({\n      model: primary,\n      messages,\n      max_tokens: options?.maxTokens ?? 1024,\n    });\n  } catch (err: any) {\n    if (err.status !== 429 && err.status \u003C 500) throw err;\n    console.warn(`Primary model ${primary} failed (${err.status}), trying fallback`);\n  }\n\n  \u002F\u002F Attempt 2: Fallback model (different rate limit pool)\n  try {\n    return await groq.chat.completions.create({\n      model: fallbackModel,\n      messages,\n      max_tokens: options?.maxTokens ?? 1024,\n    });\n  } catch (err: any) {\n    console.warn(`Groq fallback also failed (${err.status})`);\n  }\n\n  \u002F\u002F Attempt 3: Graceful degradation\n  return {\n    choices: [{\n      message: {\n        role: \"assistant\" as const,\n        content: \"Service temporarily unavailable. Please try again in a moment.\",\n      },\n      finish_reason: \"stop\" as const,\n    }],\n    model: \"fallback\",\n    usage: { prompt_tokens: 0, completion_tokens: 0, total_tokens: 0 },\n  };\n}\n```\n\n### Step 5: Streaming Pipeline\n```typescript\n\u002F\u002F src\u002Fgroq\u002Fstreaming.ts\nimport Groq from \"groq-sdk\";\n\nexport async function* streamCompletion(\n  groq: Groq,\n  messages: any[],\n  model = \"llama-3.3-70b-versatile\"\n): AsyncGenerator\u003C{ type: \"token\" | \"done\" | \"error\"; content?: string; error?: string }> {\n  try {\n    const stream = await groq.chat.completions.create({\n      model,\n      messages,\n      stream: true,\n      max_tokens: 2048,\n    });\n\n    for await (const chunk of stream) {\n      const content = chunk.choices[0]?.delta?.content;\n      if (content) yield { type: \"token\", content };\n    }\n\n    yield { type: \"done\" };\n  } catch (err: any) {\n    yield { type: \"error\", error: err.message };\n  }\n}\n```\n\n## Integration Patterns\n\n| Pattern | When to Use | Groq Feature |\n|---------|-------------|-------------|\n| Direct completion | Simple request\u002Fresponse | `chat.completions.create` |\n| Streaming SSE | Real-time chat UI | `stream: true` |\n| Tool calling | Agent with function execution | `tools` parameter |\n| JSON extraction | Structured data from text | `response_format: json_object` |\n| Batch processing | High-volume document processing | Queue + rate limiting |\n| Audio transcription | Voice input | `audio.transcriptions.create` |\n| Vision analysis | Image understanding | Llama 4 Scout\u002FMaverick |\n\n## Error Handling\n| Issue | Cause | Solution |\n|-------|-------|----------|\n| 429 on primary model | RPM\u002FTPM exceeded | Fall back to different model |\n| High latency | Wrong model tier | Route to `8b-instant` for latency-critical paths |\n| Context overflow | Input > 128K tokens | Truncate or chunk input |\n| Vision errors | Wrong model for images | Use Llama 4 Scout full model path |\n\n## Resources\n- [Groq API Documentation](https:\u002F\u002Fconsole.groq.com\u002Fdocs)\n- [Groq Models](https:\u002F\u002Fconsole.groq.com\u002Fdocs\u002Fmodels)\n- [Groq Rate Limits](https:\u002F\u002Fconsole.groq.com\u002Fdocs\u002Frate-limits)\n- [Groq Pricing](https:\u002F\u002Fgroq.com\u002Fpricing)\n\n## Next Steps\nFor multi-environment deployment, see `groq-multi-env-setup`.\n","# Groq Reference Architecture\n\n## Overview\nProduction architecture for applications built on Groq's LPU inference API. Covers model routing by latency requirements, streaming pipelines, multi-provider fallback, and the middleware layer that ties it together.