Skill UI

A comprehensive, multi-phase workflow designed for building sophisticated AI systems. This guide covers everything from designing autonomous agents and implementing single-agent logic, to orchestrating complex multi-agent systems and integrating advanced tools and memory mechanisms. Ideal for developers building production-grade AI applications using frameworks like CrewAI and LangGraph.

A comprehensive, multi-phase workflow designed for building sophisticated AI systems. This guide covers everything from designing autonomous agents and implementing single-agent logic, to orchestrating complex multi-agent systems and integrating advanced tools and memory mechanisms. Ideal for developers building production-grade AI applications using frameworks like CrewAI and LangGraph.

Framework for building stateful, multi-actor AI applications with LangGraph, covering graph construction, reducers, persistence, human-in-the-loop patterns, and ReAct agents suitable for Python production systems.

Fetch execution traces from LangSmith Studio to inspect LangChain/LangGraph agent runs, analyze errors, tool calls, memory usage, and performance, and export sessions for deeper diagnostics using the langsmith-fetch CLI.

An expert guide and framework for building production-grade, sophisticated AI agent systems. This skill specializes in utilizing the latest LangChain 0.1+ and LangGraph APIs to implement multi-agent orchestration, advanced Retrieval-Augmented Generation (RAG) pipelines (e.g., RAG Fusion, HyDE), and complex state management. It covers comprehensive topics from architectural design (Plan-and-Execute, ReAct Agents) to production deployment (FastAPI streaming, LangSmith observability, caching, and robust error handling).

A robust framework for building complex, long-horizon AI agents using LangGraph. It addresses common pitfalls in advanced agent design, such as unbounded state growth (Virtual FS cleanup) and subagent persona leakage (explicit message overriding). Ideal for tasks requiring multi-step planning, task delegation, and self-correction through reflection loops.

This harness provides comprehensive, reproducible evaluation pipelines for complex LLM chains and agents (LangChain/LangGraph 1.0). It integrates golden dataset management, LangSmith evaluation, RAGAS metrics, deepeval LLM-as-judge, and structured agent trajectory analysis. Use it when establishing quality benchmarks for new chains, diagnosing performance regressions after model switches, or implementing CI/CD gates to prevent quality drops.

This guide teaches how to build robust, production-grade ReAct agents using LangGraph 1.0's `create_react_agent`. It specifically addresses common agent failure modes, such as preventing infinite loops (recursion caps) and ensuring proper error propagation. Learn to define typed tools using Pydantic, manage state with checkpointers, and set precise recursion limits. Perfect for users migrating from legacy AgentExecutor or building reliable, multi-step tool-calling workflows.

This skill provides a comprehensive guide to building robust LangGraph 1.0 StateGraphs in Python. It covers defining typed TypedDict states with reducers, writing deterministic nodes, and defensively wiring conditional edges. It addresses common pitfalls such as silent graph termination, incorrect state updates using reducers, proper management of recursion limits, and handling evolving checkpoint schemas for reliable LLM workflow orchestration.

A comprehensive guide to ensuring robust state management for LangGraph agents. This skill addresses common checkpointing pitfalls (like missing thread_id or non-JSON serializable state) and details best practices for implementing reliable state persistence using MemorySaver or PostgresSaver. It covers thread discipline, schema migration, and time-travel debugging for production-ready applications.

Implement robust human-in-the-loop (HITL) approval gates for sophisticated LangGraph workflows. This skill enables the graph to pause execution before critical, irreversible actions (like sending emails or calling tools). It manages complex state serialization, provides clear resume semantics using `Command(resume=...)`, and integrates with external UIs (e.g., Slack) to await human decision, ensuring safe and controlled workflow execution.

This guide addresses critical LangGraph streaming pitfalls, including state overdraw, proxy buffering issues (Nginx, Cloud Run), and excessive event noise. It provides a production-grade pattern for implementing robust SSE/WebSocket endpoints using FastAPI. Learn how to correctly select the `stream_mode` (messages, updates, values) and implement server-side event filtering to reliably build live-token chat UIs and perform comprehensive state visualization.