[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M792JQSYFDWYJR5ZYPPRK9H2":3,"skill-same:01M792JQSYFDWYJR5ZYPPRK9H2":58},{"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":35,"commitSha":36,"skillDirectory":37,"forksCount":38,"repositoryHtmlUrl":39,"repositoryHomepageUrl":6,"ownerHtmlUrl":40,"ownerBlogUrl":41,"ownerDescription":42,"updatedAt":43,"install":44,"resources":57},"01M792JQSYFDWYJR5ZYPPRK9H2","langfuse-reference-architecture",null,"Production-grade Langfuse architecture patterns and best practices.\nUse when designing LLM observability infrastructure, planning Langfuse deployment,\nor implementing enterprise-grade tracing architecture.\nTrigger with phrases like \"langfuse architecture\", \"langfuse design\",\n\"langfuse infrastructure\", \"langfuse enterprise\", \"langfuse at scale\".","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--langfuse-pack--langfuse-reference-architecture\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: langfuse-reference-architecture\ndescription: |\n  Production-grade Langfuse architecture patterns and best practices.\n  Use when designing LLM observability infrastructure, planning Langfuse deployment,\n  or implementing enterprise-grade tracing architecture.\n  Trigger with phrases like \"langfuse architecture\", \"langfuse design\",\n  \"langfuse infrastructure\", \"langfuse enterprise\", \"langfuse at scale\".\nallowed-tools: Read, Write, Edit\nversion: 1.0.0\nlicense: MIT\nauthor: Jeremy Longshore \u003Cjeremy@intentsolutions.io>\ncompatible-with: claude-code, codex, openclaw\ntags: [saas, langfuse, deployment, observability, llm]\n---\n# Langfuse Reference Architecture\n\n## Overview\nProduction-grade architecture patterns for Langfuse LLM observability: singleton SDK, context propagation with `AsyncLocalStorage`, cross-service trace correlation, multi-environment configurations, and scale strategies.\n\n## Prerequisites\n- Understanding of distributed systems and async patterns\n- Node.js 18+ with OpenTelemetry SDK\n- For v4+: `@langfuse\u002Ftracing`, `@langfuse\u002Fotel`, `@opentelemetry\u002Fsdk-node`\n\n## Architecture Tiers\n\n| Tier | Scale | Architecture | Langfuse Host |\n|------|-------|-------------|---------------|\n| Starter | \u003C 100K traces\u002Fday | Direct SDK, Cloud | Langfuse Cloud |\n| Growth | 100K-1M traces\u002Fday | Singleton + batching | Cloud or Self-hosted |\n| Enterprise | 1M+ traces\u002Fday | Queue-buffered + sampling | Self-hosted (HA) |\n\n## Instructions\n\n### Pattern 1: Singleton SDK with Context Propagation\n\n```typescript\n\u002F\u002F src\u002Flib\u002Ftracing.ts -- Single module for all tracing\nimport { LangfuseClient } from \"@langfuse\u002Fclient\";\nimport { LangfuseSpanProcessor } from \"@langfuse\u002Fotel\";\nimport { NodeSDK } from \"@opentelemetry\u002Fsdk-node\";\nimport { AsyncLocalStorage } from \"async_hooks\";\n\n\u002F\u002F Singleton OTel SDK\nlet sdk: NodeSDK | null = null;\n\nexport function initTracing() {\n  if (sdk) return sdk;\n\n  sdk = new NodeSDK({\n    spanProcessors: [\n      new LangfuseSpanProcessor({\n        exportIntervalMillis: 5000,\n        maxExportBatchSize: 50,\n      }),\n    ],\n  });\n  sdk.start();\n\n  \u002F\u002F Graceful shutdown\n  for (const signal of [\"SIGTERM\", \"SIGINT\"]) {\n    process.on(signal, async () => {\n      console.log(`Received ${signal}, flushing traces...`);\n      await sdk?.shutdown();\n      process.exit(0);\n    });\n  }\n\n  return sdk;\n}\n\n\u002F\u002F Singleton client for non-tracing operations\nlet client: LangfuseClient | null = null;\n\nexport function getLangfuseClient(): LangfuseClient {\n  if (!client) client = new LangfuseClient();\n  return client;\n}\n\n\u002F\u002F Request context for user\u002Fsession tracking\ninterface RequestContext {\n  userId?: string;\n  sessionId?: string;\n  requestId: string;\n}\n\nconst requestStore = new AsyncLocalStorage\u003CRequestContext>();\n\nexport function getRequestContext(): RequestContext | undefined {\n  return requestStore.getStore();\n}\n\nexport function runWithContext\u003CT>(ctx: RequestContext, fn: () => T): T {\n  return requestStore.run(ctx, fn);\n}\n```\n\n### Pattern 2: Express Middleware for Automatic Tracing\n\n```typescript\n\u002F\u002F src\u002Fmiddleware\u002Ftracing.ts\nimport { startActiveObservation, updateActiveObservation } from \"@langfuse\u002Ftracing\";\nimport { runWithContext, getRequestContext } from \"..