sk Skill · usecompai
skill-evaluation
Evaluate whether a the reference deployment skill actually works — blind runner + separate judge against a bar, rubric scoring, pass-rate on re-runs, and defect diagnosis. Use when asked to evaluate a skill, eval skills, run a blind eval, score against a rubric, test a skill, audit skill quality, grade a skill, review the skill library, or before promoting a new skill to the company master prompt or the whole swarm.…
Open on skills.sh ↗read 2026-09-19
- installs 8w
- 0
- 30-day movement
- starts with the next reading
- Related entries
- 2
- Connections
- 0
Python
- Host repository
- usecompai/compound-operations-model
- Host stars
- 26
- Host language
- Python