[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7927N8BHD1K3PTY7SCDDTWE":3,"skill-same:01M7927N8BHD1K3PTY7SCDDTWE":57},{"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":34,"commitSha":35,"skillDirectory":36,"forksCount":37,"repositoryHtmlUrl":38,"repositoryHomepageUrl":6,"ownerHtmlUrl":39,"ownerBlogUrl":40,"ownerDescription":41,"updatedAt":42,"install":43,"resources":56},"01M7927N8BHD1K3PTY7SCDDTWE","langchain-reference-architecture",null,"Implement LangChain reference architecture for production systems:\nlayered design, provider abstraction, chain registry, RAG pipelines,\nand multi-agent orchestration.\nTrigger: \"langchain architecture\", \"langchain design patterns\",\n\"langchain scalable\", \"langchain enterprise\", \"LLM architecture\".","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--langchain-pack--langchain-reference-architecture\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: langchain-reference-architecture\ndescription: |\n  Implement LangChain reference architecture for production systems:\n  layered design, provider abstraction, chain registry, RAG pipelines,\n  and multi-agent orchestration.\n  Trigger: \"langchain architecture\", \"langchain design patterns\",\n  \"langchain scalable\", \"langchain enterprise\", \"LLM architecture\".\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, langchain, llm, scaling]\n---\n# LangChain Reference Architecture\n\n## Overview\n\nProduction architectural patterns for LangChain: layered project structure, provider abstraction for vendor flexibility, chain registry for dynamic management, RAG architecture, and multi-agent orchestration.\n\n## Layered Architecture\n\n```\nsrc\u002F\n├── api\u002F                    # HTTP layer (Express\u002FFastify\u002FFastAPI)\n│   ├── routes\u002F\n│   │   ├── chat.ts         # POST \u002Fapi\u002Fchat, \u002Fapi\u002Fchat\u002Fstream\n│   │   └── documents.ts    # POST \u002Fapi\u002Fdocuments\u002Fingest\n│   └── middleware\u002F\n│       ├── auth.ts         # JWT\u002FOAuth validation\n│       └── rateLimit.ts    # Per-user rate limiting\n├── core\u002F                   # Business logic (pure, testable)\n│   ├── chains\u002F\n│   │   ├── summarize.ts    # Summarize chain factory\n│   │   ├── qa.ts           # Q&A chain factory\n│   │   └── rag.ts          # RAG chain factory\n│   ├── agents\u002F\n│   │   └── assistant.ts    # Agent with tools\n│   └── tools\u002F\n│       ├── calculator.ts\n│       └── search.ts\n├── infra\u002F                  # External integrations\n│   ├── llm\u002F\n│   │   └── factory.ts      # LLM provider factory\n│   ├── vectorStore\u002F\n│   │   └── pinecone.ts     # Vector store setup\n│   └── cache\u002F\n│       └── redis.ts        # Response caching\n├── config\u002F\n│   ├── index.ts            # Config loader + validation\n│   └── models.ts           # Model configurations\n└── index.ts                # App entry point\n```\n\n## Provider Abstraction (LLM Factory)\n\n```typescript\n\u002F\u002F src\u002Finfra\u002Fllm\u002Ffactory.ts\nimport { ChatOpenAI } from \"@langchain\u002Fopenai\";\nimport { ChatAnthropic } from \"@langchain\u002Fanthropic\";\nimport { BaseChatModel } from \"@langchain\u002Fcore\u002Flanguage_models\u002Fchat_models\";\n\ntype Provider = \"openai\" | \"anthropic\";\n\ninterface ModelConfig {\n  provider: Provider;\n  model: string;\n  temperature?: number;\n  maxRetries?: number;\n  timeout?: number;\n}\n\nconst DEFAULT_CONFIG: Partial\u003CModelConfig> = {\n  temperature: 0,\n  maxRetries: 3,\n  timeout: 30000,\n};\n\nexport function createModel(config: ModelConfig): BaseChatModel {\n  const merged = { ...DEFAULT_CONFIG, ...config };\n\n  switch (merged.provider) {\n    case \"openai\":\n      return new ChatOpenAI({\n        model: merged.model,\n        temperature: merged.temperature,\n        maxRetries: merged.maxRetries,\n        timeout: merged.timeout,\n      });\n\n    case \"anthropic\":\n      return new ChatAnthropic({\n        model: merged.model,\n        temperature: merged.temperature,\n        maxRetries: merged.maxRetries,\n      });\n\n    default:\n      throw new Error(`Unknown provider: ${merged.provider}`);\n  }\n}\n\n\u002F\u002F Usage: swap providers without touching chain code\nconst model = createModel({\n  provider: \"openai\",\n  model: \"gpt-4o-mini\",\n});\n```\n\n## Chain Registry\n\n```typescript\n\u002F\u002F src\u002Fcore\u002Fchains\u002Fregistry.ts\nimport { Runnable } from \"@langchain\u002Fcore\u002Frunnables\";\n\nclass ChainRegistry {\n  private chains = new Map\u003Cstring, Runnable>();\n\n  register(name: string, chain: Runnable) {\n    this.chains.set(name, chain);\n  }\n\n  get(name: string): Runnable {\n    const chain = this.chains.get(name);\n    if (!chain) throw new Error(`Chain not found: ${name}`);\n    return chain;\n  }\n\n  list(): string[] {\n    return Array.from(this.chains.keys());\n  }\n}\n\nexport const registry = new ChainRegistry();\n\n\u002F\u002F At startup:\nregistry.register(\"summarize\", summarizeChain);\nregistry.register(\"qa\", qaChain);\nregistry.register(\"rag\", ragChain);\n\n\u002F\u002F In API routes:\napp.post(\"\u002Fapi\u002Fchain\u002F:name\u002Finvoke\", async (req, res) => {\n  const chain = registry.get(req.params.name);\n  const result = await chain.invoke(req.body.input);\n  res.json({ result });\n});\n```\n\n## RAG Architecture\n\n```typescript\n\u002F\u002F src\u002Fcore\u002Fchains\u002Frag.ts\nimport { ChatOpenAI, OpenAIEmbeddings } from \"@langchain\u002Fopenai\";\nimport { PineconeStore } from \"@langchain\u002Fpinecone\";\nimport { ChatPromptTemplate } from \"@langchain\u002Fcore\u002Fprompts\";\nimport { StringOutputParser } from \"@langchain\u002Fcore\u002Foutput_parsers\";\nimport { RunnableSequence, RunnablePassthrough } from \"@langchain\u002Fcore\u002Frunnables\";\n\nexport function createRAGChain(vectorStore: PineconeStore) {\n  const retriever = vectorStore.asRetriever({ k: 4 });\n  const model = new ChatOpenAI({ model: \"gpt-4o-mini\", temperature: 0 });\n\n  const prompt = ChatPromptTemplate.fromTemplate(`\nAnswer based only on the provided context.\nIf the answer is not in the context, say \"I don't have that information.\"\n\nContext:\n{context}\n\nQuestion: {question}`);\n\n  return RunnableSequence.from([\n    {\n      context: retriever.pipe(\n        (docs) => docs.map((d: any) => d.pageContent).join(\"\\n\\n\")\n      ),\n      question: new RunnablePassthrough(),\n    },\n    prompt,\n    model,\n    new StringOutputParser(),\n  ]);\n}\n```\n\n## Multi-Agent Orchestration\n\n```typescript\n\u002F\u002F src\u002Fcore\u002Fagents\u002Forchestrator.ts\nimport { ChatOpenAI } from \"@langchain\u002Fopenai\";\nimport { createToolCallingAgent, AgentExecutor } from \"langchain\u002Fagents\";\nimport { ChatPromptTemplate, MessagesPlaceholder } from \"@langchain\u002Fcore\u002Fprompts\";\n\ninterface SpecializedAgent {\n  name: string;\n  description: string;\n  executor: AgentExecutor;\n}\n\nclass AgentOrchestrator {\n  private agents: SpecializedAgent[] = [];\n  private router: any;\n\n  register(agent: SpecializedAgent) {\n    this.agents.push(agent);\n  }\n\n  async route(input: string): Promise\u003Cstring> {\n    \u002F\u002F Use LLM to pick the right agent\n    const model = new ChatOpenAI({ model: \"gpt-4o-mini\", temperature: 0 });\n    const agentList = this.agents\n      .map((a) => `- ${a.name}: ${a.description}`)\n      .join(\"\\n\");\n\n    const routerPrompt = ChatPromptTemplate.fromTemplate(`\nGiven these specialized agents:\n${agentList}\n\nWhich agent should handle this request? Reply with just the agent name.