[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6C62XSSA8RNWCV71NQCBYYN":3,"skill-same:01M6C62XSSA8RNWCV71NQCBYYN":62},{"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":26,"linkOnly":27,"markdownContent":28,"markdownBody":29,"frontMatter":30,"refName":31,"commitSha":32,"skillDirectory":33,"forksCount":14,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":36,"ownerDescription":6,"updatedAt":37,"install":38,"resources":51},"01M6C62XSSA8RNWCV71NQCBYYN","framework-selection",null,"INVOKE THIS SKILL at the START of any LangChain\u002FLangGraph\u002FDeep Agents project, before writing any agent code. Determines which framework layer is right for the task: LangChain, LangGraph, Deep Agents, or a combination. Must be consulted before other agent skills.","CoralShades\u002Facm-ai","CoralShades","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F220297585?v=4","01M6C5211QSJHZ8HXSDDWCR507","Coral Shades AI Agency","01M6C52161FNQDRQ0FRR8DAA9D",0,"MIT","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Fframework-selection\u002FSKILL.md",[],[19,20,21,22,23,24,25],"framework","framework selection","writing","code","start","langgraph","langchain","2026-11-10 10:12:30",false,"---\nname: framework-selection\ndescription: \"INVOKE THIS SKILL at the START of any LangChain\u002FLangGraph\u002FDeep Agents project, before writing any agent code. Determines which framework layer is right for the task: LangChain, LangGraph, Deep Agents, or a combination. Must be consulted before other agent skills.\"\n---\n\n\u003Coverview>\nLangChain, LangGraph, and Deep Agents are **layered**, not competing choices. Each builds on the one below it:\n\n```\n┌─────────────────────────────────────────┐\n│              Deep Agents                │  ← highest level: batteries included\n│   (planning, memory, skills, files)     │\n├─────────────────────────────────────────┤\n│               LangGraph                 │  ← orchestration: graphs, loops, state\n│    (nodes, edges, state, persistence)   │\n├─────────────────────────────────────────┤\n│               LangChain                 │  ← foundation: models, tools, chains\n│      (models, tools, prompts, RAG)      │\n└─────────────────────────────────────────┘\n```\n\nPicking a higher layer does not cut you off from lower layers — you can use LangGraph graphs inside Deep Agents, and LangChain primitives inside both.\n\n> **This skill should be loaded at the top of any project before selecting other skills or writing agent code.** The framework you choose dictates which other skills to invoke next.\n\u003C\u002Foverview>\n\n---\n\n## Decision Guide\n\n\u003Cdecision-table>\n\nAnswer these questions in order:\n\n| Question | Yes → | No → |\n|----------|-------|-------|\n| Does the task require breaking work into sub-tasks, managing files across a long session, persistent memory, or loading on-demand skills? | **Deep Agents** | ↓ |\n| Does the task require complex control flow — loops, dynamic branching, parallel workers, human-in-the-loop, or custom state? | **LangGraph** | ↓ |\n| Is this a single-purpose agent that takes input, runs tools, and returns a result? | **LangChain** (`create_agent`) | ↓ |\n| Is this a pure model call, chain, or retrieval pipeline with no agent loop? | **LangChain** (LCEL \u002F chain) | — |\n\n\u003C\u002Fdecision-table>\n\n---\n\n## Framework Profiles\n\n\u003Clangchain-profile>\n\n### LangChain — Use when the task is focused and self-contained\n\n**Best for:**\n- Single-purpose agents that use a fixed set of tools\n- RAG pipelines and document Q&A\n- Model calls, prompt templates, output parsing\n- Quick prototypes where agent logic is simple\n\n**Not ideal when:**\n- The agent needs to plan across many steps\n- State needs to persist across multiple sessions\n- Control flow is conditional or iterative\n\n**Skills to invoke next:** `langchain-models`, `langchain-rag`, `langchain-middleware`\n\n\u003C\u002Flangchain-profile>\n\n\u003Clanggraph-profile>\n\n### LangGraph — Use when you need to own the control flow\n\n**Best for:**\n- Agents with branching logic or