workshop-facilitation — Claude Code skill: what it does

What workshop-facilitation does

The skill lays down how an interactive session runs. It opens with a heads-up on time and question count, asks you to pick an entry mode, then asks a single question per turn and waits. Progress stays visible through labels such as Context Qx/8 during context collection and Scoring Qx/5 during scoring.

Regular questions come with short numbered answers, and numbered recommendations show up only at decision points, for example after context synthesis or when picking a priority. Responses like 1,3 or 1 and 3 get parsed and combined. Interrupt with a meta question and the flow answers it, restates where you are, then returns to the pending question. Say stop and it halts until you resume. Ask for a single output and the multi-turn part is skipped.

What you get is predictable pacing, not finished answers. The protocol knows nothing about your product: either you paste context at the start or you accept guessed details, and in that case the session closes with a list of assumptions worth checking. That list is usually where you see whether the session went off course.