\nRequest: {input}`);\n\n    const routerChain = routerPrompt.pipe(model).pipe(new StringOutputParser());\n    const agentName = (await routerChain.invoke({ input })).trim();\n\n    const agent = this.agents.find((a) => a.name === agentName);\n    if (!agent) {\n      return `No agent found for: ${input}`;\n    }\n\n    const result = await agent.executor.invoke({ input, chat_history: [] });\n    return result.output;\n  }\n}\n\n\u002F\u002F Usage\nconst orchestrator = new AgentOrchestrator();\norchestrator.register({\n  name: \"code-reviewer\",\n  description: \"Reviews code for bugs and best practices\",\n  executor: codeReviewAgent,\n});\norchestrator.register({\n  name: \"data-analyst\",\n  description: \"Analyzes data and generates reports\",\n  executor: dataAnalystAgent,\n});\n```\n\n## Configuration-Driven Design\n\n```typescript\n\u002F\u002F src\u002Fconfig\u002Findex.ts\nimport { z } from \"zod\";\nimport \"dotenv\u002Fconfig\";\n\nconst ConfigSchema = z.object({\n  llm: z.object({\n    provider: z.enum([\"openai\", \"anthropic\"]),\n    model: z.string(),\n    temperature: z.number().min(0).max(2).default(0),\n    maxRetries: z.number().default(3),\n  }),\n  vectorStore: z.object({\n    provider: z.enum([\"pinecone\", \"faiss\", \"memory\"]),\n    indexName: z.string().optional(),\n  }),\n  server: z.object({\n    port: z.number().default(8000),\n    cors: z.boolean().default(true),\n  }),\n  langsmith: z.object({\n    enabled: z.boolean().default(false),\n    project: z.string().default(\"default\"),\n  }),\n});\n\nexport type Config = z.infer\u003Ctypeof ConfigSchema>;\n\nexport function loadConfig(): Config {\n  return ConfigSchema.parse({\n    llm: {\n      provider: process.env.LLM_PROVIDER ?? \"openai\",\n      model: process.env.LLM_MODEL ?? \"gpt-4o-mini\",\n      temperature: Number(process.env.LLM_TEMPERATURE ?? 0),\n    },\n    vectorStore: {\n      provider: process.env.VECTOR_STORE_PROVIDER ?? \"memory\",\n      indexName: process.env.PINECONE_INDEX,\n    },\n    server: {\n      port: Number(process.env.PORT ?? 8000),\n    },\n    langsmith: {\n      enabled: process.env.LANGSMITH_TRACING === \"true\",\n      project: process.env.LANGSMITH_PROJECT ?? \"default\",\n    },\n  });\n}\n```\n\n## Error Handling\n\n| Issue | Cause | Fix |\n|-------|-------|-----|\n| Circular imports | Wrong layering | Core should never import from API layer |\n| Provider not found | Unknown in factory | Add to factory switch statement |\n| Chain not registered | Missing startup init | Register all chains in app bootstrap |\n| Config validation fail | Missing env var | Add to `.env.example`, validate on startup |\n\n## Resources\n\n- [Clean Architecture](https:\u002F\u002Fblog.cleancoder.com\u002Funcle-bob\u002F2012\u002F08\u002F13\u002Fthe-clean-architecture.html)\n- [LangChain Architecture Guide](https:\u002F\u002Fjs.langchain.com\u002Fdocs\u002Fconcepts\u002Farchitecture\u002F)\n- [Domain-Driven Design](https:\u002F\u002Fmartinfowler.com\u002Fbliki\u002FDomainDrivenDesign.html)\n\n## Next Steps\n\nUse `langchain-multi-env-setup` for environment management.\n","# LangChain Reference Architecture\n\n## Overview\n\nProduction architectural patterns for LangChain: layered project structure, provider abstraction for vendor flexibility, chain registry for dynamic management, RAG architecture, and multi-agent orchestration.