← ClaudeAtlas

gatherlisted

This skill should be used BEFORE any feature design. It runs structured gathering with the user — asking 5 high-leverage questions per round, up to 3 rounds, to extract Goal / Scope / Constraints / Edges / Done. Output is saved to .mumei/scratch/<topic>.md and used as input for /mumei:proceed. Triggers include "I want to add X", "we need a feature for Y", "let's brainstorm Z", or any vague feature request.
hir4ta/mumei · ★ 1 · AI & Automation · score 70
Install: claude install-skill hir4ta/mumei
<!-- Role: Pre-spec gathering partner for /mumei:proceed Input: free-form feature request from the user Output: .mumei/scratch/<topic>.md (structured, consumed by /mumei:proceed) Principle: Questions must be high-leverage. Cap at 5 per round x 3 rounds. No silent assumptions. --> # Gather Run a structured gathering session with the user before they invoke `/mumei:proceed`. The output is a scratch file at `.mumei/scratch/<topic>.md` that captures the user's intent in a form `/mumei:proceed` can consume cleanly. ## When to use - The user describes a vague feature request ("I want X", "let's add Y"). - The user asks for help thinking through a problem before specing it. - The user invokes `/mumei:gather` directly. Do NOT use this skill if `/mumei:proceed` is already running — `proceed` does its own clarification. ## Method Run up to **3 rounds of 5 questions each** (15 total cap). Each round: 1. Use `AskUserQuestion` with multiple-choice options where possible. 2. Aim for **high-leverage** questions: ones that materially affect architecture, data modeling, scope, testing, or UX. Skip trivial questions ("what should the variable be named?"). 3. Stop early if the user signals closure ("ok" / "good" / "proceed" / "make spec", or the equivalent in their language). ### Round 1 — Cover the 5 axes Aim to cover all five in this round. Use multiple-choice for speed: | # | Axis | Example phrasing