upskill
Generate, evaluate, and refine Agent Skills from tasks or agent traces.
- Stars
- 711
- Forks
- 89
- Updated
- Updated Jul 13, 2026
Generate, evaluate, and refine Agent Skills from tasks or agent traces.
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.
Resource types
Use cases
Platforms
Handle coding tasks through natural language in the terminal, IDE, or GitHub.
Use Gemini from the terminal to inspect code, make changes, and automate development tasks.
Runtime
Capabilities
Audience
Public GitHub facts last synced Jul 14, 2026.
Manage multiple coding agents in parallel from one terminal dashboard.
Let AI agents control browsers through sandboxed JavaScript.