Skip to content

jev-skills (laguagu)

Collection of agent skills and a curated directory of Jev projects, SDKs and examples for building with typed decisions.

Agent skillbetaMIT

This repository is mostly documentation or write-up rather than runnable code.

Overview

Jev Skills (laguagu) is a mostly-curation repository that collects agent skills, repositories and examples for TypeSafe Jev. It ships three of its own skills: jev-builder, which helps find a fitting cookbook, SDK, integration or example; jev-evidence-eval, which helps measure accuracy, review rate, latency and cost; and jev-curator, which checks original sources and keeps the collection current.

Beyond those, it links to the official typesafe-ai/skills package and a range of community skill collections, projects, SDKs, offline examples, open models and evaluations, noting licence status where relevant. It is aimed at developers getting started with Jev who want both an install path for agent skills and a map of the ecosystem. The decision model itself is not invoked by the repository; the skills guide an agent in designing and evaluating Jev decisions.

What the decision model decides

TypeQuestionAnswers
OtherWhich cookbook, SDK, integration or example fits what the user wants to build?(inferred)—

How it works

  1. Install the official typesafe-ai skill and jev-builder via the skills CLI
  2. Ask the agent to build; jev-builder finds a fitting pattern or example
  3. Use jev-evidence-eval to measure accuracy, review rate, latency and cost
  4. Use jev-curator to keep the linked directory current

Strengths

  • Single entry point to official and community Jev skills
  • Evaluation skill focuses on measurable accuracy, latency and cost
  • Notes licence status of linked collections

Caveats

  • Largely a directory; most linked projects are external
  • Contents depend on manual curation staying current

Getting started

bunx --bun skills add typesafe-ai/skills --skill typesafe-ai && bunx --bun skills add laguagu/jev-skills --skill jev-builder

At a glance

Type
Agent skill
Status
beta
Runtime
Agent skills
Has code
yes
License
MIT

Use cases and integrations

How curated lists describe it

Frequently asked questions

What skills does this repo include?

jev-builder, jev-evidence-eval and jev-curator, plus links to the official and community skill collections.

How do I install it?

Use `bunx --bun skills add laguagu/jev-skills --skill jev-builder` and choose your agent when prompted.

Does it call Jev itself?

The skills guide an agent in building and evaluating Jev decisions; your own code makes the API calls.

Related projects

  • Community directory of Jev apps, resources and runnable offline examples, with a guide skill and a searchable JevList web UI.

    Articleproduction
  • 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 serverbetaTypeScript
  • Independent agent skill that makes a coding agent design, build, test and tune a bounded Jev decision layer with a contract first.

    Agent skillbeta
  • Claude Code and Codex skills plus a study course for building with Jev, including Jevaluate, which rates how well projects use Jev.

    Projectbeta
  • Community Jev skill for Claude Code and Codex: a guide, a dependency-free Python CLI and 5 measured question sets.

    Agent skillbetaPython