🎯

langsmith-evaluator

🎯Skill

from langchain-ai/skills-benchmarks

What it does

A benchmark framework by LangChain that measures how skill documentation design affects Claude Code's adherence to recommended patterns. Runs tasks with configurable treatments in Docker sandboxes and supports evaluation via LangSmith.

📦

Same repository

langchain-ai/skills-benchmarks(21 items)

langsmith-evaluator

Installation

Vibe Index InstallInstalls to .claude/skills/

npx vibeindex add langchain-ai/skills-benchmarks --skill langsmith-evaluator

skills.sh Install⚠ Installs to .agents/skills/

npx skills add langchain-ai/skills-benchmarks --skill langsmith-evaluator

Manual InstallCopy SKILL.md content and save to the path below

~/.claude/skills/langsmith-evaluator/SKILL.md

SKILL.md

46Installs

AddedApr 13, 2026

View on GitHub Back to Skills

More from this repository10

🎯

react-components🎯Skill

A benchmarking framework from LangChain that measures how skill documentation design affects Claude Code's adherence to recommended patterns, using Docker-sandboxed tasks with treatment-based test variations.

🎯

langchain-oss-primer🎯Skill

A benchmark suite by LangChain that measures how skill documentation design affects Claude Code's adherence to recommended patterns, using Docker-sandboxed tasks with configurable treatments and repetitions.

🎯

langchain-dependencies🎯Skill

A benchmarking framework that measures how skill documentation design affects Claude Code's adherence to recommended patterns. It supports multiple treatments, repetitions, and parallel test execution with Docker-sandboxed validation.

🎯

database-migrations🎯Skill

A benchmarking framework that measures how skill documentation design affects Claude Code's adherence to recommended patterns, using Docker-sandboxed tasks with configurable treatments and validation scripts.

🎯

langgraph-persistence🎯Skill

Part of LangChain's skill benchmarks project that measures how skill documentation design affects Claude Code's adherence to recommended patterns, using Docker-sandboxed test tasks with configurable treatments.

🎯

framework-selection🎯Skill

🎯

langsmith-trace🎯Skill

A benchmarking framework that measures how skill documentation design affects Claude Code's adherence to recommended patterns. Supports multiple treatments, repetitions, and parallel test execution in Docker-sandboxed environments.

🎯

api-docs🎯Skill

A benchmark skill from LangChain that measures how skill documentation design affects Claude Code's adherence to recommended patterns, with support for multiple treatments and configurable model selection.

🎯

testing-patterns🎯Skill

A benchmarking framework from LangChain that measures how skill documentation design affects Claude Code adherence to recommended patterns, using configurable treatments, Docker-sandboxed execution, and automated validation.

🎯

deep-agents-core🎯Skill

A benchmarking framework that measures how skill documentation design affects Claude Code's adherence to recommended patterns. It runs tasks in Docker-sandboxed environments with configurable treatments and repetitions to evaluate skill effectiveness.