loops (e.g. retry-until-correct, reflection)\n- Multi-step workflows where different paths depend on intermediate results\n- Human-in-the-loop approval at specific steps\n- Parallel fan-out \u002F fan-in (map-reduce patterns)\n- Persistent state across invocations within a session\n\n**Not ideal when:**\n- You want planning, file management, and subagent delegation handled for you (use Deep Agents instead)\n- The workflow is straightforward enough for a simple agent\n\n**Skills to invoke next:** `langgraph-fundamentals`, `langgraph-human-in-the-loop`, `langgraph-persistence`\n\n\u003C\u002Flanggraph-profile>\n\n\u003Cdeep-agents-profile>\n\n### Deep Agents — Use when the task is open-ended and multi-dimensional\n\n**Best for:**\n- Long-running tasks that require breaking work into a todo list\n- Agents that need to read, write, and manage files across a session\n- Delegating subtasks to specialized subagents\n- Loading domain-specific skills on demand\n- Persistent memory that survives across multiple sessions\n\n**Not ideal when:**\n- The task is simple enough for a single-purpose agent\n- You need precise, hand-crafted control over every graph edge (use LangGraph directly)\n\n**Middleware — built-in and extensible:**\n\nDeep Agents ships with a built-in middleware layer out of the box — you configure it, you don't implement it. The following come pre-wired; you can also add your own on top:\n\n| Middleware | What it provides | Always on? |\n|------------|-----------------|------------|\n| `TodoListMiddleware` | `write_todos` tool — agent plans and tracks multi-step tasks | ✓ |\n| `FilesystemMiddleware` | `ls`, `read_file`, `write_file`, `edit_file`, `glob`, `grep` tools | ✓ |\n| `SubAgentMiddleware` | `task` tool — delegate work to named subagents | ✓ |\n| `SkillsMiddleware` | Load SKILL.md files on demand from a skills directory | Opt-in |\n| `MemoryMiddleware` | Long-term memory across sessions via a `Store` instance | Opt-in |\n| `HumanInTheLoopMiddleware` | Interrupt and request human approval before sensitive tool calls | Opt-in |\n\n**Skills to invoke next:** `deep-agents-core`, `deep-agents-memory`, `deep-agents-orchestration`\n\n\u003C\u002Fdeep-agents-profile>\n\n---\n\n## Mixing Layers\n\n\u003Cmixing-layers>\nBecause the frameworks are layered, they can be combined in the same project. The most common pattern is using Deep Agents as the top-level orchestrator while dropping down to LangGraph for specialized subagents.\n\n### When to mix\n\n| Scenario | Recommended pattern |\n|----------|---------------------|\n| Main agent needs planning + memory, but one subtask requires precise graph control | Deep Agents orchestrator → LangGraph subagent |\n| Specialized pipeline (e.g. RAG, reflection loop) is called by a broader agent | LangGraph graph wrapped as a tool or subagent |\n| High-level coordination but low-level graph for a specific domain | Deep Agents + LangGraph compiled graph as a subagent |\n\n### How it works in practice\n\nA LangGraph compiled graph can be registered as a subagent inside Deep Agents. This means you can build a tightly-controlled LangGraph workflow (e.g. a retrieval-and-verify loop) and hand it off to the Deep Agents `task` tool as a named subagent — the Deep Agents orchestrator delegates to it without caring about its internal graph structure.\n\nLangChain tools, chains, and retrievers can be used freely inside both LangGraph nodes and Deep Agents tools — they are the shared building blocks at every level.\n\n\u003C\u002Fmixing-layers>\n\n---\n\n## Quick Reference\n\n\u003Cquick-reference>\n\n| | LangChain | LangGraph | Deep Agents |\n|---|-----------|-----------|-------------|\n| **Control flow** | Fixed (tool loop) | Custom (graph) | Managed (middleware) |\n| **Middleware layer** | Callbacks only | ✗ None | ✓ Explicit, configurable |\n| **Planning** | ✗ | Manual | ✓ TodoListMiddleware |\n| **File management** | ✗ | Manual | ✓ FilesystemMiddleware |\n| **Persistent memory** | ✗ | With checkpointer | ✓ MemoryMiddleware |\n| **Subagent delegation** | ✗ | Manual | ✓ SubAgentMiddleware |\n| **On-demand skills** | ✗ | ✗ | ✓ SkillsMiddleware |\n| **Human-in-the-loop** | ✗ | Manual interrupt | ✓ HumanInTheLoopMiddleware |\n| **Custom graph edges** | ✗ | ✓ Full control | Limited |\n| **Setup complexity** | Low | Medium | Low |\n| **Flexibility** | Medium | High | Medium |\n\n> **Middleware is a concept specific to LangChain (callbacks) and Deep Agents (explicit middleware layer). LangGraph has no middleware — you wire behavior directly into nodes and edges.