Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

Awesome Jev Skills

Installable agent skills for triage, routing, code review and document work with Jev, plus 108 scenarios and recorded examples.

ArticlebetaMIT
View on GitHub ↗

Overview

Awesome Jev Skills collects Jev demos, workflows and installable skills for coding agents, built on the idea that Jev chooses, classifies and scores while your agent supplies evidence and takes action. It lists 66 community projects and resources (browser agents, Tetris, a small simulated city, music, code review and more), a set of installable skills, and a catalogue of 108 scenarios with templates and 14 recorded input/output pairs.

Skills use a standard-library-only Python decision wrapper and are installed by giving an install prompt to your agent. It notes that listed community projects are not installed or tested by the maintainers and that alternatives are not official Jev. It has tests in CI and English and Chinese docs.

What the decision model decides

TypeQuestionAnswers
ChoiceWhich route or category fits this item? (triage and routing skills)(inferred)—
Yes / noDoes this code need a closer look? (code review skill)(inferred)yes · no

How it works

  1. Give the install prompt to your agent
  2. Pick a skill or scenario
  3. Agent gathers evidence and calls Jev via the wrapper
  4. Agent acts on the typed answer

Strengths

  • Stdlib-only wrapper
  • Recorded examples to compare against
  • CI tests

Caveats

  • Listed community projects are not tested

Getting started

Give the README's install prompt to your coding agent.

At a glance

Type
Article
Status
beta
Language
Python
Runtime
agent skills
Has code
yes
Has tests
yes
License
MIT

Use cases and integrations

How curated lists describe it

  • This project is a collection of Jev use cases, workflows, and agent skills with a stdlib-only Python decision wrapper.

    logicrw/awesome-jev-projects

  • An awesome collection of Jev use cases, workflows, and agent skills.

    wh000wh000/awesome-jev-live

  • An awesome collection of Jev use cases, workflows, and agent skills.

    hellogumbo/awesome-jev

  • Nine installable agent skills — triage, routing, code review, document and UI work — with a catalogue of scenarios to copy.

    MrJev/awesome-jev

Frequently asked questions

What skills are included?

Triage, routing, code review, document and UI work skills.

Does it need dependencies?

The decision wrapper uses only the Python standard library.

Are listed projects tested?

No, listing does not mean installed or tested.

Related projects

  • decisionkit

    CLI, MCP server and Claude Code plugin for closed-form yes/no, choice, score and rank decisions via Jev, OpenAI Decisions or Claude.

    MCP serverbetaTypeScript
  • jev-flash-router

    MCP server exposing Jev Noul, Choice and Score via OpenRouter so coding agents can make quick decisions without reasoning tokens.

    MCP serverbetaTypeScript
  • hermes-jev-plugin

    Hermes Agent plugin exposing Jev as four coding-workflow tools: jev_check, jev_route, jev_score and jev_evaluate.

    PluginbetaPython
  • jev-code

    Gives Claude Code, Codex, Pi and OpenCode five typed Jev tools (classify, check, score, rank, ask) plus a skill on when to use them.

    MCP serverbetaTypeScript
  • jev-mcp-spring

    Java/Spring Boot MCP server exposing Jev classify, score, check and patch-gate tools over HTTP instead of stdio.

    MCP serverbetaJava
  • jev-workbench

    Local service to define, test and publish versioned Jev judgment functions, callable over HTTP by backends and over MCP by agents.

    MCP serverbetaTypeScript