\n\n## Architecture Diagram\n\n```\n┌──────────────────────────────────────────────────────────────┐\n│                     Application Layer                         │\n│  Chat UI  │  API Backend  │  Batch Processor  │  Agent       │\n└─────┬─────┴──────┬────────┴────────┬──────────┴──────┬───────┘\n      │            │                 │                 │\n      ▼            ▼                 ▼                 ▼\n┌──────────────────────────────────────────────────────────────┐\n│                    Groq Service Layer                         │\n│  ┌─────────────┐  ┌────────────┐  ┌─────────────────────┐   │\n│  │ Model Router │  │ Middleware │  │ Fallback Chain      │   │\n│  │             │  │            │  │                     │   │\n│  │ speed →     │  │ Cache      │  │ Groq (primary)      │   │\n│  │   8b-instant│  │ Rate Guard │  │   ↓ 429\u002F5xx         │   │\n│  │ quality →   │  │ Metrics    │  │ Groq (fallback model)│  │\n│  │   70b-versa.│  │ Logging    │  │   ↓ still failing    │   │\n│  │ vision →    │  │ Retry      │  │ OpenAI (backup)     │   │\n│  │   llama-4   │  │            │  │   ↓ also failing     │   │\n│  │ audio →     │  │            │  │ Graceful degrade    │   │\n│  │   whisper   │  │            │  │                     │   │\n│  └─────────────┘  └────────────┘  └─────────────────────┘   │\n└──────────────────────────────────────────────────────────────┘\n```\n\n## Project Structure\n```\nsrc\u002F\n├── groq\u002F\n│   ├── client.ts            # Singleton Groq client\n│   ├── models.ts            # Model constants and capabilities\n│   ├── router.ts            # Model selection logic\n│   ├── middleware.ts         # Cache, rate limit, metrics\n│   ├── fallback.ts          # Multi-provider fallback chain\n│   └── types.ts             # Shared types\n├── services\u002F\n│   ├── chat.ts              # Chat completion service\n│   ├── transcription.ts     # Audio transcription (Whisper)\n│   ├── extraction.ts        # Structured data extraction\n│   └── batch.ts             # Batch processing service\n└── api\u002F\n    ├── chat.ts              # HTTP endpoint\n    ├── transcribe.ts        # Audio endpoint\n    └── health.ts            # Health check\n```\n\n## Instructions\n\n### Step 1: Model Registry\n```typescript\n\u002F\u002F src\u002Fgroq\u002Fmodels.ts\nexport interface ModelSpec {\n  id: string;\n  tier: \"speed\" | \"quality\" | \"vision\" | \"audio\";\n  contextWindow: number;\n  maxOutput: number;\n  speedTokPerSec: number;\n  inputCostPer1M: number;\n  outputCostPer1M: number;\n  capabilities: (\"text\" | \"tools\" | \"json\" | \"vision\" | \"audio\")[];\n}\n\nexport const MODELS: Record\u003Cstring, ModelSpec> = {\n  \"llama-3.1-8b-instant\": {\n    id: \"llama-3.1-8b-instant\",\n    tier: \"speed\",\n    contextWindow: 131_072,\n    maxOutput: 8_192,\n    speedTokPerSec: 560,\n    inputCostPer1M: 0.05,\n    outputCostPer1M: 0.08,\n    capabilities: [\"text\", \"tools\", \"json\"],\n  },\n  \"llama-3.3-70b-versatile\": {\n    id: \"llama-3.3-70b-versatile\",\n    tier: \"quality\",\n    contextWindow: 131_072,\n    maxOutput: 32_768,\n    speedTokPerSec: 280,\n    inputCostPer1M: 0.59,\n    outputCostPer1M: 0.79,\n    capabilities: [\"text\", \"tools\", \"json\"],\n  },\n  \"meta-llama\u002Fllama-4-scout-17b-16e-instruct\": {\n    id: \"meta-llama\u002Fllama-4-scout-17b-16e-instruct\",\n    tier: \"vision\",\n    contextWindow: 131_072,\n    maxOutput: 8_192,\n    speedTokPerSec: 460,\n    inputCostPer1M: 0.11,\n    outputCostPer1M: 0.34,\n    capabilities: [\"text\", \"tools\", \"json\", \"vision\"],\n  },\n  \"whisper-large-v3-turbo\": {\n    id: \"whisper-large-v3-turbo\",\n    tier: \"audio\",\n    contextWindow: 0,\n    maxOutput: 0,\n    speedTokPerSec: 0,\n    inputCostPer1M: 0,\n    outputCostPer1M: 0,\n    capabilities: [\"audio\"],\n  },\n};\n```\n\n### Step 2: Model Router\n```typescript\n\u002F\u002F src\u002Fgroq\u002Frouter.ts\nimport { MODELS, ModelSpec } from \".