\u002Flib\u002Ftracing\";\nimport { randomUUID } from \"crypto\";\nimport type { Request, Response, NextFunction } from \"express\";\n\nexport function langfuseMiddleware() {\n  return (req: Request, res: Response, next: NextFunction) => {\n    const ctx = {\n      requestId: req.headers[\"x-request-id\"]?.toString() || randomUUID(),\n      userId: req.headers[\"x-user-id\"]?.toString(),\n      sessionId: req.headers[\"x-session-id\"]?.toString(),\n    };\n\n    runWithContext(ctx, () => {\n      startActiveObservation(`${req.method} ${req.path}`, async () => {\n        updateActiveObservation({\n          input: {\n            method: req.method,\n            path: req.path,\n            query: req.query,\n          },\n          metadata: {\n            userId: ctx.userId,\n            sessionId: ctx.sessionId,\n            requestId: ctx.requestId,\n          },\n        });\n\n        \u002F\u002F Capture response\n        const originalEnd = res.end.bind(res);\n        res.end = function (...args: any[]) {\n          updateActiveObservation({\n            output: { statusCode: res.statusCode },\n          });\n          return originalEnd(...args);\n        } as any;\n\n        next();\n      }).catch(next);\n    });\n  };\n}\n\n\u002F\u002F Usage\nimport express from \"express\";\nimport { initTracing } from \".\u002Flib\u002Ftracing\";\nimport { langfuseMiddleware } from \".\u002Fmiddleware\u002Ftracing\";\n\ninitTracing();\nconst app = express();\napp.use(langfuseMiddleware());\n```\n\n### Pattern 3: Cross-Service Trace Correlation\n\nFor microservices, propagate trace context via HTTP headers:\n\n```typescript\n\u002F\u002F Service A: Inject trace context into outbound requests\nimport { context, propagation } from \"@opentelemetry\u002Fapi\";\n\nasync function callServiceB(data: any) {\n  const headers: Record\u003Cstring, string> = {};\n\n  \u002F\u002F OTel propagation injects traceparent header automatically\n  propagation.inject(context.active(), headers);\n\n  const response = await fetch(\"https:\u002F\u002Fservice-b.internal\u002Fapi\u002Fprocess\", {\n    method: \"POST\",\n    headers: {\n      \"Content-Type\": \"application\u002Fjson\",\n      ...headers, \u002F\u002F Includes traceparent, tracestate\n    },\n    body: JSON.stringify(data),\n  });\n\n  return response.json();\n}\n```\n\n```typescript\n\u002F\u002F Service B: Extract and continue trace context\nimport { context, propagation } from \"@opentelemetry\u002Fapi\";\nimport { startActiveObservation, updateActiveObservation } from \"@langfuse\u002Ftracing\";\n\napp.post(\"\u002Fapi\u002Fprocess\", async (req, res) => {\n  \u002F\u002F OTel automatically extracts context from incoming headers\n  \u002F\u002F when using standard HTTP instrumentation.\n  \u002F\u002F Any startActiveObservation call will be a child of the extracted trace.