What it is
An agent skill that helps an agent recognize work suitable for Jev, design typed questions, and learn from recent community usage. It is for developers and agents building products that involve repeated semantic judgments.
How it uses Jev
Jevify teaches the agent to delegate bulk semantic judgments to Jev, such as selecting passages, ranking candidates, checking items, or choosing a handler. The agent sends decisions to Jev, brings selected evidence into context, and continues reasoning. It uses Choice, Noul, and Score primitives with shared-state batching.
Primitives:choicenoulscore
Technique worth stealing
Delegate first-pass semantic judgments to Jev, then read selected evidence before final reasoning.
Try it
npx skills add altryne/jevify --skill jevify
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-centricyes0.89
- Shows a System One patternunclear0.47
- Handles uncertaintyno0.05
- Measuredno0.05
- Runnableunclear0.60
- Worth recommendingunclear0.50
- Model replicano0.04
- Problem scopescore on a 0–2 scale1.16
- About Jevyes0.97
Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 21 Sept 2026.