[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M752EZ5BJ487GAZJB07DBQTX":3,"skill-same:01M752EZ5BJ487GAZJB07DBQTX":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},"01M752EZ5BJ487GAZJB07DBQTX","langchain-sdk-patterns",null,"Apply production-ready LangChain SDK patterns for chains, agents, and memory.\nUse when implementing LangChain integrations, refactoring code,\nor establishing team coding standards for LangChain applications.\nTrigger with phrases like \"langchain SDK patterns\", \"langchain best practices\",\n\"langchain code patterns\", \"idiomatic langchain\", \"langchain architecture\".","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\u002Flangchain-sdk-patterns\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: langchain-sdk-patterns\ndescription: |\n  Apply production-ready LangChain SDK patterns for chains, agents, and memory.\n  Use when implementing LangChain integrations, refactoring code,\n  or establishing team coding standards for LangChain applications.\n  Trigger with phrases like \"langchain SDK patterns\", \"langchain best practices\",\n  \"langchain code patterns\", \"idiomatic langchain\", \"langchain architecture\".\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# LangChain SDK Patterns\n\n## Overview\nProduction-ready patterns for LangChain applications including LCEL chains, structured output, and error handling.\n\n## Prerequisites\n- Completed `langchain-install-auth` setup\n- Familiarity with async\u002Fawait patterns\n- Understanding of error handling best practices\n\n## Core Patterns\n\n### Pattern 1: Type-Safe Chain with Pydantic\n```python\nfrom pydantic import BaseModel, Field\nfrom langchain_openai import ChatOpenAI\nfrom langchain_core.prompts import ChatPromptTemplate\n\nclass SentimentResult(BaseModel):\n    \"\"\"Structured output for sentiment analysis.\"\"\"\n    sentiment: str = Field(description=\"positive, negative, or neutral\")\n    confidence: float = Field(description=\"Confidence score 0-1\")\n    reasoning: str = Field(description=\"Brief explanation\")\n\nllm = ChatOpenAI(model=\"gpt-4o-mini\")\nstructured_llm = llm.with_structured_output(SentimentResult)\n\nprompt = ChatPromptTemplate.from_template(\n    \"Analyze the sentiment of: {text}\"\n)\n\nchain = prompt | structured_llm\n\n# Returns typed SentimentResult\nresult: SentimentResult = chain.invoke({\"text\": \"I love LangChain!\"})\nprint(f\"Sentiment: {result.sentiment} ({result.confidence})\")\n```\n\n### Pattern 2: Retry with Fallback\n```python\nfrom langchain_openai import ChatOpenAI\nfrom langchain_anthropic import ChatAnthropic\nfrom langchain_core.runnables import RunnableWithFallbacks\n\nprimary = ChatOpenAI(model=\"gpt-4o\")\nfallback = ChatAnthropic(model=\"claude-3-5-sonnet-20241022\")  # 20241022 = date\u002Fversion stamp\n\n# Automatically falls back on failure\nrobust_llm = primary.with_fallbacks([fallback])\n\nresponse = robust_llm.invoke(\"Hello!\")\n```\n\n### Pattern 3: Async Batch Processing\n```python\nimport asyncio\nfrom langchain_openai import ChatOpenAI\nfrom langchain_core.prompts import ChatPromptTemplate\n\nllm = ChatOpenAI(model=\"gpt-4o-mini\")\nprompt = ChatPromptTemplate.from_template(\"Summarize: {text}\")\nchain = prompt | llm\n\nasync def process_batch(texts: list[str]) -> list:\n    \"\"\"Process multiple texts concurrently.\"\"\"\n    inputs = [{\"text\": t} for t in texts]\n    results = await chain.abatch(inputs, config={\"max_concurrency\": 5})\n    return results\n\n# Usage\nresults = asyncio.run(process_batch([\"text1\", \"text2\", \"text3\"]))\n```\n\n### Pattern 4: Streaming with Callbacks\n```python\nfrom langchain_openai import ChatOpenAI\nfrom langchain_core.callbacks import StreamingStdOutCallbackHandler\n\nllm = ChatOpenAI(\n    model=\"gpt-4o-mini\",\n    streaming=True,\n    callbacks=[StreamingStdOutCallbackHandler()]\n)\n\n# Streams tokens to stdout as they arrive\nfor chunk in llm.stream(\"Tell me a story\"):\n    # Each chunk contains partial content\n    pass\n```\n\n### Pattern 5: Caching for Cost Reduction\n```python\nfrom langchain_openai import ChatOpenAI\nfrom langchain_core.globals import set_llm_cache\nfrom langchain_community.cache import SQLiteCache\n\n# Enable SQLite caching\nset_llm_cache(SQLiteCache(database_path=\".langchain_cache.db\"))\n\nllm = ChatOpenAI(model=\"gpt-4o-mini\")\n\n# First call hits API\nresponse1 = llm.invoke(\"What is 2+2?