JevHunt

TypeSafe Agent Skills: guidance for building with Jev

typesafe-ai/skills

Resource / directoryOfficial

TypeSafe Agent Skills gives coding agents guidance for designing typed-decision workflows with Jev and System One models.

Open GitHub ↗ Read evidence ↗ Alternatives Report a problem

MIT · updated 2026-09-12 · 2,434 ★ · Evidence checked Sep 30, 2026

What you can build with it

Search & discovery

Purpose and audience

This official resource helps agents design TypeSafe workflows, find documentation and compose typed judgments in code.

Evidence 1 ↗ · Evidence 2 ↗

How Jev fits

The skill describes Jev as a System One model returning typed answers and probabilities for application-controlled workflows.

Evidence 1 ↗

Using the project

Install the Claude Code plugin or the skills.sh package, then request a workflow such as support-ticket routing with uncertain cases reviewed.

Evidence 1 ↗ · Evidence 2 ↗

Scope and limits

Installation through skills.sh is project-local by default. The skill supplies guidance; live TypeSafe documentation carries current API contracts, model limits and examples.

Evidence 1 ↗ · Evidence 2 ↗

Evidence checked:

Repository description

Agent skills for building with TypeSafe's System One API

Project facts

Relationship to Jev
Resource / directory
Evidence
Official
Language
Not reported
License
MIT
Origin
Original repository
Repository status
Not archived
Created
2026-08-24
Last code update
2026-09-12
GitHub stars
2,434
Evidence checked
Sep 30, 2026
Metadata checked
Sep 30, 2026
Check status
Up to date

Stars measure the whole repository, including work unrelated to Jev.

Evidence and scope

Official records the linked documentation or source. JevHunt has not independently run or benchmarked this project.

Evidence commit: 65a39f393687675ce170e6094757de20370365b9

Discovered through: awesome-jev, typesafe-official.

How we review →

Suggest a correction · Claim this listing · Submit a project