Jev

Ask the Jev (System One) model for a typed decision — a calibrated probability for a bounded question. Use when the agent must choose among options (routing, tool choice, loop control), answer yes/no (urgency, moderation), or rate on a scale (risk, sentiment) instead of guessing.

9 stars 1 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add Vincent-the-gamer/skills --skill jev
Manual install
git clone --depth 1 https://github.com/Vincent-the-gamer/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/skills/jev ~/.claude/skills/jev

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Jev

Jev is TypeSafe AI's System One Model. It returns a **typed decision** — one pick, one probability, or one score — rather than prose, so the answer is calibrated and can be acted on directly.

Reach for it when a guess would be too vague to defend.

`scripts/jev.mjs` is self-contained (axios and cac are bundled); run it with Node.js ≥ 20.

## Before you ask

`state` is the situation; `question` is one bounded question about it. Jev answers structured questions, not open-ended prompts — restate the request as those two fields, plus an option list for `choice` and `score`.

Never put passwords, credentials, or personal data in `state` or `question`.

## Choose one — `choice`

```bash
node scripts/jev.mjs choice \
  --state "A customer writes: my plan was charged twice this month, can you refund one charge?" \
  --question "Which team should handle this ticket?" \
  -o Billing -o "Tech Support" -o Sales -o "Account Security"
```

**Done when** you hold `decision` (the picked label) and its `probability`.

## Answer yes / no — `noul`

```bash
node scripts/jev.mjs noul \
  --state "A user's account just signed in from another country and they ask you to freeze it now." \
  --question "Does this need an immediate reply?"
```

Takes no options. `probabilities[0]` is P(yes) and `probabilities[1]` is P(no).

**Done when** you hold the yes probability.

## Rate on a scale — `score`
Read the full skill on GitHub

Details

Skill name
jev
Path
skills/jev/SKILL.md
License
Apache-2.0
Repo updated
15 November 2026

FAQ

What does the Jev skill do?

Ask the Jev (System One) model for a typed decision — a calibrated probability for a bounded question. Use when the agent must choose among options (routing, tool choice, loop control), answer yes/no (urgency, moderation), or rate on a scale (risk, sentiment) instead of guessing.

How do I install the Jev skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add Vincent-the-gamer/skills --skill jev. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Jev popular?

It lives in Vincent-the-gamer/skills, which has 9 GitHub stars and 1 forks.

Related skills

Slidev

9

Vincent-the-gamer/skills

Create and present web-based slidedecks for developers using Slidev with Markdown, Vue components, code highlighting, animations, and interactive features. Use when building technical presentations, conference talks, code walkthroughs, teaching materials, or developer decks.

Documents & Office Files

Build MCP App

9

Vincent-the-gamer/skills

This skill should be used when the user wants to build an "MCP app", add "interactive UI" or "widgets" to an MCP server, "render components in chat", build "MCP UI resources", make a tool that shows a "form", "picker", "dashboard" or "confirmation dialog" inline in the conversation, or mentions "apps SDK" in the context of MCP. Use AFTER the build-mcp-server skill has settled the deployment model, or when the user already knows they want UI widgets.

AI, LLMs & Agents

Build MCP Server

9

Vincent-the-gamer/skills

This skill should be used when the user asks to "build an MCP server", "create an MCP", "make an MCP integration", "wrap an API for Claude", "expose tools to Claude", "make an MCP app", or discusses building something with the Model Context Protocol. It is the entry point for MCP server development — it interrogates the user about their use case, determines the right deployment model (remote HTTP, MCPB, local stdio), picks a tool-design pattern, and hands off to specialized skills.

AI, LLMs & Agents

Md Review

9

JordanGunn/nunchuck

Agent review for markdown quality, clarity, and structural integrity. Leverages deterministic lint output as input for subjective assessment.

AI, LLMs & Agents

Grape

9

JordanGunn/nunchuck

AI-enabled, deterministic codebase search. Converts vague intent into explicit, auditable grep parameters and executes a stable surface scan over disk.

AI, LLMs & Agents

Minimap

5

zot/mini-spec

The mini-spec structural model in miniature — the 3-level spec→design→code layout, where artifacts live, the root spec index, and the traceability links that connect them. Load to navigate or search a mini-spec project across specs, design, and code (the model, not the maintenance process). Foundation for mini-spec.

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.