\n\n## Layered Architecture\n\n```\nsrc\u002F\n├── api\u002F                    # HTTP layer (Express\u002FFastify\u002FFastAPI)\n│   ├── routes\u002F\n│   │   ├── chat.ts         # POST \u002Fapi\u002Fchat, \u002Fapi\u002Fchat\u002Fstream\n│   │   └── documents.ts    # POST \u002Fapi\u002Fdocuments\u002Fingest\n│   └── middleware\u002F\n│       ├── auth.ts         # JWT\u002FOAuth validation\n│       └── rateLimit.ts    # Per-user rate limiting\n├── core\u002F                   # Business logic (pure, testable)\n│   ├── chains\u002F\n│   │   ├── summarize.ts    # Summarize chain factory\n│   │   ├── qa.ts           # Q&A chain factory\n│   │   └── rag.ts          # RAG chain factory\n│   ├── agents\u002F\n│   │   └── assistant.ts    # Agent with tools\n│   └── tools\u002F\n│       ├── calculator.ts\n│       └── search.ts\n├── infra\u002F                  # External integrations\n│   ├── llm\u002F\n│   │   └── factory.ts      # LLM provider factory\n│   ├── vectorStore\u002F\n│   │   └── pinecone.ts     # Vector store setup\n│   └── cache\u002F\n│       └── redis.ts        # Response caching\n├── config\u002F\n│   ├── index.ts            # Config loader + validation\n│   └── models.ts           # Model configurations\n└── index.ts                # App entry point\n```\n\n## Provider Abstraction (LLM Factory)\n\n```typescript\n\u002F\u002F src\u002Finfra\u002Fllm\u002Ffactory.ts\nimport { ChatOpenAI } from \"@langchain\u002Fopenai\";\nimport { ChatAnthropic } from \"@langchain\u002Fanthropic\";\nimport { BaseChatModel } from \"@langchain\u002Fcore\u002Flanguage_models\u002Fchat_models\";\n\ntype Provider = \"openai\" | \"anthropic\";\n\ninterface ModelConfig {\n  provider: Provider;\n  model: string;\n  temperature?: number;\n  maxRetries?: number;\n  timeout?: number;\n}\n\nconst DEFAULT_CONFIG: Partial\u003CModelConfig> = {\n  temperature: 0,\n  maxRetries: 3,\n  timeout: 30000,\n};\n\nexport function createModel(config: ModelConfig): BaseChatModel {\n  const merged = { ...DEFAULT_CONFIG, ...config };\n\n  switch (merged.provider) {\n    case \"openai\":\n      return new ChatOpenAI({\n        model: merged.model,\n        temperature: merged.temperature,\n        maxRetries: merged.maxRetries,\n        timeout: merged.timeout,\n      });\n\n    case \"anthropic\":\n      return new ChatAnthropic({\n        model: merged.model,\n        temperature: merged.temperature,\n        maxRetries: merged.maxRetries,\n      });\n\n    default:\n      throw new Error(`Unknown provider: ${merged.provider}`);\n  }\n}\n\n\u002F\u002F Usage: swap providers without touching chain code\nconst model = createModel({\n  provider: \"openai\",\n  model: \"gpt-4o-mini\",\n});\n```\n\n## Chain Registry\n\n```typescript\n\u002F\u002F src\u002Fcore\u002Fchains\u002Fregistry.ts\nimport { Runnable } from \"@langchain\u002Fcore\u002Frunnables\";\n\nclass ChainRegistry {\n  private chains = new Map\u003Cstring, Runnable>();\n\n  register(name: string, chain: Runnable) {\n    this.chains.set(name, chain);\n  }\n\n  get(name: string): Runnable {\n    const chain = this.chains.get(name);\n    if (!chain) throw new Error(`Chain not found: ${name}`);\n    return chain;\n  }\n\n  list(): string[] {\n    return Array.from(this.chains.keys());\n  }\n}\n\nexport const registry = new ChainRegistry();\n\n\u002F\u002F At startup:\nregistry.register(\"summarize\", summarizeChain);\nregistry.register(\"qa\", qaChain);\nregistry.register(\"rag\", ragChain);\n\n\u002F\u002F In API routes:\napp.post(\"\u002Fapi\u002Fchain\u002F:name\u002Finvoke\", async (req, res) => {\n  const chain = registry.get(req.params.name);\n  const result = await chain.invoke(req.body.input);\n  