\")\n\n# Second identical call uses cache (no API cost)\nresponse2 = llm.invoke(\"What is 2+2?\")\n```\n\n## Output\n- Type-safe chains with Pydantic models\n- Robust error handling with fallbacks\n- Efficient async batch processing\n- Cost-effective caching strategies\n\n## Error Handling\n\n### Standard Error Pattern\n```python\nfrom langchain_core.exceptions import OutputParserException\nfrom openai import RateLimitError, APIError\n\ndef safe_invoke(chain, input_data, max_retries=3):\n    \"\"\"Invoke chain with error handling.\"\"\"\n    for attempt in range(max_retries):\n        try:\n            return chain.invoke(input_data)\n        except RateLimitError:\n            if attempt \u003C max_retries - 1:\n                time.sleep(2 ** attempt)\n                continue\n            raise\n        except OutputParserException as e:\n            # Handle parsing failures\n            return {\"error\": str(e), \"raw\": e.llm_output}\n        except APIError as e:\n            raise RuntimeError(f\"API error: {e}\")\n```\n\n## Resources\n- [LCEL Documentation](https:\u002F\u002Fpython.langchain.com\u002Fdocs\u002Fconcepts\u002Flcel\u002F)\n- [Structured Output](https:\u002F\u002Fpython.langchain.com\u002Fdocs\u002Fconcepts\u002Fstructured_outputs\u002F)\n- [Fallbacks](https:\u002F\u002Fpython.langchain.com\u002Fdocs\u002Fhow_to\u002Ffallbacks\u002F)\n- [Caching](https:\u002F\u002Fpython.langchain.com\u002Fdocs\u002Fhow_to\u002Fllm_caching\u002F)\n\n## Next Steps\nProceed to `langchain-core-workflow-a` for chains and prompts workflow.\n\n## Instructions\n\n1. Assess the current state of the Langchain Sdk Patterns configuration\n2. Identify the specific requirements and constraints\n3. Apply the recommended patterns from this skill\n4. Validate the changes against expected behavior\n5. Document the configuration for team reference\n\n## Examples\n\n**Basic usage**: Apply langchain sdk patterns to a standard project setup with default configuration options.\n\n**Advanced scenario**: Customize langchain sdk patterns for production environments with multiple constraints and team-specific requirements.","# LangChain SDK Patterns\n\n## Overview\nProduction-ready patterns for LangChain applications including LCEL chains, structured output, and error handling.\n\n## Prerequisites\n- Completed `langchain-install-auth` setup\n- Familiarity with async\u002Fawait patterns\n- Understanding of error handling best practices\n\n## Core Patterns\n\n### Pattern 1: Type-Safe Chain with Pydantic\n```python\nfrom pydantic import BaseModel, Field\nfrom langchain_openai import ChatOpenAI\nfrom langchain_core.prompts import ChatPromptTemplate\n\nclass SentimentResult(BaseModel):\n    \"\"\"Structured output for sentiment analysis.\"\"\"\n    sentiment: str = Field(description=\"positive, negative, or neutral\")\n    confidence: float = Field(description=\"Confidence score 0-1\")\n    reasoning: str = Field(description=\"Brief explanation\")\n\nllm = ChatOpenAI(model=\"gpt-4o-mini\")\nstructured_llm = llm.with_structured_output(SentimentResult)\n\nprompt = ChatPromptTemplate.from_template(\n    \"Analyze the sentiment of: {text}\"\n)\n\nchain = prompt | structured_llm\n\n# Returns typed SentimentResult\nresult: SentimentResult = chain.invoke({\"text\": \"I love LangChain!\"})\nprint(f\"Sentiment: {result.sentiment} ({result.confidence})\")\n```\n\n### Pattern 2: Retry with Fallback\n```python\nfrom langchain_openai import ChatOpenAI\nfrom langchain_anthropic import ChatAnthropic\nfrom langchain_core.runnables import RunnableWithFallbacks\n\nprimary = ChatOpenAI(model=\"gpt-4o\")\nfallback = ChatAnthropic(model=\"claude-3-5-sonnet-20241022\")  # 20241022 = date\u002Fversion stamp\n\n# Automatically falls back on failure\nrobust_llm = primary.with_fallbacks([fallback])\n\nresponse = robust_llm.invoke(\"Hello!\")\n```\n\n### Pattern 3: Async Batch Processing\n```python\nimport asyncio\nfrom langchain_openai import ChatOpenAI\nfrom langchain_core.prompts import ChatPromptTemplate\n\nllm = ChatOpenAI(model=\"gpt-4o-mini\")\nprompt = ChatPromptTemplate.from_template(\"Summarize: {text}\")\nchain = prompt | llm\n\nasync def process_batch(texts: list[str]) -> list:\n    \"\"\"Process multiple texts concurrently.