---
title: "jev-skills"
description: "Practical Jev skills, decision examples, and a small guide to useful integrations."
canonical: https://agentpluginsdirectory.com/plugins/jev-skills
last-updated: 2026-09-21
---

# jev-skills
Practical Jev skills, decision examples, and a small guide to useful integrations.
- Slug: jev-skills
- Publisher: laguagu
- Repository: https://github.com/laguagu/jev-skills
- Manifest: plugin.json
- Version: 1.4.0
- License: MIT
- Category (editorial): other
- Skills: 2 (jev-builder, jev-evidence-eval)
- MCP servers: 0
- Stars: 1
- Repository created: 2026-09-20
- Repository last pushed: 2026-09-20
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/jev-skills
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What jev-skills does, in the publisher's words

Practical skills for coding agents building with Jev. Set up the API, choose a decision pattern, and add routing, ranking, or evidence checks to your app.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/laguagu/jev-skills/HEAD/README.md

## Skills

- jev-builder: Helps build applications with TypeSafe Jev by choosing decision patterns, wording and debugging typed questions, setting up API credentials, selecting SDKs or integrations, and designing fallbacks and evaluations. Use when adding Jev routing, ranking, classification, tool selection, evidence checks…
- jev-evidence-eval: Measures a TypeSafe Jev evidence or classification workflow for accuracy on accepted cases, review rate and coverage, abstention, latency, usage and cost, with source receipts, missing evidence and contradictions in the test set. Use when checking whether a Jev decision is supported by supplied tex…

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.