Jev 101
Start Guides
Search
中文 EN
Agents heat 1 · Quiet★ 0heat incomplete (no X)

next-steps-jev

A MIT Claude Code terminal plugin where the session model proposes up to three next prompts and hosted TypeSafe Jev scores each against your goal so the best suggestion is listed first; never auto-submits.

Repo: kevinyin9/next-steps-jev ↗

What it is

Rank suggested next prompts with a decision model.

What it does: Claude proposes next steps; Jev scores goal-helpfulness; you pick.

Why it belongs in the showcase: Clean skill-suggestion loop on hosted Jev without auto-run.

Caveats: Privacy and surface limits.

Evidence

Public MIT repo, created 2026-11-03, 0 stars as of 2026-11-04. README documents api.typesafe.ai payload limits, number-key draft insertion, conflict with original next-steps, and terminal-only rendering.

Caveats

  • Sends truncated conversation text to TypeSafe after each answer
  • Terminal Claude Code only; desktop/VS Code unsupported
  • Disable original next-steps to avoid key conflicts

Unofficial case page. Stars / list position observed for heat; do not treat heat as a quality SLA. Review the upstream README before you depend on it.