\n\n  await startActiveObservation(\"service-b-process\", async () => {\n    updateActiveObservation({ input: req.body });\n    const result = await processData(req.body);\n    updateActiveObservation({ output: result });\n    res.json(result);\n  });\n});\n```\n\n### Pattern 4: Multi-Environment Configuration\n\n```typescript\n\u002F\u002F src\u002Fconfig\u002Flangfuse.ts\ntype Environment = \"development\" | \"staging\" | \"production\";\n\nconst configs: Record\u003CEnvironment, {\n  exportIntervalMillis: number;\n  maxExportBatchSize: number;\n  sampleRate: number;\n}> = {\n  development: {\n    exportIntervalMillis: 1000,   \u002F\u002F Immediate visibility\n    maxExportBatchSize: 1,\n    sampleRate: 1.0,              \u002F\u002F Trace everything\n  },\n  staging: {\n    exportIntervalMillis: 5000,\n    maxExportBatchSize: 25,\n    sampleRate: 0.5,              \u002F\u002F 50% sampling\n  },\n  production: {\n    exportIntervalMillis: 10000,\n    maxExportBatchSize: 100,\n    sampleRate: 0.1,              \u002F\u002F 10% sampling\n  },\n};\n\nexport function getTracingConfig() {\n  const env = (process.env.NODE_ENV || \"development\") as Environment;\n  return configs[env] || configs.development;\n}\n```\n\n### Pattern 5: Graceful Degradation\n\nWhen Langfuse is unavailable, the app must keep running:\n\n```typescript\n\u002F\u002F The v4+ SDK with OTel handles this gracefully:\n\u002F\u002F - Failed exports are logged but don't throw\n\u002F\u002F - Events are buffered in the queue\n\u002F\u002F - Queue drops oldest events when maxQueueSize is exceeded\n\u002F\u002F\n\u002F\u002F For additional safety at the application level:\n\nimport { observe, updateActiveObservation } from \"@langfuse\u002Ftracing\";\n\nlet tracingHealthy = true;\nlet consecutiveFailures = 0;\nconst MAX_FAILURES = 10;\n\nexport function safeTrace\u003CT extends (...args: any[]) => Promise\u003Cany>>(\n  name: string,\n  fn: T\n): T {\n  return (async (...args: Parameters\u003CT>) => {\n    if (!tracingHealthy) {\n      return fn(...args); \u002F\u002F Circuit breaker open\n    }\n\n    try {\n      const result = await observe({ name }, async () => {\n        updateActiveObservation({ input: args });\n        const r = await fn(...args);\n        updateActiveObservation({ output: r });\n        return r;\n      })();\n      consecutiveFailures = 0;\n      return result;\n    } catch (error) {\n      consecutiveFailures++;\n      if (consecutiveFailures >= MAX_FAILURES) {\n        tracingHealthy = false;\n        console.error(\"Langfuse tracing disabled (circuit breaker open)\");\n        \u002F\u002F Re-enable after 5 minutes\n        setTimeout(() => { tracingHealthy = true; consecutiveFailures = 0; }, 300000);\n      }\n      return fn(...args);\n    }\n  }) as T;\n}\n```\n\n## Architecture Decision Matrix\n\n| Decision | Starter | Growth | Enterprise |\n|----------|---------|--------|------------|\n| Langfuse host | Cloud | Cloud or Self-hosted | Self-hosted (HA) |\n| SDK version | v4+ | v4+ | v4+ with custom processor |\n| Sampling | 100% | 50-100% | 5-20% + error always |\n| Context propagation | Not needed | AsyncLocalStorage | OTel + HTTP headers |\n| Queue buffer | SDK internal | SDK internal | External (SQS\u002FKafka) |\n| Failover | None | Log-and-continue | Circuit breaker |\n\n## Error Handling\n\n| Issue | Cause | Solution |\n|-------|-------|----------|\n| Multiple SDK instances | No singleton | Centralize in `tracing.ts` module |\n| Lost traces on deploy | No SIGTERM handler | Register shutdown handler |\n| Cross-service trace gaps | No context propagation | Inject OTel `traceparent` header |\n| Scale bottleneck | Direct SDK at high volume | Add queue buffer or increase sampling |\n\n## Resources\n- [TypeScript SDK Overview](https:\u002F\u002Flangfuse.com\u002Fdocs\u002Fobservability\u002Fsdk\u002Ftypescript\u002Foverview)\n- [Advanced Configuration](https:\u002F\u002Flangfuse.com\u002Fdocs\u002Fobservability\u002Fsdk\u002Ftypescript\u002Fadvanced-usage)\n- [Self-Hosting Guide](https:\u002F\u002Flangfuse.com\u002Fself-hosting)\n- [OpenTelemetry Context Propagation](https:\u002F\u002Fopentelemetry.io\u002Fdocs\u002Fconcepts\u002Fcontext-propagation\u002F)\n","# Langfuse Reference Architecture\n\n## Overview\nProduction-grade architecture patterns for Langfuse LLM observability: singleton SDK, context propagation with `AsyncLocalStorage`, cross-service trace correlation, multi-environment configurations, and scale strategies.