res.json({ result });\n});\n```\n\n## RAG Architecture\n\n```typescript\n\u002F\u002F src\u002Fcore\u002Fchains\u002Frag.ts\nimport { ChatOpenAI, OpenAIEmbeddings } from \"@langchain\u002Fopenai\";\nimport { PineconeStore } from \"@langchain\u002Fpinecone\";\nimport { ChatPromptTemplate } from \"@langchain\u002Fcore\u002Fprompts\";\nimport { StringOutputParser } from \"@langchain\u002Fcore\u002Foutput_parsers\";\nimport { RunnableSequence, RunnablePassthrough } from \"@langchain\u002Fcore\u002Frunnables\";\n\nexport function createRAGChain(vectorStore: PineconeStore) {\n  const retriever = vectorStore.asRetriever({ k: 4 });\n  const model = new ChatOpenAI({ model: \"gpt-4o-mini\", temperature: 0 });\n\n  const prompt = ChatPromptTemplate.fromTemplate(`\nAnswer based only on the provided context.\nIf the answer is not in the context, say \"I don't have that information.\"\n\nContext:\n{context}\n\nQuestion: {question}`);\n\n  return RunnableSequence.from([\n    {\n      context: retriever.pipe(\n        (docs) => docs.map((d: any) => d.pageContent).join(\"\\n\\n\")\n      ),\n      question: new RunnablePassthrough(),\n    },\n    prompt,\n    model,\n    new StringOutputParser(),\n  ]);\n}\n```\n\n## Multi-Agent Orchestration\n\n```typescript\n\u002F\u002F src\u002Fcore\u002Fagents\u002Forchestrator.ts\nimport { ChatOpenAI } from \"@langchain\u002Fopenai\";\nimport { createToolCallingAgent, AgentExecutor } from \"langchain\u002Fagents\";\nimport { ChatPromptTemplate, MessagesPlaceholder } from \"@langchain\u002Fcore\u002Fprompts\";\n\ninterface SpecializedAgent {\n  name: string;\n  description: string;\n  executor: AgentExecutor;\n}\n\nclass AgentOrchestrator {\n  private agents: SpecializedAgent[] = [];\n  private router: any;\n\n  register(agent: SpecializedAgent) {\n    this.agents.push(agent);\n  }\n\n  async route(input: string): Promise\u003Cstring> {\n    \u002F\u002F Use LLM to pick the right agent\n    const model = new ChatOpenAI({ model: \"gpt-4o-mini\", temperature: 0 });\n    const agentList = this.agents\n      .map((a) => `- ${a.name}: ${a.description}`)\n      .join(\"\\n\");\n\n    const routerPrompt = ChatPromptTemplate.fromTemplate(`\nGiven these specialized agents:\n${agentList}\n\nWhich agent should handle this request? Reply with just the agent name.\nRequest: {input}`);\n\n    const routerChain = routerPrompt.pipe(model).pipe(new StringOutputParser());\n    const agentName = (await routerChain.invoke({ input })).trim();\n\n    const agent = this.agents.find((a) => a.name === agentName);\n    if (!agent) {\n      return `No agent found for: ${input}`;\n    }\n\n    const result = await agent.executor.invoke({ input, chat_history: [] });\n    return result.output;\n  }\n}\n\n\u002F\u002F Usage\nconst orchestrator = new AgentOrchestrator();\norchestrator.register({\n  name: \"code-reviewer\",\n  description: \"Reviews code for bugs and best practices\",\n  executor: codeReviewAgent,\n});\norchestrator.register({\n  name: \"data-analyst\",\n  description: \"Analyzes data and generates reports\",\n  executor: dataAnalystAgent,\n});\n```\n\n## Configuration-Driven Design\n\n```typescript\n\u002F\u002F src\u002Fconfig\u002Findex.ts\nimport { z } from \"zod\";\nimport \"dotenv\u002Fconfig\";\n\nconst ConfigSchema = z.object({\n  llm: z.object({\n    provider: z.enum([\"openai\", \"anthropic\"]),\n    model: z.string(),\n    temperature: z.number().min(0).max(2).default(0),\n    maxRetries: z.number().default(3),\n  }),\n  vectorStore: z.object({\n    provider: z.enum([\"pinecone\", \"faiss\", \"memory\"]),\n    indexName: z.string().optional(),\n  }),\n  server: z.object({\n    port: z.number().default(8000),\n    cors: z.boolean().default(true),\n  }),\n  langsmith: z.object({\n    enabled: z.boolean().default(false),\n    project: z.string().default(\"default\"),\n  }),\n});\n\nexport type Config = z.infer\u003Ctypeof ConfigSchema>;\n\nexport function loadConfig(): Config {\n  return ConfigSchema.parse({\n    llm: {\n      provider: process.env.LLM_PROVIDER ?? \"openai\",\n      model: process.env.LLM_MODEL ?? \"gpt-4o-mini\",\n      temperature: Number(process.env.LLM_TEMPERATURE ?? 