\u002Fmodels\";\n\ninterface RoutingRequest {\n  maxLatencyMs?: number;\n  needsVision?: boolean;\n  needsTools?: boolean;\n  needsJSON?: boolean;\n  contextLength?: number;\n  costSensitive?: boolean;\n}\n\nexport function selectModel(req: RoutingRequest): ModelSpec {\n  if (req.needsVision) return MODELS[\"meta-llama\u002Fllama-4-scout-17b-16e-instruct\"];\n\n  if (req.costSensitive || (req.maxLatencyMs && req.maxLatencyMs \u003C 100)) {\n    return MODELS[\"llama-3.1-8b-instant\"];\n  }\n\n  if (req.needsTools || req.needsJSON) {\n    return MODELS[\"llama-3.3-70b-versatile\"];\n  }\n\n  \u002F\u002F Default: speed tier\n  return MODELS[\"llama-3.1-8b-instant\"];\n}\n```\n\n### Step 3: Middleware Layer\n```typescript\n\u002F\u002F src\u002Fgroq\u002Fmiddleware.ts\nimport Groq from \"groq-sdk\";\nimport { LRUCache } from \"lru-cache\";\nimport { createHash } from \"crypto\";\n\nconst cache = new LRUCache\u003Cstring, any>({ max: 500, ttl: 10 * 60_000 });\n\nexport async function completionWithMiddleware(\n  groq: Groq,\n  model: string,\n  messages: any[],\n  options?: { maxTokens?: number; temperature?: number; stream?: boolean }\n) {\n  const temp = options?.temperature ?? 0.7;\n\n  \u002F\u002F Cache check (only for deterministic requests)\n  if (temp === 0 && !options?.stream) {\n    const key = createHash(\"sha256\").update(JSON.stringify({ model, messages })).digest(\"hex\");\n    const cached = cache.get(key);\n    if (cached) return cached;\n  }\n\n  \u002F\u002F Metrics\n  const start = performance.now();\n\n  const response = await groq.chat.completions.create({\n    model,\n    messages,\n    max_tokens: options?.maxTokens ?? 1024,\n    temperature: temp,\n    stream: options?.stream ?? false,\n  });\n\n  const latency = performance.now() - start;\n\n  \u002F\u002F Emit metrics\n  emitMetrics({\n    model,\n    latencyMs: Math.round(latency),\n    tokens: (response as any).usage?.total_tokens ?? 0,\n    cached: false,\n  });\n\n  \u002F\u002F Cache deterministic responses\n  if (temp === 0 && !options?.stream) {\n    const key = createHash(\"sha256\").update(JSON.stringify({ model, messages })).digest(\"hex\");\n    cache.set(key, response);\n  }\n\n  return response;\n}\n\nfunction emitMetrics(data: any) {\n  \u002F\u002F Plug in your metrics system: Prometheus, Datadog, etc.\n  console.log(`[groq-metrics] ${JSON.stringify(data)}`);\n}\n```\n\n### Step 4: Fallback Chain\n```typescript\n\u002F\u002F src\u002Fgroq\u002Ffallback.ts\nimport Groq from \"groq-sdk\";\n\nexport async function completionWithFallback(\n  groq: Groq,\n  messages: any[],\n  options?: { primaryModel?: string; maxTokens?: number }\n) {\n  const primary = options?.primaryModel || \"llama-3.3-70b-versatile\";\n  const fallbackModel = \"llama-3.1-8b-instant\";\n\n  \u002F\u002F Attempt 1: Primary model\n  try {\n    return await groq.chat.completions.create({\n      model: primary,\n      messages,\n      max_tokens: options?.maxTokens ?? 1024,\n    });\n  } catch (err: any) {\n    if (err.status !== 429 && err.status \u003C 500) throw err;\n    console.warn(`Primary model ${primary} failed (${err.status}), trying fallback`);\n  }\n\n  \u002F\u002F Attempt 2: Fallback model (different rate limit pool)\n  try {\n    return await groq.chat.completions.create({\n      model: fallbackModel,\n      messages,\n      max_tokens: options?.maxTokens ?? 1024,\n    });\n  } catch (err: any) {\n    console.warn(`Groq fallback also failed (${err.status})`);\n  }\n\n  \u002F\u002F Attempt 3: Graceful degradation\n  return {\n    choices: [{\n      message: {\n        role: \"assistant\" as const,\n        content: \"Service temporarily unavailable. Please try again in a moment.