skills-benchmarks is a test suite that measures how the design of skill documentation affects Claude Code's adherence to recommended coding patterns. It is used to compare documentation approaches across LangChain-related tasks and other agent workflows. Its catalogue entries represent skills, hooks, instructions, and a plugin used in the benchmark project.
Latest release v0.1.0 · 9 Mar 2026
1 file for Claude Code: skills-benchmarks CLAUDE.md — 1,324 tokens loaded in every session.
CLAUDE.md A 1,324 tok These files are langchain-ai/skills-benchmarks's own configuration — they tell Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.