0),\n    },\n    vectorStore: {\n      provider: process.env.VECTOR_STORE_PROVIDER ?? \"memory\",\n      indexName: process.env.PINECONE_INDEX,\n    },\n    server: {\n      port: Number(process.env.PORT ?? 8000),\n    },\n    langsmith: {\n      enabled: process.env.LANGSMITH_TRACING === \"true\",\n      project: process.env.LANGSMITH_PROJECT ?? \"default\",\n    },\n  });\n}\n```\n\n## Error Handling\n\n| Issue | Cause | Fix |\n|-------|-------|-----|\n| Circular imports | Wrong layering | Core should never import from API layer |\n| Provider not found | Unknown in factory | Add to factory switch statement |\n| Chain not registered | Missing startup init | Register all chains in app bootstrap |\n| Config validation fail | Missing env var | Add to `.env.example`, validate on startup |\n\n## Resources\n\n- [Clean Architecture](https:\u002F\u002Fblog.cleancoder.com\u002Funcle-bob\u002F2012\u002F08\u002F13\u002Fthe-clean-architecture.html)\n- [LangChain Architecture Guide](https:\u002F\u002Fjs.langchain.com\u002Fdocs\u002Fconcepts\u002Farchitecture\u002F)\n- [Domain-Driven Design](https:\u002F\u002Fmartinfowler.com\u002Fbliki\u002FDomainDrivenDesign.html)\n\n## Next Steps\n\nUse `langchain-multi-env-setup` for environment management.\n",{"name":5,"tags":24,"author":29,"license":15,"version":30,"description":31,"allowed-tools":32,"compatible-with":33},[25,26,27,28],"saas","langchain","llm","scaling","Jeremy Longshore \u003Cjeremy@intentsolutions.io>","1.0.0","Implement LangChain reference architecture for production systems:\nlayered design, provider abstraction, chain registry, RAG pipelines,\nand multi-agent orchestration.\nTrigger: \"langchain architecture\", \"langchain design patterns\",\n\"langchain scalable\", \"langchain enterprise\", \"LLM architecture\".\n","Read, Write, Edit","claude-code, codex, openclaw","main","99825ad3f3bcc6597ddcc7294a14e6e922f2b67b","skills\u002Fsaas-packs--langchain-pack--langchain-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":44,"prompt":54,"zipAvailable":55},[45,48,51],{"tool":46,"command":47},"npx","npx skills add jukeyman\u002Fjukeyman-skills --skill langchain-reference-architecture",{"tool":49,"command":50},"bunx","bunx skills add jukeyman\u002Fjukeyman-skills --skill langchain-reference-architecture",{"tool":52,"command":53},"pnpm","pnpm dlx skills add jukeyman\u002Fjukeyman-skills --skill langchain-reference-architecture","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjukeyman\u002Fjukeyman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsaas-packs--langchain-pack--langchain-reference-architecture\u002FSKILL.md",true,[],[58,65,72,79,86,94],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"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":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"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":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":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":90,"sourceHtmlUrl":91,"categories":92,"keywords":93,"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":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"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",[],[]]