**\n\n\u003C\u002Fquick-reference>\n","\u003Coverview>\nLangChain, LangGraph, and Deep Agents are **layered**, not competing choices. Each builds on the one below it:\n\n```\n┌─────────────────────────────────────────┐\n│              Deep Agents                │  ← highest level: batteries included\n│   (planning, memory, skills, files)     │\n├─────────────────────────────────────────┤\n│               LangGraph                 │  ← orchestration: graphs, loops, state\n│    (nodes, edges, state, persistence)   │\n├─────────────────────────────────────────┤\n│               LangChain                 │  ← foundation: models, tools, chains\n│      (models, tools, prompts, RAG)      │\n└─────────────────────────────────────────┘\n```\n\nPicking a higher layer does not cut you off from lower layers — you can use LangGraph graphs inside Deep Agents, and LangChain primitives inside both.\n\n> **This skill should be loaded at the top of any project before selecting other skills or writing agent code.** The framework you choose dictates which other skills to invoke next.\n\u003C\u002Foverview>\n\n---\n\n## Decision Guide\n\n\u003Cdecision-table>\n\nAnswer these questions in order:\n\n| Question | Yes → | No → |\n|----------|-------|-------|\n| Does the task require breaking work into sub-tasks, managing files across a long session, persistent memory, or loading on-demand skills? | **Deep Agents** | ↓ |\n| Does the task require complex control flow — loops, dynamic branching, parallel workers, human-in-the-loop, or custom state? | **LangGraph** | ↓ |\n| Is this a single-purpose agent that takes input, runs tools, and returns a result? | **LangChain** (`create_agent`) | ↓ |\n| Is this a pure model call, chain, or retrieval pipeline with no agent loop? | **LangChain** (LCEL \u002F chain) | — |\n\n\u003C\u002Fdecision-table>\n\n---\n\n## Framework Profiles\n\n\u003Clangchain-profile>\n\n### LangChain — Use when the task is focused and self-contained\n\n**Best for:**\n- Single-purpose agents that use a fixed set of tools\n- RAG pipelines and document Q&A\n- Model calls, prompt templates, output parsing\n- Quick prototypes where agent logic is simple\n\n**Not ideal when:**\n- The agent needs to plan across many steps\n- State needs to persist across multiple sessions\n- Control flow is conditional or iterative\n\n**Skills to invoke next:** `langchain-models`, `langchain-rag`, `langchain-middleware`\n\n\u003C\u002Flangchain-profile>\n\n\u003Clanggraph-profile>\n\n### LangGraph — Use when you need to own the control flow\n\n**Best for:**\n- Agents with branching logic or loops (e.g. retry-until-correct, reflection)\n- Multi-step workflows where different paths depend on intermediate results\n- Human-in-the-loop approval at specific steps\n- Parallel fan-out \u002F fan-in (map-reduce patterns)\n- Persistent state across invocations within a session\n\n**Not ideal when:**\n- You want planning, file management, and subagent delegation handled for you (use Deep Agents instead)\n- The workflow is straightforward enough for a simple agent\n\n**Skills to invoke next:** `langgraph-fundamentals`, `langgraph-human-in-the-loop`, `langgraph-persistence`\n\n\u003C\u002Flanggraph-profile>\n\n\u003Cdeep-agents-profile>\n\n### Deep Agents — Use when the task is open-ended and multi-dimensional\n\n**Best for:**\n- Long-running tasks that require breaking work into a todo list\n- Agents that need to read, write, and manage files across a session\n- Delegating subtasks to specialized subagents\n- Loading domain-specific skills on demand\n- Persistent memory that survives across multiple