Setting the issue. One moment.
Contents
Issue No. 20LangChain · Official
langchain-ai /langchain-skills
22 skills published from this repository. No description was given upstream, so this issue takes its voice from the chapters themselves.
22 chapters · 1 hour 9 minutes · 14,966 words
Install and provenance
npx skills add langchain-ai/langchain-skills/plugin marketplace add langchain-ai/langchain-skills- Owner
- langchain-ai · Organization
- Licence
- All rights reserved — view on GitHub
- Last updated
- Published from
- github.com/
langchain-ai/ langchain-skills
Typeset in this issue’s own colours, resolved from a curated brand profile.
Front matter
From the README⚠️ — 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 (opens in a new tab).
Supported Coding Agents
These skills can be installed via npx skills (opens in a new tab) for any agent that supports the Agent Skills specification (opens in a new tab), including Claude Code, Cursor, Windsurf, and more.
Installation
Quick Install
Using npx skills (opens in a new tab):
Local (current project):
npx skills add langchain-ai/langchain-skills --skill '*' --yesGlobal (all projects):
npx skills add langchain-ai/langchain-skills --skill '*' --yes --globalTo link skills to a specific agent (e.g. Claude Code):
npx skills add langchain-ai/langchain-skills --agent claude-code --skill '*' --yes --globalClaude Code Plugin
Install directly as a Claude Code plugin (opens in a new tab):
/plugin marketplace add langchain-ai/langchain-skills
/plugin install langchain-skills@langchain-skillsInstall Script (Claude Code & Deep Agents CLI only)
Alternatively, clone the repo and use the install script:
# 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:
export OPENAI_API_KEY=<your-key> # For OpenAI models
export ANTHROPIC_API_KEY=<your-key> # For Anthropic modelsThen 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:
npx skills add langchain-ai/langchain-skills --skill eval-engineering --yesOr ask Codex: “Install the eval-engineering skill from langchain-ai/langchain-skills.”
Eval tasks require Harbor (opens in a new tab). Run Harbor locally with Docker or use a supported cloud environment.
Then ask your coding agent:
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 (opens in a new tab) / JS (opens in a new tab) (weather)
- langgraph-python-quickstart / langgraph-typescript-quickstart → Python (opens in a new tab) / JS (opens in a new tab) (math)
- deepagents-python-quickstart / deepagents-typescript-quickstart → Python (opens in a new tab) / JS (opens in a new tab) (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
useStreamUIs
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
Colophon
How this issue was made- Source
- github.com/langchain-ai/langchain-skills, branch
main, last pushed 7 August 2026. - Licence
- All rights reserved — view on GitHub — with no detectable licence, this issue links rather than republishes: the chapters are omitted from the agent manifest and from the whole-book markdown.
- Discovery
- 22 chapters found by walking the repository tree for
SKILL.md, not by matching a directory convention. One layout observed:config/skills/*/SKILL.md. - Issue colours
- Resolved from a curated brand profile — hue 224°, chroma 0.190. Two accent tones are generated per issue and each is proven against its own ground before it ships: a single accent that passes AA on both light and dark paper is arithmetically impossible.
- Heading repairs
- 1 repair applied to the front matter so the document has one
h1and no skipped levels:- Removed “LangChain Skills”, a leading h1 that duplicated the chapter title.
- Spec compliance
- Every chapter satisfies the Agent Skills specification’s frontmatter rules.
- Images
- Images inside a chapter come from the upstream repository. Where the author gave no alternative text we mark the image decorative rather than inventing a description — a plausible caption we made up is worse than none for the reader who depends on it.
- Marketplace
- A plugin manifest is published at
.claude-plugin/marketplace.jsonby LangChain, declaring 1 plugin. It is read for editorial metadata only — never as the skill index, which is always the repository tree. - Signal
- Install counts come from skills.sh. They measure downloads, not quality, and an unranked repository is not an unread one.
- Agent surfaces
- The whole issue is available as one markdown document at
/langchain-ai/langchain-skills.md, and each chapter at its own.mdURL. - Publication
- Set by Skills Docs from the source repository. Body text is Literata at the reader’s chosen size and measure; code is Geist Mono. Nothing on this page was written by us except this paragraph.