by huggingface · Codex Skill · ★ 516
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
UPskill Generate and evaluate agent skills based on traces with agents. Create skills with teacher models (expensive/slow) that student models (cheap/fast) can use to perform harder tasks reliably. [!TIP] UPskill v2 - recommended default config file now runs evaluations on Hugging Face Jobs. Make sure to set your and use for job creation and result capture Quick Start Install upskill: Create a new skill Generate a skill with a teaching model and evaluate it on a student model. Benchmark a set of models against a skill. View the results later. Development checks This repo uses a CI flow inspired by with separate format, lint, typecheck, and test stages. Install dev dependencies: Run t
| Stars | 516 |
| Forks | 64 |
| Language | Python |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 53.544/100 |
| Open Issues | 8 |
| Last Updated | 2026-05-04 |
| Created | 2026-01-21 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~33k |
Explore other popular codex skill tools:
upskill is Generate and evaluate agent skills for code agents like Claude Code, Open Code, OpenAI Codex. It is categorized as a Codex Skill with 516 GitHub stars.
upskill is primarily written in Python.
You can find installation instructions and usage details in the upskill GitHub repository at github.com/huggingface/upskill. The project has 516 stars and 64 forks, indicating an active community.
upskill is released under the Apache-2.0 license, making it free to use and modify according to the license terms.