Skill collection · langchain-ai
langchain-skills agent skills by langchain-ai
21 skills from langchain-ai/langchain-skills are listed in the directory, across 4 categories.
View langchain-ai/langchain-skills on GitHub
At a glance
| Publisher | langchain-ai Official |
|---|---|
| Repository | github.com/langchain-ai/langchain-skills |
| Listed skills | 21 |
| Security scan | Not scanned |
| Categories | AI Agents and LLM Engineering, Developer Tools and Frameworks, Writing and Editing, DevOps and Cloud |
| License | MIT |
| Last commit | October 2, 2026 |
| README badge | Get the badge for this listing |
Show the listing in your README
This general badge links to the repository listing. For the two quality badges and feature offer, choose Get badges beside a skill below. Each skill keeps its own score and grade.
Markdown
[](https://skills.suedeai.ai/directory/langchain-ai/langchain-skills/)HTML
<a href="https://skills.suedeai.ai/directory/langchain-ai/langchain-skills/"><img src="https://skills.suedeai.ai/directory/langchain-ai/langchain-skills/badge.svg" alt="Suede Skills Directory: listed" height="20"></a>Limited-time feature offer: display either the numeric or letter badge in your repository or skill README (both also qualify), then request badge verification. Eligible skills scoring 80–99 can receive a featured placement after Suede verifies at least one valid badge linked to the skill’s listing. Suede has not announced an end date.
Skills in langchain-ai/langchain-skills
Linked names open the skill's directory page; the rest open the skill folder on GitHub. Descriptions on rows without a page are quoted from each SKILL.md.
| Skill | Category | What it does |
|---|---|---|
| deep-agents-core 77/100 · C | AI agents | INVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format, and configuration… |
| deep-agents-memory 77/100 · C | AI agents | INVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access. Covers StateBackend (ephemeral), StoreBackend (persistent)… |
| deep-agents-orchestration 69/100 · D | AI agents | INVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL… |
| deepagents-python-quickstart 74/100 · C | AI agents | Scaffold a minimal local Deep Agent in Python by following the official quickstart, using provider-native web search instead of Tavily. Use when the… |
| deepagents-typescript-quickstart 74/100 · C | AI agents | Scaffold a minimal local Deep Agent in TypeScript by following the official quickstart, using provider-native web search instead of Tavily. Use when… |
| ecosystem-primer 69/100 · D | AI agents | INVOKE FIRST for any LangChain / LangGraph / Deep Agents agent building project before consulting other skills or writing any agent code. Required… |
| eval-engineering 82/100 · B | AI agents | Inspect an agent repository and optional traces, interview the user, write reviewed Task Specs, build and audit Harbor tasks, and bootstrap reusable…Get badges  Choose the numeric badge, the letter badge, or both. Each links to this skill’s Suede listing; either valid linked badge can qualify for the feature offer. Markdown HTML |
| langchain-dependencies 77/100 · C | Dev tools | INVOKE THIS SKILL when setting up a new project or when asked about package versions, installation, or dependency management for LangChain… |
| langchain-fundamentals 67/100 · D | AI agents | Create LangChain agents with create_agent, define tools, and use middleware for human-in-the-loop and error handling. |
| langchain-middleware 77/100 · C | Dev tools | INVOKE THIS SKILL when you need human-in-the-loop approval, custom middleware, or structured output. Covers HumanInTheLoopMiddleware for human… |
| langchain-python-quickstart 71/100 · C | AI agents | 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… |
| langchain-rag 69/100 · D | AI agents | INVOKE THIS SKILL when building ANY retrieval-augmented generation (RAG) system. Covers document loaders, RecursiveCharacterTextSplitter, embeddings… |
| langchain-typescript-quickstart 71/100 · C | AI agents | Scaffold a minimal local LangChain agent in TypeScript by following the official quickstart. Use when the user wants to quickly build or try a… |
| langgraph-cli 69/100 · D | DevOps | INVOKE THIS SKILL when using the langgraph CLI to scaffold, develop, build, or deploy LangGraph applications. Covers langgraph new, dev, build, up… |
| langgraph-decision-models 72/100 · C | AI agents | INVOKE THIS SKILL when routing a LangGraph agent with a decision model (TypeSafe Jev, SemIf) instead of an LLM, or when auditing an existing agent… |
| langgraph-fundamentals 80/100 · B | Writing | INVOKE THIS SKILL when writing ANY LangGraph code. Covers StateGraph, state schemas, nodes, edges, Command, Send, invoke, streaming, and error…Get badges  Choose the numeric badge, the letter badge, or both. Each links to this skill’s Suede listing; either valid linked badge can qualify for the feature offer. Markdown HTML |
| langgraph-persistence 69/100 · D | Writing | INVOKE THIS SKILL when your LangGraph needs to persist state, remember conversations, travel through history, or configure subgraph checkpointer… |
| langgraph-python-quickstart 71/100 · C | AI agents | 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… |
| langgraph-typescript-quickstart 71/100 · C | AI agents | Scaffold a minimal local LangGraph agent in TypeScript by following the official quickstart. Use when the user wants to quickly build or try a… |
| managed-deep-agents 63/100 · D | AI agents | INVOKE THIS SKILL when building, testing, or deploying Managed Deep Agents in LangSmith. Walks a user through their first agent end to end —… |
| swarm 71/100 · C | Dev tools | Dispatches many independent items in parallel: create a table, fan out to subagents, aggregate results. One row = one unit of work. |
Where this repository is cited
langchain-ai/langchain-skills is listed as its publisher's official collection or from a listing request.