← ClaudeAtlas

bondlisted

Assesses team fitness and composes agent teams. Use when "set up a team", "team for this", "should I use agents", "design a team", "how many agents", "agent team".
saadshahd/moo.md · ★ 32 · AI & Automation · score 82
Install: claude install-skill saadshahd/moo.md
Assess whether a task benefits from parallel agents. Most tasks are better solo. A team only pays off with genuine independence across modules. ## Presentation - **Minto pyramid via AskUserQuestion** — Label = recommendation (conclusion first). Description = one-line tradeoff (always visible). Detail panel = structured plain text, short lines (~50 chars), ALL CAPS for section headers, dashes for bullets. No markdown in detail panels. - **Minimal text between prompts** — One bold sentence framing, then AskUserQuestion. Nothing else. - **Infer, state, ask only if ambiguous** — Assess fitness yourself. Present your assessment as a choice, not a question. ## Workflow ### Step 1: Assess Read the task scope. Evaluate internally: - Can workers operate without each other's output? - Do they touch different files? - Is scope multi-module (8+ story points)? Search the codebase to identify module boundaries and file ownership zones. If any answer is no on file independence, fitness = solo. If scope is 3 or fewer story points, fitness = solo. Otherwise, fitness = team. Do not output assessment reasoning in any form — no headers, no bullet points, no labeled sections. Go straight to Step 2. ### Step 2: Choose mode **One bold sentence stating your assessment**, then AskUserQuestion with three options: - **Team (Recommended)** or **Solo (Recommended)** — whichever fitness determined. Label the recommended option. Description = one-line why. - Detail panel: module count, story p