\"\"\"\n    inputs = [{\"text\": t} for t in texts]\n    results = await chain.abatch(inputs, config={\"max_concurrency\": 5})\n    return results\n\n# Usage\nresults = asyncio.run(process_batch([\"text1\", \"text2\", \"text3\"]))\n```\n\n### Pattern 4: Streaming with Callbacks\n```python\nfrom langchain_openai import ChatOpenAI\nfrom langchain_core.callbacks import StreamingStdOutCallbackHandler\n\nllm = ChatOpenAI(\n    model=\"gpt-4o-mini\",\n    streaming=True,\n    callbacks=[StreamingStdOutCallbackHandler()]\n)\n\n# Streams tokens to stdout as they arrive\nfor chunk in llm.stream(\"Tell me a story\"):\n    # Each chunk contains partial content\n    pass\n```\n\n### Pattern 5: Caching for Cost Reduction\n```python\nfrom langchain_openai import ChatOpenAI\nfrom langchain_core.globals import set_llm_cache\nfrom langchain_community.cache import SQLiteCache\n\n# Enable SQLite caching\nset_llm_cache(SQLiteCache(database_path=\".langchain_cache.db\"))\n\nllm = ChatOpenAI(model=\"gpt-4o-mini\")\n\n# First call hits API\nresponse1 = llm.invoke(\"What is 2+2?\")\n\n# Second identical call uses cache (no API cost)\nresponse2 = llm.invoke(\"What is 2+2?\")\n```\n\n## Output\n- Type-safe chains with Pydantic models\n- Robust error handling with fallbacks\n- Efficient async batch processing\n- Cost-effective caching strategies\n\n## Error Handling\n\n### Standard Error Pattern\n```python\nfrom langchain_core.exceptions import OutputParserException\nfrom openai import RateLimitError, APIError\n\ndef safe_invoke(chain, input_data, max_retries=3):\n    \"\"\"Invoke chain with error handling.\"\"\"\n    for attempt in range(max_retries):\n        try:\n            return chain.invoke(input_data)\n        except RateLimitError:\n            if attempt \u003C max_retries - 1:\n                time.sleep(2 ** attempt)\n                continue\n            raise\n        except OutputParserException as e:\n            # Handle parsing failures\n            return {\"error\": str(e), \"raw\": e.llm_output}\n        except APIError as e:\n            raise RuntimeError(f\"API error: {e}\")\n```\n\n## Resources\n- [LCEL Documentation](https:\u002F\u002Fpython.langchain.com\u002Fdocs\u002Fconcepts\u002Flcel\u002F)\n- [Structured Output](https:\u002F\u002Fpython.langchain.com\u002Fdocs\u002Fconcepts\u002Fstructured_outputs\u002F)\n- [Fallbacks](https:\u002F\u002Fpython.langchain.com\u002Fdocs\u002Fhow_to\u002Ffallbacks\u002F)\n- [Caching](https:\u002F\u002Fpython.langchain.com\u002Fdocs\u002Fhow_to\u002Fllm_caching\u002F)\n\n## Next Steps\nProceed to `langchain-core-workflow-a` for chains and prompts workflow.\n\n## Instructions\n\n1. Assess the current state of the Langchain Sdk Patterns configuration\n2. Identify the specific requirements and constraints\n3. Apply the recommended patterns from this skill\n4. Validate the changes against expected behavior\n5. Document the configuration for team reference\n\n## Examples\n\n**Basic usage**: Apply langchain sdk patterns to a standard project setup with default configuration options.\n\n**Advanced scenario**: Customize langchain sdk patterns for production environments with multiple constraints and team-specific requirements.",{"name":5,"author":24,"license":15,"version":25,"description":26,"allowed-tools":27,"compatible-with":28},"Jeremy Longshore \u003Cjeremy@intentsolutions.io>","1.0.0","Apply production-ready LangChain SDK patterns for chains, agents, and memory.\nUse when implementing LangChain integrations, refactoring code,\nor establishing team coding standards for LangChain applications.\nTrigger with phrases like \"langchain SDK patterns\", \"langchain best practices\",\n\"langchain code patterns\", \"idiomatic langchain\", \"langchain architecture\".\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 langchain-sdk-patterns",{"tool":41,"command":42},"bunx","bunx skills add SamuelChien\u002Fmega-skills-collection --skill langchain-sdk-patterns",{"tool":44,"command":45},"pnpm","pnpm dlx skills add SamuelChien\u002Fmega-skills-collection --skill langchain-sdk-patterns","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Flangchain-sdk-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",[],[]]