What it is
An agent skill that helps developers write and improve programs calling Jev, TypeSafe's System One model. It covers question design, state structure, answer composition, confidence thresholds, and debugging. Targets jev-1.13.
How it uses Jev
The README does not describe specific decisions Jev makes, the state passed to it, or how results are used in code. It only states the skill covers question design (Choice, Score, Noul), state structure, answer composition, confidence thresholds, and diagnosing questions that answer wrong or with low confidence.
Primitives:choicescorenoul
Try it
Install via Claude Code plugin, `npx skills add dbreunig/building-with-jev-skill`, or manual copy; invoke with `/jev`.
Evidence
Each line is one question put to Jev about the README. ≥ 0.60 reads as yes, ≤ 0.40 as no; in between Jev is not making a call.
- Jev-centricyes0.88
- Shows a System One patternyes0.90
- Handles uncertaintyno0.19
- Measuredno0.05
- Runnableyes0.96
- Worth recommendingyes0.61
- Model replicano0.03
- Problem scopescore on a 0–2 scale1.00
- About Jevyes0.98
Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 20 Sept 2026.