Skillsbench
Fresh
skillsbench — evaluating how well AI agents use skills (86-task default grid + 14 opt-in extras).
- Type
- RL Env
- Runtime
multi-turn- License
- unknown
- Size
- v0.1.6
- Published
- Jun 2026
Cite
Notes
Only stored in your browser.
skillsbench — evaluating how well AI agents use skills (86-task default grid + 14 opt-in extras).
multi-turnCite
Notes
Only stored in your browser.