deepagents-skills

Agent Skills for LangChain, LangGraph, LangSmith & Deep Agents

A comprehensive collection of agent-optimized skills for AI coding assistants working in the LangChain ecosystem. These skills cover the complete development lifecycle from project setup to production deployment, monitoring, debugging, and Deep Agents setup/configuration.

Each skill is a self-contained package with a SKILL.md entry point plus optional scripts, references, and templates.

Available Skills

Skill	Description
langgraph-project-setup	Initialize and configure LangGraph projects (structure, langgraph.json, env vars, dependencies).
langgraph-agent-patterns	Multi-agent coordination patterns: supervisor, router, orchestrator-worker, handoffs.
langgraph-state-management	State schemas, reducers, persistence, checkpoint inspection, and migration workflows.
langgraph-error-handling	Retry strategies, LLM-based recovery loops, and human-in-the-loop escalation patterns.
langgraph-testing-evaluation	Test and evaluate LangGraph agents with unit/integration patterns, trajectory evaluation, LangSmith dataset evals, and A/B comparisons.
langsmith-trace-analyzer	Fetch, organize, and analyze LangSmith traces for debugging and performance optimization.
langsmith-deployment	Deploy, monitor, and manage LangGraph applications in production (Cloud, Hybrid, Standalone).
deepagents-setup-configuration	Initialize, configure, and validate Deep Agents projects (Python/JavaScript), including middleware, backends, subagents, persistence, and migration guidance.
deepagents-planning-todos	Master the write_todos tool for task planning and decomposition in Deep Agents, with patterns for research, coding, analysis tasks, and trace visualization.
skill-creator	Guidance for creating and maintaining skills in this repo.

Coverage

9 production-ready skills covering the complete LangChain/LangGraph/Deep Agents development lifecycle:

• 🚀 Project Setup - Initialize projects with proper structure and configuration
• 🤝 Multi-Agent Patterns - Supervisor, router, orchestrator, and handoff patterns
• 💾 State Management - Schemas, reducers, persistence, and checkpointing
• 🛡️ Error Handling - Retry policies, LLM recovery, and human-in-the-loop
• ✅ Testing & Evaluation - Unit/integration tests, trajectory evaluation, LangSmith evaluation, A/B testing
• 🔍 Trace Analysis - Debug with LangSmith traces and pattern detection
• 🌐 Production Deployment - Cloud, Hybrid, and Standalone deployment with monitoring
• 🧠 Deep Agents Setup - Initialize and configure Deep Agents with validated project scaffolding and compatibility guidance
• 📝 Deep Agents Planning - Master write_todos for effective task decomposition with patterns, best practices, and trace visualization

Plus the skill-creator meta-skill for extending this collection.

Quick Start

Optional (recommended for contributors): create and sync a local environment.

uv venv --python=3.12
uv sync

1. Pick a skill folder in skills/ and open its SKILL.md.
2. Use it directly in your assistant by pasting relevant sections or pointing the assistant to the file path.
3. For development tasks (creating, validating, packaging skills), follow the commands in AGENTS.md.

Example: initialize a new skill using the repo tooling.

uv run skills/skill-creator/scripts/init_skill.py <skill-name> --path skills/

Install as Claude Code Plugin

1. Add the marketplace:

/plugin marketplace add Lubu-Labs/langchain-agent-skills

2. Install a skill:

/plugin install langsmith-deployment@lubu-labs-langchain-agent-skills

Or any other skill (e.g., langgraph-project-setup, langgraph-agent-patterns) Or use the interactive menu:

/plugin menu

For local development:

claude --plugin-dir ./path/to/langchain-agent-skills

Once installed, Claude Code will automatically use these skills when relevant.

Use in Other Repositories

These skills can be shared by copying a skill folder (for example skills/langgraph-agent-patterns/) into another repository or a supported assistant skills directory.

OpenAI Codex CLI

Install via the Codex skill installer (replace with your repo path):

$skill-installer install langgraph-agent-patterns from Lubu-Labs/langchain-agent-skills

Or clone and copy manually:

git clone https://github.com/Lubu-Labs/langchain-agent-skills.git
cp -r langchain-agent-skills/skills/* ~/.codex/skills/

Restart Codex to pick up new skills.