\n\n## Prerequisites\n- Understanding of distributed systems and async patterns\n- Node.js 18+ with OpenTelemetry SDK\n- For v4+: `@langfuse\u002Ftracing`, `@langfuse\u002Fotel`, `@opentelemetry\u002Fsdk-node`\n\n## Architecture Tiers\n\n| Tier | Scale | Architecture | Langfuse Host |\n|------|-------|-------------|---------------|\n| Starter | \u003C 100K traces\u002Fday | Direct SDK, Cloud | Langfuse Cloud |\n| Growth | 100K-1M traces\u002Fday | Singleton + batching | Cloud or Self-hosted |\n| Enterprise | 1M+ traces\u002Fday | Queue-buffered + sampling | Self-hosted (HA) |\n\n## Instructions\n\n### Pattern 1: Singleton SDK with Context Propagation\n\n```typescript\n\u002F\u002F src\u002Flib\u002Ftracing.ts -- Single module for all tracing\nimport { LangfuseClient } from \"@langfuse\u002Fclient\";\nimport { LangfuseSpanProcessor } from \"@langfuse\u002Fotel\";\nimport { NodeSDK } from \"@opentelemetry\u002Fsdk-node\";\nimport { AsyncLocalStorage } from \"async_hooks\";\n\n\u002F\u002F Singleton OTel SDK\nlet sdk: NodeSDK | null = null;\n\nexport function initTracing() {\n  if (sdk) return sdk;\n\n  sdk = new NodeSDK({\n    spanProcessors: [\n      new LangfuseSpanProcessor({\n        exportIntervalMillis: 5000,\n        maxExportBatchSize: 50,\n      }),\n    ],\n  });\n  sdk.start();\n\n  \u002F\u002F Graceful shutdown\n  for (const signal of [\"SIGTERM\", \"SIGINT\"]) {\n    process.on(signal, async () => {\n      console.log(`Received ${signal}, flushing traces...`);\n      await sdk?.shutdown();\n      process.exit(0);\n    });\n  }\n\n  return sdk;\n}\n\n\u002F\u002F Singleton client for non-tracing operations\nlet client: LangfuseClient | null = null;\n\nexport function getLangfuseClient(): LangfuseClient {\n  if (!client) client = new LangfuseClient();\n  return client;\n}\n\n\u002F\u002F Request context for user\u002Fsession tracking\ninterface RequestContext {\n  userId?: string;\n  sessionId?: string;\n  requestId: string;\n}\n\nconst requestStore = new AsyncLocalStorage\u003CRequestContext>();\n\nexport function getRequestContext(): RequestContext | undefined {\n  return requestStore.getStore();\n}\n\nexport function runWithContext\u003CT>(ctx: RequestContext, fn: () => T): T {\n  return requestStore.run(ctx, fn);\n}\n```\n\n### Pattern 2: Express Middleware for Automatic Tracing\n\n```typescript\n\u002F\u002F src\u002Fmiddleware\u002Ftracing.ts\nimport { startActiveObservation, updateActiveObservation } from \"@langfuse\u002Ftracing\";\nimport { runWithContext, getRequestContext } from \"..\u002Flib\u002Ftracing\";\nimport { randomUUID } from \"crypto\";\nimport type { Request, Response, NextFunction } from \"express\";\n\nexport function langfuseMiddleware() {\n  return (req: Request, res: Response, next: NextFunction) => {\n    const ctx = {\n      requestId: req.headers[\"x-request-id\"]?.toString() || randomUUID(),\n      userId: req.headers[\"x-user-id\"]?.toString(),\n      sessionId: req.headers[\"x-session-id\"]?.toString(),\n    };\n\n    runWithContext(ctx, () => {\n      startActiveObservation(`${req.method} ${req.path}`, async () => {\n        updateActiveObservation({\n          input: {\n            method: req.method,\n            path: req.path,\n            query: req.query,\n          },\n          metadata: {\n            userId: ctx.userId,\n            sessionId: ctx.sessionId,\n            requestId: ctx.requestId,\n          },\n        });\n\n        \u002F\u002F Capture response\n        const originalEnd = res.end.bind(res);\n        res.end = function (...args: any[]) {\n          updateActiveObservation({\n            output: { statusCode: res.statusCode },\n          });\n          return originalEnd(...args);\n        } as any;\n\n        next();\n      }).catch(next);\n    });\n  };\n}\n\n\u002F\u002F Usage\nimport express from \"express\";\nimport { initTracing } from \".