sessions\n\n**Not ideal when:**\n- The task is simple enough for a single-purpose agent\n- You need precise, hand-crafted control over every graph edge (use LangGraph directly)\n\n**Middleware — built-in and extensible:**\n\nDeep Agents ships with a built-in middleware layer out of the box — you configure it, you don't implement it. The following come pre-wired; you can also add your own on top:\n\n| Middleware | What it provides | Always on? |\n|------------|-----------------|------------|\n| `TodoListMiddleware` | `write_todos` tool — agent plans and tracks multi-step tasks | ✓ |\n| `FilesystemMiddleware` | `ls`, `read_file`, `write_file`, `edit_file`, `glob`, `grep` tools | ✓ |\n| `SubAgentMiddleware` | `task` tool — delegate work to named subagents | ✓ |\n| `SkillsMiddleware` | Load SKILL.md files on demand from a skills directory | Opt-in |\n| `MemoryMiddleware` | Long-term memory across sessions via a `Store` instance | Opt-in |\n| `HumanInTheLoopMiddleware` | Interrupt and request human approval before sensitive tool calls | Opt-in |\n\n**Skills to invoke next:** `deep-agents-core`, `deep-agents-memory`, `deep-agents-orchestration`\n\n\u003C\u002Fdeep-agents-profile>\n\n---\n\n## Mixing Layers\n\n\u003Cmixing-layers>\nBecause the frameworks are layered, they can be combined in the same project. The most common pattern is using Deep Agents as the top-level orchestrator while dropping down to LangGraph for specialized subagents.\n\n### When to mix\n\n| Scenario | Recommended pattern |\n|----------|---------------------|\n| Main agent needs planning + memory, but one subtask requires precise graph control | Deep Agents orchestrator → LangGraph subagent |\n| Specialized pipeline (e.g. RAG, reflection loop) is called by a broader agent | LangGraph graph wrapped as a tool or subagent |\n| High-level coordination but low-level graph for a specific domain | Deep Agents + LangGraph compiled graph as a subagent |\n\n### How it works in practice\n\nA LangGraph compiled graph can be registered as a subagent inside Deep Agents. This means you can build a tightly-controlled LangGraph workflow (e.g. a retrieval-and-verify loop) and hand it off to the Deep Agents `task` tool as a named subagent — the Deep Agents orchestrator delegates to it without caring about its internal graph structure.\n\nLangChain tools, chains, and retrievers can be used freely inside both LangGraph nodes and Deep Agents tools — they are the shared building blocks at every level.\n\n\u003C\u002Fmixing-layers>\n\n---\n\n## Quick Reference\n\n\u003Cquick-reference>\n\n| | LangChain | LangGraph | Deep Agents |\n|---|-----------|-----------|-------------|\n| **Control flow** | Fixed (tool loop) | Custom (graph) | Managed (middleware) |\n| **Middleware layer** | Callbacks only | ✗ None | ✓ Explicit, configurable |\n| **Planning** | ✗ | Manual | ✓ TodoListMiddleware |\n| **File management** | ✗ | Manual | ✓ FilesystemMiddleware |\n| **Persistent memory** | ✗ | With checkpointer | ✓ MemoryMiddleware |\n| **Subagent delegation** | ✗ | Manual | ✓ SubAgentMiddleware |\n| **On-demand skills** | ✗ | ✗ | ✓ SkillsMiddleware |\n| **Human-in-the-loop** | ✗ | Manual interrupt | ✓ HumanInTheLoopMiddleware |\n| **Custom graph edges** | ✗ | ✓ Full control | Limited |\n| **Setup complexity** | Low | Medium | Low |\n| **Flexibility** | Medium | High | Medium |\n\n> **Middleware is a concept specific to LangChain (callbacks) and Deep Agents (explicit middleware layer). LangGraph has no middleware — you wire behavior directly into nodes and edges.