Langsmith

If you're already using LangSmith for tracing or evals and need help instrumenting something specific, this skill routes you to the right workflow packet before you touch SDK code. It picks one focus area (trace debugging, offline evals, annotation queues, prompt registry, cross-service propagation, or audit) instead of dumping the entire LangSmith API surface on you. Works best when you know LangSmith is the tool but aren't sure whether you need better trace coverage, a pre-ship eval gate, human review queues, or multi-service lineage. The routing discipline keeps you from turning every LangSmith question into a sprawling observability project. Python and TypeScript projects with LANGSMITH_API_KEY already configured get the most mileage.

skills.sh installs: 164
GitHub stars: 22
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add akillness/oh-my-skills --skill langsmith --agent claude-code

Installs into .claude/skills of the current project.

Files

LangSmith

When to use this skill

The user already chose LangSmith and needs the smallest useful packet for tracing, evals, review, prompt ownership, or trace propagation.
A request mentions LangChain tracing, @traceable / traceable, wrap_openai / wrapOpenAI, annotation queues, run trees, trace IDs, datasets, or experiment comparison.
The team needs to decide whether a change needs debugging traces, an offline eval gate, an online review queue, Prompt Hub / prompt-registry work, or multi-service lineage.
The user has some LangSmith setup already, but confidence is still low and they need an audit / gap review.