← ClaudeAtlas

loom-idea-refinelisted

Use when an operator's rough product, engineering, workflow, research, or opportunity idea lacks clear problem, audience, scope decisions, system-shape, data-model or state implications, success criteria, design coherence, direction, or next Loom record move.
z3z1ma/agent-loom · ★ 15 · Code & Development · score 80
Install: claude install-skill z3z1ma/agent-loom
# loom-idea-refine Idea refinement is an outer-loop playbook for turning a rough concept into a clear next Loom move. It explores options, tests assumptions, chooses a direction, and routes durable results into Loom records. ## Loom Routing Common routes use these Loom skills for durable records or follow-up workflow: `loom-research`, `loom-specs`, `loom-plans`, `loom-tickets`, `loom-knowledge`, and `loom-constitution`. Follow any named Loom skill fully. This playbook adds workflow pressure; it does not shorten target-skill requirements. This playbook stays in the outer loop. It produces a routed next move: research, spec, plan, ticket, knowledge, constitution, or an explicit no-go. When the operator's ask is not concrete enough for execution, prefer this route over implementation. Its job is to reveal the scope, system-shape, data-model, state, evidence, and coherence choices that would otherwise be hidden inside an implementation guess. This playbook creates no separate idea ledger. ## Use This Playbook When Use this playbook when: - the operator has a vague product, engineering, workflow, or research idea - the problem, audience, success criteria, or constraints are unclear - several possible directions exist and need comparison - hidden assumptions need validation before execution - an idea should become a spec, research record, plan, ticket, knowledge note, or constitutional question Skip this playbook when the next Loom record move is already clear. ## Ro