\u002Flib\u002Ftracing\";\nimport { langfuseMiddleware } from \".\u002Fmiddleware\u002Ftracing\";\n\ninitTracing();\nconst app = express();\napp.use(langfuseMiddleware());\n```\n\n### Pattern 3: Cross-Service Trace Correlation\n\nFor microservices, propagate trace context via HTTP headers:\n\n```typescript\n\u002F\u002F Service A: Inject trace context into outbound requests\nimport { context, propagation } from \"@opentelemetry\u002Fapi\";\n\nasync function callServiceB(data: any) {\n  const headers: Record\u003Cstring, string> = {};\n\n  \u002F\u002F OTel propagation injects traceparent header automatically\n  propagation.inject(context.active(), headers);\n\n  const response = await fetch(\"https:\u002F\u002Fservice-b.internal\u002Fapi\u002Fprocess\", {\n    method: \"POST\",\n    headers: {\n      \"Content-Type\": \"application\u002Fjson\",\n      ...headers, \u002F\u002F Includes traceparent, tracestate\n    },\n    body: JSON.stringify(data),\n  });\n\n  return response.json();\n}\n```\n\n```typescript\n\u002F\u002F Service B: Extract and continue trace context\nimport { context, propagation } from \"@opentelemetry\u002Fapi\";\nimport { startActiveObservation, updateActiveObservation } from \"@langfuse\u002Ftracing\";\n\napp.post(\"\u002Fapi\u002Fprocess\", async (req, res) => {\n  \u002F\u002F OTel automatically extracts context from incoming headers\n  \u002F\u002F when using standard HTTP instrumentation.\n  \u002F\u002F Any startActiveObservation call will be a child of the extracted trace.\n\n  await startActiveObservation(\"service-b-process\", async () => {\n    updateActiveObservation({ input: req.body });\n    const result = await processData(req.body);\n    updateActiveObservation({ output: result });\n    res.json(result);\n  });\n});\n```\n\n### Pattern 4: Multi-Environment Configuration\n\n```typescript\n\u002F\u002F src\u002Fconfig\u002Flangfuse.ts\ntype Environment = \"development\" | \"staging\" | \"production\";\n\nconst configs: Record\u003CEnvironment, {\n  exportIntervalMillis: number;\n  maxExportBatchSize: number;\n  sampleRate: number;\n}> = {\n  development: {\n    exportIntervalMillis: 1000,   \u002F\u002F Immediate visibility\n    maxExportBatchSize: 1,\n    sampleRate: 1.0,              \u002F\u002F Trace everything\n  },\n  staging: {\n    exportIntervalMillis: 5000,\n    maxExportBatchSize: 25,\n    sampleRate: 0.5,              \u002F\u002F 50% sampling\n  },\n  production: {\n    exportIntervalMillis: 10000,\n    maxExportBatchSize: 100,\n    sampleRate: 0.1,              \u002F\u002F 10% sampling\n  },\n};\n\nexport function getTracingConfig() {\n  const env = (process.env.NODE_ENV || \"development\") as Environment;\n  return configs[env] || configs.development;\n}\n```\n\n### Pattern 5: Graceful Degradation\n\nWhen Langfuse is unavailable, the app must keep running:\n\n```typescript\n\u002F\u002F The v4+ SDK with OTel handles this gracefully:\n\u002F\u002F - Failed exports are logged but don't throw\n\u002F\u002F - Events are buffered in the queue\n\u002F\u002F - Queue drops oldest events when maxQueueSize is exceeded\n\u002F\u002F\n\u002F\u002F For additional safety at the application level:\n\nimport { observe, updateActiveObservation } from \"@langfuse\u002Ftracing\";\n\nlet tracingHealthy = true;\nlet consecutiveFailures = 0;\nconst MAX_FAILURES = 10;\n\nexport function safeTrace\u003CT extends (...args: any[]) => Promise\u003Cany>>(\n  name: string,\n  fn: T\n): T {\n  return (async (...args: Parameters\u003CT>) => {\n    if (!tracingHealthy) {\n      return fn(...args); \u002F\u002F Circuit breaker open\n    }\n\n    try {\n      const result = await observe({ name }, async () => {\n        updateActiveObservation({ input: args });\n        const r = await fn(...args);\n        updateActiveObservation({ output: r });\n        return r;\n      })();\n      consecutiveFailures = 0;\n      return result;\n    } catch (error) {\n      