Analytics & Monitoring Agent Skills for Zed

Build LangChain chains and prompts for structured LLM workflows.

Optimize LangChain API costs and token usage.

Load and chunk documents for LangChain 1.0 RAG pipelines correctly \u2014\

Implement LangChain RAG pipelines with document loaders, text splitters, embeddings, and vector stores (Chroma, Pinecone, FAISS).

Collect LangChain debug evidence for troubleshooting and support.

Produce a reproducible, sanitized diagnostic bundle for a LangChain\

Build a LangGraph 1.0 Deep Agent \u2014 planner + subagents + virtual\

Build and query vector stores with LangChain 1.0 without getting burned

Create a minimal working LangChain example.

Triage LangChain 1.0 / LangGraph 1.0 production incidents \u2014 LLM-specific\

Install and configure LangChain SDK with provider authentication.

Set up comprehensive observability for LangChain applications

Wire LangSmith tracing and custom metric callbacks into a LangChain\

Tune LangChain 1.0 / LangGraph 1.0 Python chains and agents for throughput,\n\

Manage LangChain 1.0 prompts like code \u2014 LangSmith prompt hub versioning,\n\

Implement LangChain reference architecture for production systems: layered design, provider abstraction, chain registry, RAG pipelines…

Compose LangChain 1.0 Python runnables with the production defaults

Plan and execute LangChain SDK upgrades and migrations.

Dispatch LangChain 1.0 chain/agent events to external systems \u2014\

Expert in Langfuse - the open-source LLM observability platform.

Execute Langfuse primary workflow: Tracing LLM calls and spans.