Skip to content
Agentmart
Submit a tool

jev

Get an independent, scored second opinion about a piece of state from TypeSafe's System One model (Jev), called through cred.

Skill by IanLuo

IndexedLicense unknown
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/ianluo-jev

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Get an independent, scored second opinion about a piece of state from TypeSafe's System One model (Jev), called through cred. Use when a decision gate is being answered on judgement alone and a calibrated second opinion would help — "ask jev", "second opinion", "score this gate", "how confident is that", "is this gate uncertain", "double-check my call", "is this ready to merge", "is this deliverable actually done" — or when recording the result of such a check. Do NOT use it to gate or block anything — it advises and never decides. Do NOT use for research (that is librarian), for exploring a codebase (that is Explore), or as a substitute for a test, a check step, or evidence.

Use cases: testing, research

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/jev

What's inside

Skill name
jev
Description
Get an independent, scored second opinion about a piece of state from TypeSafe's System One model (Jev), called through cred. Use when a decision gate is being answered on judgement alone and a calibrated second opinion would help — "ask jev", "second opinion", "score this gate", "how confident is that", "is this gate uncertain", "double-check my call", "is this ready to merge", "is this deliverable actually done" — or when recording the result of such a check. Do NOT use it to gate or block anything — it advises and never decides. Do NOT use for research (that is librarian), for exploring a codebase (that is Explore), or as a substitute for a test, a check step, or evidence.
License
unknown
Metadata
domain: reasoning · audience: personal
Instructions
103 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts
  • Instructions call the network

Files (5)

  • SKILL.md
  • evidence.md · references/
  • observations.md · references/
  • rubrics.json · references/
  • jev.py · scripts/

The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub

More from IanLuo/skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Sep 26, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
License unknown
Repository
github.com/IanLuo/skills
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from IanLuo

Cite this page

jev skill. Agent Mart. https://agentmart.dev/skills/ianluo-jev (last updated 2026-10-24)