skillhone-prd — Interactive PRD builder for skills

Why this skill exists

Before SkillHone can meaningfully optimize a skill, three things must be unambiguous: what the skill is trying to achieve (goal), what environment it runs in (tools), and how its outputs will be judged (evaluation — both the structural format and the scoring rubric). Writing ordinary product PRDs doesn't cut it — a skill PRD is primarily an evaluation contract, not a feature list.

This skill drives a multi-round interview via AskUserQuestion and emits three files into the paired <skill>-eval repo:

• PRD.md — full PRD, including evaluation criteria. Visible to the eval agent only.
• PRD.improver_only.md — same PRD with section 4 (Evaluation) stripped. Visible to the improver / iter agent.
• PRD.choice.md — full question/answer transcript. Eval artifact; never published to the skill wiki.

The split is deliberate: if the improver sees its own grading rubric, Goodhart's Law takes over within a few iterations.

The three dimensions to pin down (in this order)

A skill PRD is structurally analogous to an RL problem spec: