ss_y2n

An agent skill (Claude Code + Codex, same SKILL.md) that audits a repo read-only and finds the fuzzy decisions — routing, triage, severity, escalation — that could become a typed Jev question: Choice, Score, or Noul.

Output is a ranked, source-grounded report: file/line, current behavior, a concrete question contract, a fallback, and what stays in code (math, auth, ranking). It's conservative — "keep as code" and "zero candidates" are valid findings. Includes a worked example and a stdlib validator in CI. Feedback welcome on the suitability gates.

Buy a mac mini. Add a decent monitor, keyboard and mouse and you are ready.

Are there any other companies doing this? Why not? Is it not a big enough problem to solve. Or is it that the actual buyer of such product and user of products differ from one another.

Quick question here: Is it not many times that the problem with estimates is scoping and not really the time estimate of the scope decided?