\",\n      },\n      finish_reason: \"stop\" as const,\n    }],\n    model: \"fallback\",\n    usage: { prompt_tokens: 0, completion_tokens: 0, total_tokens: 0 },\n  };\n}\n```\n\n### Step 5: Streaming Pipeline\n```typescript\n\u002F\u002F src\u002Fgroq\u002Fstreaming.ts\nimport Groq from \"groq-sdk\";\n\nexport async function* streamCompletion(\n  groq: Groq,\n  messages: any[],\n  model = \"llama-3.3-70b-versatile\"\n): AsyncGenerator\u003C{ type: \"token\" | \"done\" | \"error\"; content?: string; error?: string }> {\n  try {\n    const stream = await groq.chat.completions.create({\n      model,\n      messages,\n      stream: true,\n      max_tokens: 2048,\n    });\n\n    for await (const chunk of stream) {\n      const content = chunk.choices[0]?.delta?.content;\n      if (content) yield { type: \"token\", content };\n    }\n\n    yield { type: \"done\" };\n  } catch (err: any) {\n    yield { type: \"error\", error: err.message };\n  }\n}\n```\n\n## Integration Patterns\n\n| Pattern | When to Use | Groq Feature |\n|---------|-------------|-------------|\n| Direct completion | Simple request\u002Fresponse | `chat.completions.create` |\n| Streaming SSE | Real-time chat UI | `stream: true` |\n| Tool calling | Agent with function execution | `tools` parameter |\n| JSON extraction | Structured data from text | `response_format: json_object` |\n| Batch processing | High-volume document processing | Queue + rate limiting |\n| Audio transcription | Voice input | `audio.transcriptions.create` |\n| Vision analysis | Image understanding | Llama 4 Scout\u002FMaverick |\n\n## Error Handling\n| Issue | Cause | Solution |\n|-------|-------|----------|\n| 429 on primary model | RPM\u002FTPM exceeded | Fall back to different model |\n| High latency | Wrong model tier | Route to `8b-instant` for latency-critical paths |\n| Context overflow | Input > 128K tokens | Truncate or chunk input |\n| Vision errors | Wrong model for images | Use Llama 4 Scout full model path |\n\n## Resources\n- [Groq API Documentation](https:\u002F\u002Fconsole.groq.com\u002Fdocs)\n- [Groq Models](https:\u002F\u002Fconsole.groq.com\u002Fdocs\u002Fmodels)\n- [Groq Rate Limits](https:\u002F\u002Fconsole.groq.com\u002Fdocs\u002Frate-limits)\n- [Groq Pricing](https:\u002F\u002Fgroq.com\u002Fpricing)\n\n## Next Steps\nFor multi-environment deployment, see `groq-multi-env-setup`.\n",{"name":5,"tags":24,"author":28,"license":15,"version":29,"description":30,"allowed-tools":31,"compatible-with":32},[25,26,27],"saas","groq","groq-reference","Jeremy Longshore \u003Cjeremy@intentsolutions.io>","1.0.0","Implement Groq reference architecture with model routing, streaming pipelines, and fallbacks.\nUse when designing new Groq integrations, reviewing project structure,\nor establishing architecture standards for Groq applications.\nTrigger with phrases like \"groq architecture\", \"groq best practices\",\n\"groq project structure\", \"how to organize groq\", \"groq design\".\n","Read, Grep","claude-code, codex, openclaw","main","99825ad3f3bcc6597ddcc7294a14e6e922f2b67b","skills\u002Fsaas-packs--groq-pack--groq-reference-architecture",0,"https:\u002F\u002Fgithub.com\u002Fjukeyman\u002Fjukeyman-skills","https:\u002F\u002Fgithub.com\u002Fjukeyman","https:\u002F\u002FRJBUSINESSSOLUTIONS.ORG","Credit and Finance Expert | Developer\r\n\r\nI'm Rick Jefferson, a seasoned credit and finance expert with over a decade of experience in financial literacy,","2026-07-13 07:03:29",{"source":8,"skillName":5,"commands":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add jukeyman\u002Fjukeyman-skills --skill groq-reference-architecture",{"tool":48,"command":49},"bunx","bunx skills add jukeyman\u002Fjukeyman-skills --skill groq-reference-architecture",{"tool":51,"command":52},"pnpm","pnpm dlx skills add jukeyman\u002Fjukeyman-skills --skill groq-reference-architecture","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjukeyman\u002Fjukeyman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsaas-packs--groq-pack--groq-reference-architecture\u002FSKILL.md",true,[],[57,64,71,78,85,93],{"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},"01M79ANS2SM329NEP5ZCX106RR","zustand-store-creator","Create zustand store creator operations. Auto-activating skill for Frontend Development.