# langchain-ai/langchain-skills

Repository: https://github.com/langchain-ai/langchain-skills
Canonical: https://ross.abutalabs.com/products/langchain-skills
Language: TypeScript
License Family: other
Last push: 2026-08-29T01:39:54+00:00

## Health v2 (maintenance only)
Score: 63/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 100, release rhythm 42, longevity 15
- inputs: {"age_days": 223, "days_push": 5, "days_rel": 177, "gap_med": null, "n_releases_24m": 1}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1188, forks 90 (observed 2026-09-01T02:14:03.619063+00:00)

## What it is
A collection of agent skills for building agents with LangChain, LangGraph, and Deep Agents, installable into coding agents like Claude Code, Cursor, and Windsurf via the Agent Skills specification. It is in early development, so APIs and skill content may change.

## Use cases
- install langchain skills for claude code
- teach my coding agent how to use langgraph
- add langchain knowledge to cursor or windsurf
- set up eval engineering workflows with harbor
- build agents with deep agents cli
- find reusable skills for langchain agent development

## When to choose
- you use coding agents like Claude Code, Cursor, or Windsurf and want built-in LangChain/LangGraph expertise
- you want standardized, installable skill packages following the Agent Skills specification
- you need eval-engineering workflows for agent tasks with Harbor

## When to avoid
- you need a stable, production-ready library - the project is in early development with changing APIs
- you want LangSmith trace and dataset workflows - use langsmith-skills instead
- you don't use any coding agents that support the Agent Skills specification

## Facets
- artifact type: learning-resource
- maturity: experimental
- function: agent-framework, prompt-engineering, developer-tools, testing
- domain: large-language-models, developer-tools, tutorials
- platform: cli, cross-platform
- tags: agent-skills, claude-code, langchain, langgraph, deep-agents, coding-agents, eval-engineering, skills-spec, ai-agents, nodejs

## Member repositories
- langchain-ai/langchain-skills (main) score 63

## Provenance
- Observed fields: from GitHub, fetched 2026-09-01T02:14:03.619063+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:28:13.336592+00:00, confidence not recorded.
  - readme: https://github.com/langchain-ai/langchain-skills (fetched 2026-09-01T02:14:03.619063+00:00, sha 80101dfae143)
- Data as of 2026-08-30T08:39:29.467469+00:00.