What it is
An installable agent skills package for developers building with TypeSafe's System One API, which provides typed decisions and probabilities. It teaches agents the Jev workflow for designing TypeSafe workflows and composing typed judgments in code.
How it uses Jev
The README does not specify which decisions Jev makes, what state it operates on, or how results are used in code. It only states that the skill teaches the Jev workflow and that System One models provide typed decisions and probabilities.
Try it
npx skills add typesafe-ai/skills --skill typesafe-ai
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-centricyes0.70
- Shows a System One patternno0.14
- Handles uncertaintyno0.06
- Measuredno0.03
- Runnableyes0.98
- Worth recommendingno0.31
- Model replicano0.04
- Problem scopescore on a 0–2 scale1.00
- About Jevyes0.94
Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 20 Sept 2026.