langchain-architecture

Design LLM applications using LangChain 1.x and LangGraph for agents, memory, and tool integration. Use when building LangChain applications, implementing AI agents, or creating complex LLM workflows.

1.66x

Quality

66%

Does it follow best practices?

Impact

83%

1.66x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./tests/ext_conformance/artifacts/agents-wshobson/llm-application-dev/skills/langchain-architecture/SKILL.md

Evaluation results

70%

60%

Customer Support Chatbot with Persistent Memory

ReAct agent with persistent memory

Criteria

Without context

With context

Uses create_react_agent

100%

MemorySaver checkpointer

100%

Thread ID config

100%

StructuredTool with Pydantic schema

Async ainvoke

100%

Claude Sonnet 4.5 model

100%

langchain-anthropic import

100%

Tool error handling

TypedDict or MessagesState

No deprecated initialize_agent

100%

88%

43%

Internal Knowledge Base Search System

RAG pipeline with StateGraph and embeddings

Criteria

Without context

With context

StateGraph usage

100%

TypedDict state class

100%

START and END nodes

50%

100%

VoyageAI embeddings

100%

voyage-3-large model

100%

Pinecone vector store

100%

Retriever k=4

Async node functions

100%

asyncio.gather batch processing

100%

LangSmith tracing setup

62%

50%

graph.compile()

100%

92%

-4%

Automated Research and Writing Pipeline

Multi-agent orchestration with streaming

Criteria

Without context

With context

Supervisor node

100%

Agents return to supervisor

100%

Conditional routing

100%

MultiAgentState TypedDict

100%

astream_events v2

100%

on_tool_start event handling

100%

BaseCallbackHandler subclass

100%

PostgresSaver checkpointer

60%

100%

create_react_agent for sub-agents

100%

No initialize_agent

100%

Async throughout

100%

Repository: Dicklesworthstone/pi_agent_rust
Commit: 47823e3

Evaluated: 29 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Customer Support Chatbot with Persistent Memory Internal Knowledge Base Search System Automated Research and Writing Pipeline

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.