**\n\n\u003C\u002Fquick-reference>\n",{"name":5,"description":7},"main","1ca81b0a7de199942400f965edd4d7544077ac5d",".qwen\u002Fskills\u002Fframework-selection","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai","https:\u002F\u002Fgithub.com\u002FCoralShades","coralshades.com.au","2026-04-18 00:45:07",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add CoralShades\u002Facm-ai --skill framework-selection",{"tool":44,"command":45},"bunx","bunx skills add CoralShades\u002Facm-ai --skill framework-selection",{"tool":47,"command":48},"pnpm","pnpm dlx skills add CoralShades\u002Facm-ai --skill framework-selection","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Fframework-selection\u002FSKILL.md",true,[52,58],{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"SOURCE.md","REFERENCE","参考文档",182,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fai-crypto\u002Fclawdia-clawplaza\u002FSOURCE.md",{"path":59,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":60,"sourceHtmlUrl":61},"TRUST.auto.yaml",2217,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fai-crypto\u002Fclawdia-clawplaza\u002FTRUST.auto.yaml",[63,86,99,114,136,145],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":74,"publishedAt":26},"01M6C63HKXA890HHV47WBAX0TB","uncodixfy","Prevents generic AI\u002FCodex UI patterns when generating frontend code. Use this skill whenever generating HTML, CSS, React, Vue, Svelte, or any frontend UI code to enforce clean, human-designed aesthetics inspired by Linear, Raycast, Stripe, and GitHub instead of typical AI-generated UI.","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Funcodixfy\u002FSKILL.md",[69],{"categoryNo":70,"categoryName":71,"taxonomyType":72,"taxonomyTypeDesc":73},"01JBSEEDCAT000000000000009","前端开发","SCENARIO","使用场景",[65,75,76,77,78,79,22,80,81,82,83,84,85],"github","frontend","css","codex","react","linear","ui","vue","generated","use","html",{"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":90,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":26},"01M6C63FJ2GEBBGZ5XSMV40KXB","runpodctl","Runpod CLI to manage your GPU workloads.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Frunpodctl\u002FSKILL.md",[],[88,94,95,96,97,98],"macos","cli","linux","gpu","Bash",{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":26},"01M6C63DPAV46TFVQ01SFYPJ7X","langgraph-persistence","INVOKE THIS SKILL when your LangGraph needs to persist state, remember conversations, travel through history, or configure subgraph checkpointer scoping. Covers checkpointers, thread_id, time travel, Store, and subgraph persistence modes.","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Flanggraph-persistence\u002FSKILL.md",[],[106,24,107,108,109,110,111,112,113],"langgraph persistence","persistence","travel","history","scoping","remember","state","configure",{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":125,"publishedAt":26},"01M6C63BNS9CQEBTB8RNSSBFPA","langgraph-human-in-the-loop","INVOKE THIS SKILL when implementing human-in-the-loop patterns, pausing for approval, or handling errors in LangGraph. Covers interrupt(), Command(resume=...), approval\u002Fvalidation workflows, and the 4-tier error handling strategy.","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Flanggraph-human-in-the-loop\u002FSKILL.md",[120],{"categoryNo":121,"categoryName":122,"taxonomyType":123,"taxonomyTypeDesc":124},"01JBSEEDCAT000000000000038","人力资源","PROFESSION","适用职业",[126,127,24,128,129,130,131,132,133,134,135],"langgraph human in the loop","loop","workflows","error handling","validation","human-in-the-loop","command","strategy","approval","resume",{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":142,"publishedAt":26},"01M6C639GVYZFX3NFPV5FBDR4F","langgraph-fundamentals","INVOKE THIS SKILL when writing ANY LangGraph code. Covers StateGraph, state schemas, nodes, edges, Command, Send, invoke, streaming, and error handling.","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Flanggraph-fundamentals\u002FSKILL.md",[],[143,24,129,112,144,21,132,22],"langgraph fundamentals","streaming",{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":151,"publishedAt":26},"01M6C6375N34YX2GZ3SD3R7XR2","langchain-rag","INVOKE THIS SKILL when building ANY retrieval-augmented generation (RAG) system. Covers document loaders, RecursiveCharacterTextSplitter, embeddings (OpenAI), and vector stores (Chroma, FAISS, Pinecone).","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Flangchain-rag\u002FSKILL.md",[],[152,153,25,154,155,156,157,158,159,160],"rag","langchain rag","embeddings","vector","openai","chroma","faiss","vector stores","system"]