sk Skill · mims-harvard
devtu-benchmark-harness
Continuous improvement system for ToolUniverse tools, skills, and plugin. Run benchmarks, diagnose failures, route fixes to devtu skills, retest. Use after skill optimization, tool additions, or as regression check.
Open on skills.sh ↗read 2026-09-19
- installs 8w
- 0
- 30-day movement
- starts with the next reading
- Related entries
- 1
- Connections
- 0
bashPython
- Host repository
- mims-harvard/ToolUniverse
- Host stars
- 1,693
- Host language
- Python