Project overview
UPskill is a command-line toolkit for creating standard Agent Skills from task descriptions, examples, existing skills, or recorded agent traces. It can generate tests, compare baseline and skill-assisted performance, refine weak skills from failures, and benchmark multiple models across repeated runs. Evaluations can run locally or through Hugging Face Jobs, making it useful for teams that want measurable evidence before distributing a skill.
Repository facts
- Primary language
- Python
- License
- Apache-2.0
- Repository updated
- Jul 13, 2026
- Default branch
- main
Resource types
CLI app
Use cases
Software development
Platforms
Claude CodeCodex
Runtime
Command lineLocal
Capabilities
Verification and evals
Audience
Developers