consecutiveFailures++;\n      if (consecutiveFailures >= MAX_FAILURES) {\n        tracingHealthy = false;\n        console.error(\"Langfuse tracing disabled (circuit breaker open)\");\n        \u002F\u002F Re-enable after 5 minutes\n        setTimeout(() => { tracingHealthy = true; consecutiveFailures = 0; }, 300000);\n      }\n      return fn(...args);\n    }\n  }) as T;\n}\n```\n\n## Architecture Decision Matrix\n\n| Decision | Starter | Growth | Enterprise |\n|----------|---------|--------|------------|\n| Langfuse host | Cloud | Cloud or Self-hosted | Self-hosted (HA) |\n| SDK version | v4+ | v4+ | v4+ with custom processor |\n| Sampling | 100% | 50-100% | 5-20% + error always |\n| Context propagation | Not needed | AsyncLocalStorage | OTel + HTTP headers |\n| Queue buffer | SDK internal | SDK internal | External (SQS\u002FKafka) |\n| Failover | None | Log-and-continue | Circuit breaker |\n\n## Error Handling\n\n| Issue | Cause | Solution |\n|-------|-------|----------|\n| Multiple SDK instances | No singleton | Centralize in `tracing.ts` module |\n| Lost traces on deploy | No SIGTERM handler | Register shutdown handler |\n| Cross-service trace gaps | No context propagation | Inject OTel `traceparent` header |\n| Scale bottleneck | Direct SDK at high volume | Add queue buffer or increase sampling |\n\n## Resources\n- [TypeScript SDK Overview](https:\u002F\u002Flangfuse.com\u002Fdocs\u002Fobservability\u002Fsdk\u002Ftypescript\u002Foverview)\n- [Advanced Configuration](https:\u002F\u002Flangfuse.com\u002Fdocs\u002Fobservability\u002Fsdk\u002Ftypescript\u002Fadvanced-usage)\n- [Self-Hosting Guide](https:\u002F\u002Flangfuse.com\u002Fself-hosting)\n- [OpenTelemetry Context Propagation](https:\u002F\u002Fopentelemetry.io\u002Fdocs\u002Fconcepts\u002Fcontext-propagation\u002F)\n",{"name":5,"tags":24,"author":30,"license":15,"version":31,"description":32,"allowed-tools":33,"compatible-with":34},[25,26,27,28,29],"saas","langfuse","deployment","observability","llm","Jeremy Longshore \u003Cjeremy@intentsolutions.io>","1.0.0","Production-grade Langfuse architecture patterns and best practices.\nUse when designing LLM observability infrastructure, planning Langfuse deployment,\nor implementing enterprise-grade tracing architecture.\nTrigger with phrases like \"langfuse architecture\", \"langfuse design\",\n\"langfuse infrastructure\", \"langfuse enterprise\", \"langfuse at scale\".\n","Read, Write, Edit","claude-code, codex, openclaw","main","99825ad3f3bcc6597ddcc7294a14e6e922f2b67b","skills\u002Fsaas-packs--langfuse-pack--langfuse-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":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add jukeyman\u002Fjukeyman-skills --skill langfuse-reference-architecture",{"tool":50,"command":51},"bunx","bunx skills add jukeyman\u002Fjukeyman-skills --skill langfuse-reference-architecture",{"tool":53,"command":54},"pnpm","pnpm dlx skills add jukeyman\u002Fjukeyman-skills --skill langfuse-reference-architecture","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjukeyman\u002Fjukeyman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsaas-packs--langfuse-pack--langfuse-reference-architecture\u002FSKILL.md",true,[],[59,66,73,80,87,95],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"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":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"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":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":79,"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":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"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":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":91,"sourceHtmlUrl":92,"categories":93,"keywords":94,"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":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"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",[],[]]