Building with TypeSafe Jev
Unofficial skill teaching coding agents to design for Jev, with code sketches per pattern, links to 150+ projects and an eval harness.
Overview
Building with TypeSafe Jev is an unofficial community skill that teaches coding agents to stop treating Jev like a chat model and design for it: typed questions, calibrated confidence and composition in code. It links more than 150 community projects sorted by how they work, with a code sketch for each pattern, and explains how it differs from TypeSafe's official skill.
It installs in Claude Code, Codex, Antigravity CLI, Muse and Muse Code, with marketplace instructions for each host, and its README is translated into seven languages. Per the list summaries, it includes an eval harness that runs the same task with and without the skill and keeps every run's output in the repository.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Other | Which Jev pattern and question types fit the project being built?(inferred) | — |
How it works
- Install from the Claude Code or Codex marketplace
- Skill loads when working on Jev code
- Agent picks a pattern and code sketch
- Eval harness compares runs with and without the skill
Strengths
- Pattern sketches grounded in real projects
- Eval harness with stored outputs
- Many languages and hosts
Caveats
- Unofficial
- Guidance only; results depend on the agent
Getting started
claude plugin marketplace add aaddrick/building-with-typesafe-jev && claude plugin install building-with-typesafe-jev@building-with-typesafe-jevAt a glance
- Type
- Plugin
- Status
- production
- Runtime
- agent skill / plugin
- Has code
- yes
- Has tests
- yes
- License
- MIT
Use cases and integrations
How curated lists describe it
Agent skill: a plugin published to both the Claude Code and Codex marketplaces that teaches a coding agent to reach for typed Jev decisions, with a setup walkthrough for each host.
yibie/awesome-jevUnofficial skill that teaches coding agents to build with TypeSafe AI's Jev: typed decisions, calibrated confidence, and prior art from 150+ community projects.
logicrw/awesome-jev-projectsUnofficial skill that teaches coding agents to build with TypeSafe AI.
wh000wh000/awesome-jev-liveUnofficial skill that teaches coding agents to build with TypeSafe AI's Jev: typed decisions, calibrated confidence, and prior art from 150+ community projects.
hellogumbo/awesome-jevAgent skill with a code sketch per project shape, and an eval harness that runs the same task with and without the skill and keeps every run's output in the repository.
MrJev/awesome-jev
Frequently asked questions
Is it official?
No, TypeSafe's own skill is at typesafe-ai/skills.
Which hosts?
Claude Code, Codex, Antigravity CLI, Muse and Muse Code.
Is its effect measured?
An eval harness runs tasks with and without the skill, per the listing.
Related projects
- Building with Jev★ 155
Agent skill for writing and improving programs that call Jev: question design, state structure, thresholds and diagnosing wrong answers.
Agent skillproduction Portable Agent Skill teaching coding agents to use Jev as a bounded judgment layer, plus an optional MCP bridge.
MCP serverbetaTypeScriptIndependent agent skill that makes a coding agent design, build, test and tune a bounded Jev decision layer with a contract first.
Agent skillbetaClaude Code and Codex skills plus a study course for building with Jev, including Jevaluate, which rates how well projects use Jev.
ProjectbetaCommunity Jev skill for Claude Code and Codex: a guide, a dependency-free Python CLI and 5 measured question sets.
Agent skillbetaPythonAgent skill and CLI that chains Jev question design: find decision calls, check fit, draft, lint, calibrate thresholds and plan a cascade.
Agent skillprototypePython