--- title: "langchain-ai/langchain-skills" description: "Agent Skills from langchain-ai/langchain-skills." source: https://github.com/langchain-ai/langchain-skills ref: main license: null licenseName: "No licence detected" canonical: https://skillsdocs.com/langchain-ai/langchain-skills base: https://github.com/langchain-ai/langchain-skills/blob/main/ chapters: 22 inlined: 0 withheld: 22 words: 14966 updated: 2026-08-07T18:04:49Z generator: "Skills Docs" --- > **langchain-ai/langchain-skills** — every Agent Skill in this repository, inlined verbatim. > > Canonical HTML: https://skillsdocs.com/langchain-ai/langchain-skills > Per-chapter Markdown: https://skillsdocs.com/langchain-ai/langchain-skills/.md > Machine manifest: https://skillsdocs.com/langchain-ai/langchain-skills/.well-known/agent-skills/index.json > JSON: https://skillsdocs.com/api/v1/books/langchain-ai/langchain-skills > Install: `npx skills add langchain-ai/langchain-skills` > Upstream: https://github.com/langchain-ai/langchain-skills @ `main` > Licence: No licence detected — all rights reserved by its authors > > Content is mirrored from GitHub and © its authors, served unmodified. Takedown: https://github.com/DreambaseAI/skillsdocs/issues/new?labels=takedown&title=Takedown+request # langchain-ai/langchain-skills - **Chapters:** 22 - **Inlined:** 0 (licence detected) - **Words:** 14,966 - **Reading time:** 69 min - **Stars:** 1,123 ## Table of contents 1. [deep-agents-core](https://skillsdocs.com/langchain-ai/langchain-skills/deep-agents-core.md) — Not licensed for republication — link only. 2. [deep-agents-memory](https://skillsdocs.com/langchain-ai/langchain-skills/deep-agents-memory.md) — Not licensed for republication — link only. 3. [deep-agents-orchestration](https://skillsdocs.com/langchain-ai/langchain-skills/deep-agents-orchestration.md) — Not licensed for republication — link only. 4. [deepagents-python-quickstart](https://skillsdocs.com/langchain-ai/langchain-skills/deepagents-python-quickstart.md) — Not licensed for republication — link only. 5. [deepagents-typescript-quickstart](https://skillsdocs.com/langchain-ai/langchain-skills/deepagents-typescript-quickstart.md) — Not licensed for republication — link only. 6. [ecosystem-primer](https://skillsdocs.com/langchain-ai/langchain-skills/ecosystem-primer.md) — Not licensed for republication — link only. 7. [eval-engineering](https://skillsdocs.com/langchain-ai/langchain-skills/eval-engineering.md) — Not licensed for republication — link only. 8. [langchain-dependencies](https://skillsdocs.com/langchain-ai/langchain-skills/langchain-dependencies.md) — Not licensed for republication — link only. 9. [langchain-fundamentals](https://skillsdocs.com/langchain-ai/langchain-skills/langchain-fundamentals.md) — Not licensed for republication — link only. 10. [langchain-middleware](https://skillsdocs.com/langchain-ai/langchain-skills/langchain-middleware.md) — Not licensed for republication — link only. 11. [langchain-python-quickstart](https://skillsdocs.com/langchain-ai/langchain-skills/langchain-python-quickstart.md) — Not licensed for republication — link only. 12. [langchain-rag](https://skillsdocs.com/langchain-ai/langchain-skills/langchain-rag.md) — Not licensed for republication — link only. 13. [langchain-typescript-quickstart](https://skillsdocs.com/langchain-ai/langchain-skills/langchain-typescript-quickstart.md) — Not licensed for republication — link only. 14. [langgraph-cli](https://skillsdocs.com/langchain-ai/langchain-skills/langgraph-cli.md) — Not licensed for republication — link only. 15. [langgraph-fundamentals](https://skillsdocs.com/langchain-ai/langchain-skills/langgraph-fundamentals.md) — Not licensed for republication — link only. 16. [langgraph-human-in-the-loop](https://skillsdocs.com/langchain-ai/langchain-skills/langgraph-human-in-the-loop.md) — Not licensed for republication — link only. 17. [langgraph-persistence](https://skillsdocs.com/langchain-ai/langchain-skills/langgraph-persistence.md) — Not licensed for republication — link only. 18. [langgraph-python-quickstart](https://skillsdocs.com/langchain-ai/langchain-skills/langgraph-python-quickstart.md) — Not licensed for republication — link only. 19. [langgraph-typescript-quickstart](https://skillsdocs.com/langchain-ai/langchain-skills/langgraph-typescript-quickstart.md) — Not licensed for republication — link only. 20. [langsmith-online-eval-engineering](https://skillsdocs.com/langchain-ai/langchain-skills/langsmith-online-eval-engineering.md) — Not licensed for republication — link only. 21. [managed-deep-agents](https://skillsdocs.com/langchain-ai/langchain-skills/managed-deep-agents.md) — Not licensed for republication — link only. 22. [swarm](https://skillsdocs.com/langchain-ai/langchain-skills/swarm.md) — Not licensed for republication — link only. ## Licence notice 22 of 22 chapters in this book have no licence that we could detect, at either the repository or the skill level. Their bodies are **not** reproduced here and they are **not** listed in the Agent Skills manifest. Read them upstream: - deep-agents-core — https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/deep-agents-core/SKILL.md - deep-agents-memory — https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/deep-agents-memory/SKILL.md - deep-agents-orchestration — https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/deep-agents-orchestration/SKILL.md - deepagents-python-quickstart — https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/deepagents-python-quickstart/SKILL.md - deepagents-typescript-quickstart — https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/deepagents-typescript-quickstart/SKILL.md - ecosystem-primer — https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/ecosystem-primer/SKILL.md - eval-engineering — https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/eval-engineering/SKILL.md - langchain-dependencies — https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/langchain-dependencies/SKILL.md - langchain-fundamentals — https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/langchain-fundamentals/SKILL.md - langchain-middleware — https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/langchain-middleware/SKILL.md - langchain-python-quickstart — https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/langchain-python-quickstart/SKILL.md - langchain-rag — https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/langchain-rag/SKILL.md - langchain-typescript-quickstart — https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/langchain-typescript-quickstart/SKILL.md - langgraph-cli — https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/langgraph-cli/SKILL.md - langgraph-fundamentals — https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/langgraph-fundamentals/SKILL.md - langgraph-human-in-the-loop — https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/langgraph-human-in-the-loop/SKILL.md - langgraph-persistence — https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/langgraph-persistence/SKILL.md - langgraph-python-quickstart — https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/langgraph-python-quickstart/SKILL.md - langgraph-typescript-quickstart — https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/langgraph-typescript-quickstart/SKILL.md - langsmith-online-eval-engineering — https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/langsmith-online-eval-engineering/SKILL.md - managed-deep-agents — https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/managed-deep-agents/SKILL.md - swarm — https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/swarm/SKILL.md ## Front matter _The repository README, verbatim except that relative links are resolved against https://github.com/langchain-ai/langchain-skills/blob/main/._ # LangChain Skills > **⚠️** — This project is in early development. APIs and skill content may change. Agent skills for building agents with LangChain, LangGraph, and Deep Agents. > For LangSmith-specific trace and dataset workflows, use [langsmith-skills](https://github.com/langchain-ai/langsmith-skills). ## Supported Coding Agents These skills can be installed via [`npx skills`](https://github.com/vercel-labs/skills) for any agent that supports the [Agent Skills specification](https://skills.sh), including Claude Code, Cursor, Windsurf, and more. ## Installation ### Quick Install Using [`npx skills`](https://github.com/vercel-labs/skills): **Local** (current project): ```bash npx skills add langchain-ai/langchain-skills --skill '*' --yes ``` **Global** (all projects): ```bash npx skills add langchain-ai/langchain-skills --skill '*' --yes --global ``` To link skills to a specific agent (e.g. Claude Code): ```bash npx skills add langchain-ai/langchain-skills --agent claude-code --skill '*' --yes --global ``` --- ### Claude Code Plugin Install directly as a [Claude Code plugin](https://code.claude.com/docs/en/plugins): ```bash /plugin marketplace add langchain-ai/langchain-skills /plugin install langchain-skills@langchain-skills ``` --- ### Install Script (Claude Code & Deep Agents CLI only) Alternatively, clone the repo and use the install script: ```bash # Install for Claude Code in current directory (default) ./install.sh # Install for Claude Code in a specific project directory ./install.sh ~/my-project # Install for Claude Code globally ./install.sh --global # Install for Deep Agents CLI in a specific project directory ./install.sh --deepagents ~/my-project # Install for Deep Agents CLI globally (includes agent persona) ./install.sh --deepagents --global ``` | Flag / Argument | Description | |------|-------------| | `DIRECTORY` | Target project directory (default: current directory, ignored with `--global`) | | `--claude` | Install for Claude Code (default) | | `--deepagents` | Install for Deep Agents CLI | | `--global`, `-g` | Install globally instead of current directory | | `--force`, `-f` | Overwrite skills with same names as this package | | `--yes`, `-y` | Skip confirmation prompts | ## Usage After installation, set your API keys: ```bash export OPENAI_API_KEY= # For OpenAI models export ANTHROPIC_API_KEY= # For Anthropic models ``` Then run your coding agent from the directory where you installed (for local installs) or from anywhere (for global installs). ### Eval Engineering To install only the eval-engineering skill: ```bash npx skills add langchain-ai/langchain-skills --skill eval-engineering --yes ``` Or ask Codex: “Install the `eval-engineering` skill from `langchain-ai/langchain-skills`.” Eval tasks require [Harbor](https://www.harborframework.com/docs). Run Harbor locally with Docker or use a supported cloud environment. Then ask your coding agent: ```text Use eval-engineering to inspect this agent and propose two or three Harbor evals. Traces for this agent can be found here [Tracing Project/Location]. ``` ## Available Skills (21) ### Getting Started - **ecosystem-primer** - Start-here primer: framework selection (LangChain vs LangGraph vs Deep Agents), env setup, and which skill to load next - **langchain-dependencies** - Full package version and dependency management reference (Python + TypeScript) ### Quickstarts (local) Thin wrappers around the official Mintlify quickstarts — ask for provider/model (default `anthropic:claude-sonnet-5`), new directory, provider API key only: - **langchain-python-quickstart** / **langchain-typescript-quickstart** → [Python](https://docs.langchain.com/oss/python/langchain/quickstart) / [JS](https://docs.langchain.com/oss/javascript/langchain/quickstart) (weather) - **langgraph-python-quickstart** / **langgraph-typescript-quickstart** → [Python](https://docs.langchain.com/oss/python/langgraph/quickstart) / [JS](https://docs.langchain.com/oss/javascript/langgraph/quickstart) (math) - **deepagents-python-quickstart** / **deepagents-typescript-quickstart** → [Python](https://docs.langchain.com/oss/python/deepagents/quickstart) / [JS](https://docs.langchain.com/oss/javascript/deepagents/quickstart) (research; provider web search instead of Tavily) ### Deep Agents - **deep-agents-core** - Agent architecture, harness setup, and SKILL.md format - **deep-agents-memory** - Memory, persistence, filesystem middleware - **deep-agents-orchestration** - Subagents, task planning, human-in-the-loop - **managed-deep-agents** - Managed Deep Agents: deploy with the CLI, use the SDKs, stream runs, connect MCP tools, and build React `useStream` UIs ### LangChain - **langchain-fundamentals** - Agents with create_agent, tools, structured output, middleware basics - **langchain-middleware** - Human-in-the-loop approval, custom middleware, Command resume patterns - **langchain-rag** - RAG pipeline (document loaders, embeddings, vector stores) ### LangGraph - **langgraph-fundamentals** - StateGraph, nodes, edges, state reducers - **langgraph-persistence** - Checkpointers, thread_id, cross-thread memory - **langgraph-cli** - CLI lifecycle: scaffold, dev, build, deploy, langgraph.json config - **langgraph-human-in-the-loop** - Interrupts, human review, approval workflows ### Evaluation - **eval-engineering** - Build, run, and audit Harbor evals for an existing agent with user approval ### Utilities - **swarm** - Dispatch independent work items in parallel and aggregate the results --- ## 1. deep-agents-core INVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format, and configuration options. - **Source:** https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/deep-agents-core/SKILL.md - **Raw:** https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/deep-agents-core/SKILL.md - **Markdown:** https://skillsdocs.com/langchain-ai/langchain-skills/deep-agents-core.md - **Licence:** No licence detected — all rights reserved by its authors _Body withheld: no licence could be detected for this skill. Read it upstream._ --- ## 2. deep-agents-memory INVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access. Covers StateBackend (ephemeral), StoreBackend (persistent), FilesystemMiddleware, and CompositeBackend for routing. - **Source:** https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/deep-agents-memory/SKILL.md - **Raw:** https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/deep-agents-memory/SKILL.md - **Markdown:** https://skillsdocs.com/langchain-ai/langchain-skills/deep-agents-memory.md - **Licence:** No licence detected — all rights reserved by its authors _Body withheld: no licence could be detected for this skill. Read it upstream._ --- ## 3. deep-agents-orchestration INVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL interrupts. - **Source:** https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/deep-agents-orchestration/SKILL.md - **Raw:** https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/deep-agents-orchestration/SKILL.md - **Markdown:** https://skillsdocs.com/langchain-ai/langchain-skills/deep-agents-orchestration.md - **Licence:** No licence detected — all rights reserved by its authors _Body withheld: no licence could be detected for this skill. Read it upstream._ --- ## 4. deepagents-python-quickstart Scaffold a minimal local Deep Agent in Python by following the official quickstart, using provider-native web search instead of Tavily. Use when the user wants to quickly build or try a Deep Agent locally. - **Source:** https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/deepagents-python-quickstart/SKILL.md - **Raw:** https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/deepagents-python-quickstart/SKILL.md - **Markdown:** https://skillsdocs.com/langchain-ai/langchain-skills/deepagents-python-quickstart.md - **Licence:** No licence detected — all rights reserved by its authors _Body withheld: no licence could be detected for this skill. Read it upstream._ --- ## 5. deepagents-typescript-quickstart Scaffold a minimal local Deep Agent in TypeScript by following the official quickstart, using provider-native web search instead of Tavily. Use when the user wants to quickly build or try a Deep Agent locally. - **Source:** https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/deepagents-typescript-quickstart/SKILL.md - **Raw:** https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/deepagents-typescript-quickstart/SKILL.md - **Markdown:** https://skillsdocs.com/langchain-ai/langchain-skills/deepagents-typescript-quickstart.md - **Licence:** No licence detected — all rights reserved by its authors _Body withheld: no licence could be detected for this skill. Read it upstream._ --- ## 6. ecosystem-primer INVOKE FIRST for any LangChain / LangGraph / Deep Agents agent building project before consulting other skills or writing any agent code. Required starting point for up to date info on framework selection (LangChain vs LangGraph vs Deep Agents vs hybrid composition), agent patterns, install, environment setup, and which skill to load next. - **Source:** https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/ecosystem-primer/SKILL.md - **Raw:** https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/ecosystem-primer/SKILL.md - **Markdown:** https://skillsdocs.com/langchain-ai/langchain-skills/ecosystem-primer.md - **Licence:** No licence detected — all rights reserved by its authors _Body withheld: no licence could be detected for this skill. Read it upstream._ --- ## 7. eval-engineering Iteratively inspect an agent repository and optional user-provided traces, interview the user, and create, run, and audit Harbor evals one at a time. Use for agent evals, Harbor tasks, benchmark cases, verifier design, or controlled agent environments. - **Source:** https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/eval-engineering/SKILL.md - **Raw:** https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/eval-engineering/SKILL.md - **Markdown:** https://skillsdocs.com/langchain-ai/langchain-skills/eval-engineering.md - **Licence:** No licence detected — all rights reserved by its authors Bundled files (10), referenced from this skill's directory: - `references/environment-building.md` — https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/eval-engineering/references/environment-building.md - `references/harbor.md` — https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/eval-engineering/references/harbor.md - `references/harness.md` — https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/eval-engineering/references/harness.md - `references/multi-turn-simulation/guide.md` — https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/eval-engineering/references/multi-turn-simulation/guide.md - `references/multi-turn-simulation/harbor_example.py` — https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/eval-engineering/references/multi-turn-simulation/harbor_example.py - `references/multi-turn-simulation/model_user.py` — https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/eval-engineering/references/multi-turn-simulation/model_user.py - `references/multi-turn-simulation/runner.py` — https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/eval-engineering/references/multi-turn-simulation/runner.py - `references/task-design.md` — https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/eval-engineering/references/task-design.md - `references/trace-sourcing.md` — https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/eval-engineering/references/trace-sourcing.md - `references/verifier-design.md` — https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/eval-engineering/references/verifier-design.md _Body withheld: no licence could be detected for this skill. Read it upstream._ --- ## 8. langchain-dependencies INVOKE THIS SKILL when setting up a new project or when asked about package versions, installation, or dependency management for LangChain, LangGraph, LangSmith, or Deep Agents. Covers required packages, minimum versions, environment requirements, versioning best practices, and common community tool packages for both Python and TypeScript. - **Source:** https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/langchain-dependencies/SKILL.md - **Raw:** https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/langchain-dependencies/SKILL.md - **Markdown:** https://skillsdocs.com/langchain-ai/langchain-skills/langchain-dependencies.md - **Licence:** No licence detected — all rights reserved by its authors _Body withheld: no licence could be detected for this skill. Read it upstream._ --- ## 9. langchain-fundamentals Create LangChain agents with create_agent, define tools, and use middleware for human-in-the-loop and error handling. - **Source:** https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/langchain-fundamentals/SKILL.md - **Raw:** https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/langchain-fundamentals/SKILL.md - **Markdown:** https://skillsdocs.com/langchain-ai/langchain-skills/langchain-fundamentals.md - **Licence:** No licence detected — all rights reserved by its authors _Body withheld: no licence could be detected for this skill. Read it upstream._ --- ## 10. langchain-middleware INVOKE THIS SKILL when you need human-in-the-loop approval, custom middleware, or structured output. Covers HumanInTheLoopMiddleware for human approval of dangerous tool calls, creating custom middleware with hooks, Command resume patterns, and structured output with Pydantic/Zod. - **Source:** https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/langchain-middleware/SKILL.md - **Raw:** https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/langchain-middleware/SKILL.md - **Markdown:** https://skillsdocs.com/langchain-ai/langchain-skills/langchain-middleware.md - **Licence:** No licence detected — all rights reserved by its authors _Body withheld: no licence could be detected for this skill. Read it upstream._ --- ## 11. langchain-python-quickstart Scaffold a minimal local LangChain agent in Python by following the official quickstart. Use when the user wants to quickly build or try a LangChain agent locally. - **Source:** https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/langchain-python-quickstart/SKILL.md - **Raw:** https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/langchain-python-quickstart/SKILL.md - **Markdown:** https://skillsdocs.com/langchain-ai/langchain-skills/langchain-python-quickstart.md - **Licence:** No licence detected — all rights reserved by its authors _Body withheld: no licence could be detected for this skill. Read it upstream._ --- ## 12. 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). - **Source:** https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/langchain-rag/SKILL.md - **Raw:** https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/langchain-rag/SKILL.md - **Markdown:** https://skillsdocs.com/langchain-ai/langchain-skills/langchain-rag.md - **Licence:** No licence detected — all rights reserved by its authors _Body withheld: no licence could be detected for this skill. Read it upstream._ --- ## 13. langchain-typescript-quickstart Scaffold a minimal local LangChain agent in TypeScript by following the official quickstart. Use when the user wants to quickly build or try a LangChain agent locally. - **Source:** https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/langchain-typescript-quickstart/SKILL.md - **Raw:** https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/langchain-typescript-quickstart/SKILL.md - **Markdown:** https://skillsdocs.com/langchain-ai/langchain-skills/langchain-typescript-quickstart.md - **Licence:** No licence detected — all rights reserved by its authors _Body withheld: no licence could be detected for this skill. Read it upstream._ --- ## 14. langgraph-cli INVOKE THIS SKILL when using the langgraph CLI to scaffold, develop, build, or deploy LangGraph applications. Covers langgraph new, dev, build, up, deploy, and langgraph.json configuration. - **Source:** https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/langgraph-cli/SKILL.md - **Raw:** https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/langgraph-cli/SKILL.md - **Markdown:** https://skillsdocs.com/langchain-ai/langchain-skills/langgraph-cli.md - **Licence:** No licence detected — all rights reserved by its authors _Body withheld: no licence could be detected for this skill. Read it upstream._ --- ## 15. langgraph-fundamentals INVOKE THIS SKILL when writing ANY LangGraph code. Covers StateGraph, state schemas, nodes, edges, Command, Send, invoke, streaming, and error handling. - **Source:** https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/langgraph-fundamentals/SKILL.md - **Raw:** https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/langgraph-fundamentals/SKILL.md - **Markdown:** https://skillsdocs.com/langchain-ai/langchain-skills/langgraph-fundamentals.md - **Licence:** No licence detected — all rights reserved by its authors _Body withheld: no licence could be detected for this skill. Read it upstream._ --- ## 16. 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/validation workflows, and the 4-tier error handling strategy. - **Source:** https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/langgraph-human-in-the-loop/SKILL.md - **Raw:** https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/langgraph-human-in-the-loop/SKILL.md - **Markdown:** https://skillsdocs.com/langchain-ai/langchain-skills/langgraph-human-in-the-loop.md - **Licence:** No licence detected — all rights reserved by its authors _Body withheld: no licence could be detected for this skill. Read it upstream._ --- ## 17. 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. - **Source:** https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/langgraph-persistence/SKILL.md - **Raw:** https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/langgraph-persistence/SKILL.md - **Markdown:** https://skillsdocs.com/langchain-ai/langchain-skills/langgraph-persistence.md - **Licence:** No licence detected — all rights reserved by its authors _Body withheld: no licence could be detected for this skill. Read it upstream._ --- ## 18. langgraph-python-quickstart Scaffold a minimal local LangGraph agent in Python by following the official quickstart. Use when the user wants to quickly build or try a LangGraph agent locally. - **Source:** https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/langgraph-python-quickstart/SKILL.md - **Raw:** https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/langgraph-python-quickstart/SKILL.md - **Markdown:** https://skillsdocs.com/langchain-ai/langchain-skills/langgraph-python-quickstart.md - **Licence:** No licence detected — all rights reserved by its authors _Body withheld: no licence could be detected for this skill. Read it upstream._ --- ## 19. langgraph-typescript-quickstart Scaffold a minimal local LangGraph agent in TypeScript by following the official quickstart. Use when the user wants to quickly build or try a LangGraph agent locally. - **Source:** https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/langgraph-typescript-quickstart/SKILL.md - **Raw:** https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/langgraph-typescript-quickstart/SKILL.md - **Markdown:** https://skillsdocs.com/langchain-ai/langchain-skills/langgraph-typescript-quickstart.md - **Licence:** No licence detected — all rights reserved by its authors _Body withheld: no licence could be detected for this skill. Read it upstream._ --- ## 20. langsmith-online-eval-engineering Iteratively inspect traces, interview the user, and create LangSmith online evaluators one at a time. Use specifically for creating online evaluators for use within LangSmith -- use "eval-engineering" for Harbor-style online evaluations. - **Source:** https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/langsmith-online-eval-engineering/SKILL.md - **Raw:** https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/langsmith-online-eval-engineering/SKILL.md - **Markdown:** https://skillsdocs.com/langchain-ai/langchain-skills/langsmith-online-eval-engineering.md - **Licence:** No licence detected — all rights reserved by its authors Bundled files (3), referenced from this skill's directory: - `references/evaluator-design.md` — https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/langsmith-online-eval-engineering/references/evaluator-design.md - `references/langsmith-api.md` — https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/langsmith-online-eval-engineering/references/langsmith-api.md - `references/trace-inspection.md` — https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/langsmith-online-eval-engineering/references/trace-inspection.md _Body withheld: no licence could be detected for this skill. Read it upstream._ --- ## 21. managed-deep-agents INVOKE THIS SKILL when building, testing, or deploying Managed Deep Agents in LangSmith with the mda CLI. Walks a user through their first agent end to end — interviewing them about what they want to build, mapping it onto what MDA can actually do, then scaffolding and deploying it. Covers the file-based project layout; define_deep_agent / defineDeepAgent; instructions, skills, memory, identity, tools, middleware, sandboxes, schedules, channels, and evals; mda init/build/dev/deploy/logs/delete; and Context Hub. - **Source:** https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/managed-deep-agents/SKILL.md - **Raw:** https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/managed-deep-agents/SKILL.md - **Markdown:** https://skillsdocs.com/langchain-ai/langchain-skills/managed-deep-agents.md - **Licence:** No licence detected — all rights reserved by its authors _Body withheld: no licence could be detected for this skill. Read it upstream._ --- ## 22. swarm Dispatches many independent items in parallel: create a table, fan out to subagents, aggregate results. One row = one unit of work. - **Source:** https://github.com/langchain-ai/langchain-skills/blob/main/config/skills/swarm/SKILL.md - **Raw:** https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/swarm/SKILL.md - **Markdown:** https://skillsdocs.com/langchain-ai/langchain-skills/swarm.md - **Licence:** No licence detected — all rights reserved by its authors Bundled files (8), referenced from this skill's directory: - `scripts/batching.ts` — https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/swarm/scripts/batching.ts - `scripts/executor.ts` — https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/swarm/scripts/executor.ts - `scripts/filter.ts` — https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/swarm/scripts/filter.ts - `scripts/index.ts` — https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/swarm/scripts/index.ts - `scripts/interpolate.ts` — https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/swarm/scripts/interpolate.ts - `scripts/table.ts` — https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/swarm/scripts/table.ts - `scripts/types.ts` — https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/swarm/scripts/types.ts - `scripts/utils.ts` — https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/swarm/scripts/utils.ts _Body withheld: no licence could be detected for this skill. Read it upstream._