\nTriggers on: zustand store creator, zustand store creator\nPart of the Frontend Development skill category. Use when working with zustand store creator functionality. Trigger with phrases like \"zustand store creator\", \"zustand creator\", \"zustand\".","https:\u002F\u002Fgithub.com\u002Fjukeyman\u002Fjukeyman-skills\u002Fblob\u002Fmain\u002Fskills\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},"01M79AMZKP4YDEZ7EHG1Y7PP74","zero-trust-config-helper","Configure with zero trust config helper operations. Auto-activating skill for Security Advanced.\nTriggers on: zero trust config helper, zero trust config helper\nPart of the Security Advanced skill category. Use when configuring systems or services. Trigger with phrases like \"zero trust config helper\", \"zero helper\", \"zero\".","https:\u002F\u002Fgithub.com\u002Fjukeyman\u002Fjukeyman-skills\u002Fblob\u002Fmain\u002Fskills\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},"01M79AMJSBCEJQNBTYNAHYN5HM","zapier-integration-helper","Assist with zapier integration helper operations. Auto-activating skill for Business Automation.\nTriggers on: zapier integration helper, zapier integration helper\nPart of the Business Automation skill category. Use when working with APIs or building integrations. Trigger with phrases like \"zapier integration helper\", \"zapier helper\", \"zapier\".","https:\u002F\u002Fgithub.com\u002Fjukeyman\u002Fjukeyman-skills\u002Fblob\u002Fmain\u002Fskills\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":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M79AHJZGVMARS13VFQYRR1MP","yaml-config-validator","Validate yaml config validator operations. Auto-activating skill for DevOps Basics.\nTriggers on: yaml config validator, yaml config validator\nPart of the DevOps Basics skill category. Use when configuring systems or services. Trigger with phrases like \"yaml config validator\", \"yaml validator\", \"yaml\".","https:\u002F\u002Fgithub.com\u002Fjukeyman\u002Fjukeyman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fyaml-config-validator\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":89,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M79AHGDZRN0020RDQSQDPAM8","xvary-stock-research","Thesis-driven equity analysis from public SEC EDGAR and market data; \u002Fanalyze, \u002Fscore, \u002Fcompare workflows with bundled Python tools (Claude Code, Cursor, Codex).","https:\u002F\u002Fgithub.com\u002Fjukeyman\u002Fjukeyman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fxvary-stock-research\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjukeyman\u002Fjukeyman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fxvary-stock-research\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M79AHCYJ9FV9RMHQ24HDRN33","xss-vulnerability-scanner","Scan xss vulnerability scanner operations. Auto-activating skill for Security Fundamentals.\nTriggers on: xss vulnerability scanner, xss vulnerability scanner\nPart of the Security Fundamentals skill category. Use when working with xss vulnerability scanner functionality. Trigger with phrases like \"xss vulnerability scanner\", \"xss scanner\", \"xss\".","https:\u002F\u002Fgithub.com\u002Fjukeyman\u002Fjukeyman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fxss-vulnerability-scanner\u002FSKILL.md",[],[]]