Use TypeSafe Jev for typed judgments (Choice, Score, Noul) instead of asking a chat model to classify. Pair with a generative model for prose. Use when classifying, routing, scoring, guardrailing, or the user runs /jev.
cobusgreyling/Jev
Unofficial TypeSafe Jev showcase — System One decisions, not chat.
Repository statistics
Indexed skills
4
Skill groups
1
GitHub stars
139
Forks
30
Skills
4 totalAsk every independent TypeSafe Jev question in one POST /v1/systemone (speculative fan-out). Use for parallel questions, smart-home or compound commands, one-call turn assessment, or when the user runs /jev-fanout. Do not fire one HTTP call per question.
Screen LLM input and output with TypeSafe Jev Noul hazard batteries plus a harm Score; policy in code returns pass, review, or block. Use for jailbreak, prompt injection, secret leak, denylist pressure, or when the user runs /jev-guardrail or `npx jev guard`.
Route with TypeSafe Jev — map Choice plus confidence to act/confirm/human, or pick a coding-agent model tier. Use for confidence routing, model routing, cheap vs frontier, loop-jev, or when the user runs /jev-route or `npx jev route`.
Add to your README
The badge links readers to this page. It shows the skilld mark and no counts, and it follows the reader's light or dark GitHub theme.
<a href="https://skilld.dev/gh/cobusgreyling/jev">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://skilld.dev/b/cobusgreyling/jev?theme=dark">
<source media="(prefers-color-scheme: light)" srcset="https://skilld.dev/b/cobusgreyling/jev?theme=light">
<img alt="Skill repository on skilld.dev" src="https://skilld.dev/b/cobusgreyling/jev?theme=light">
</picture>
</a>