alibaba/skill-up

An evaluation and evolution tool for Agent Skills.

About the project

skill-up is a tool for evaluating and improving Agent Skills through declarative test cases, multiple agent engines, configurable judges, and structured reports. Developers and agent builders use it locally or in continuous integration to measure skill quality and iterate on failures. The catalogue entries are skills and instructions that can be evaluated or evolved with it.

Latest release v0.10.0 · 1 Sept 2026

These files are alibaba/skill-up's own configuration. They tell Codex, OpenCode and 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.

851Stars on the repository
2Files it configures its agents with
2,416Tokens loaded in every session
3Agents configured

Instructions