About Langchain Skills
Langchain Skills is an MCP server published by christian-bromann in the AI category: mCP server: Langchain Skills.
The repository has 3 stars and 1 forks, with the last commit 8 months ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues before depending on it in production.
Install
git clone https://github.com/christian-bromann/langchain-skillsThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Ask AI
Ask AI about Langchain Skills
Powered by Claude · Grounded in docs
Security checks
Static checks derived from the repository 5 days ago. Heuristics on the source, not an audit.
- ✓README presentThe repository ships documentation.
- !License declaredNo license file. Legally you have no right to use it in a product.
- ✓Tests presentA test suite exists in the repository.
- ✓Dependencies pinnedA lockfile pins dependency versions.
- ✓No dynamic code executionSource scan found no eval, dynamic Function, or shell execution.
- !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.
README
@langchain/skills
A deepagents-powered agent that scrapes LangChain documentation and generates skill.md files following the Agent Skills protocol.
Overview
This agent automatically explores the LangChain documentation and creates comprehensive skill files that help AI agents use LangChain effectively. Each skill file includes:
- Decision tables for choosing the right components
- Code examples with essential patterns
- Boundaries defining what can/cannot be configured
- Gotchas highlighting common mistakes
- Links to full documentation
Installation
bun install
Environment Variables
You'll need to set up your API keys:
export ANTHROPIC_API_KEY=your-anthropic-api-key
Usage
Generate All Skills
Run the agent to automatically explore LangChain docs and generate skill files:
bun run start
Or:
bun run src/agent.ts
Output
Skill files are generated in the ./skills/ directory with the structure:
skills/
├── langchain-chat-models/
│ └── SKILL.md
├── langchain-prompts/
│ └── SKILL.md
├── langchain-chains/
│ └── SKILL.md
├── langchain-agents/
│ └── SKILL.md
├── langchain-memory/
│ └── SKILL.md
├── langchain-rag/
│ └── SKILL.md
├── langchain-document-loaders/
│ └── SKILL.md
├── langchain-vector-stores/
│ └── SKILL.md
├── langchain-output-parsers/
│ └── SKILL.md
└── langchain-callbacks/
└── SKILL.md
Skill File Format
Each skill file follows the Agent Skills protocol:
---
name: skill-name
description: Brief description of the skill
---
# Skill Title
## Overview
Brief summary of the topic.
## Decision Table
| Need | Use |
| --- | --- |
| Simple Q&A | ChatOpenAI |
| Complex reasoning | Claude |
## Code Examples
Essential usage patterns.
## Boundaries
### Can Configure
- List of configurable items
### Requires External Setup
- List of items needing external setup
## Gotchas
- Common mistakes to avoid
## Links
- [Full Documentation](https://docs.langchain.com/...)
How It Works
- MCP Integration: Uses the LangChain docs MCP server to search documentation
- Deep Agent: Powered by deepagents with filesystem middleware
- Systematic Exploration: Explores all major LangChain topics
- Skill Generation: Creates structured skill files following the protocol
Development
This project uses:
- Bun - JavaScript runtime
- deepagents - Agentic AI framework
- @modelcontextprotocol/sdk - MCP client
README fetched from the repository 5 days ago. The original is authoritative.