Back to Projects

Published · 2026-07-04 · Public / Open Source

Skill Up

Open-source CLI framework for evaluating AI Agent Skills with reusable cases, layered assertions, and CI-friendly workflows.

#AI Engineering#Evaluation#CLI#Open Source

Problem

AI Agent Skills are often iterated by trying them manually. A model change, an agent change, or a prompt edit can shift behavior, but teams rarely have a stable way to evaluate, compare, and regress those changes.

Skill Up addresses that gap: it makes Skills testable as engineering artifacts.

Role

Creator / Maintainer.

System

  • Multi-engine support for environments such as Claude Code, Codex, and Qodercli.
  • Reusable evaluation cases that can be replayed across agents.
  • Layered assertions through expect + judge checks.
  • CI-friendly workflows for automated regression.
  • Compatibility with Anthropic skill-creator format.

Why It Matters

AI engineering is not only about connecting a model to an application. It is about building workflows that can continuously judge quality. Skill Up is my public infrastructure experiment for Agent Skill evaluation.

Link

GitHub: alibaba/skill-up