メニュー
Use when meetings are dominated by the loudest voices, when seeking diverse perspectives on roadmaps or forecasts, or when groupthink is hindering decision quality
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use when designing AI agent products, defining roadmaps for agentic workflows, or evaluating how to evolve AI from passive tool to proactive partner in software development
Shift from rigid roles (PM, Designer, Engineer) towards a model where individuals use AI to bridge skill gaps, enabling smaller and flatter teams. Use in early-stage startups or innovation units where speed is critical.
Use when designing AI agents or chatbots, when raw model outputs feel like a black box, or when building natural language interfaces that need structure and trust
Use when building AI-powered products or agents, when raw model intelligence isn't enough to solve user problems, or when designing the architecture for agentic workflows
View yourself as an entity with infinite dimensions rather than a single good/bad identity. Strengths and weaknesses are often the same trait in different contexts. Use during performance reviews or when receiving tough feedback.
Review your calendar, color-code activities by energy impact (Green/Red), and systematically delegate draining tasks to maximize time in your Zone of Genius.
| name | nominal-group-meeting |
| description | Use when meetings are dominated by the loudest voices, when seeking diverse perspectives on roadmaps or forecasts, or when groupthink is hindering decision quality |
A meeting structure designed to eliminate groupthink and coercion by separating the discovery of ideas from the discussion of them. It ensures independent thinking and focuses meeting time solely on areas of disagreement.
Core principle: The best way to get someone's opinion is independently of other people's opinions.
┌─────────────────────────────────────────────────────────────────┐
│ 1. ASYNCHRONOUS DISCOVERY │
│ Send prompt/data to participants BEFORE the meeting │
│ No reply-all allowed │
├─────────────────────────────────────────────────────────────────┤
│ 2. INDEPENDENT OUTPUT │
│ Participants generate ideas/forecasts/ranks ALONE │
│ Submit directly to leader │
├─────────────────────────────────────────────────────────────────┤
│ 3. AGGREGATION │
│ Leader collates responses │
│ Identifies areas of AGREEMENT (skip) and DISAGREEMENT │
├─────────────────────────────────────────────────────────────────┤
│ 4. DISCUSSION ONLY MEETING │
│ Group convenes SOLELY to discuss variance in opinions │
│ Reflect back what people say (curiosity over coercion) │
├─────────────────────────────────────────────────────────────────┤
│ 5. DECISION │
│ Often asynchronous, after discussion │
└─────────────────────────────────────────────────────────────────┘
| Do | Don't |
|---|---|
| Get opinions independently | Brainstorm live in the room |
| Use meetings for discussion only | Use meetings for discovery |
| Focus on disagreements | Seek "alignment" as primary goal |
| Reflect back to ensure heard | Let people interrupt |
Source: Annie Duke (First Round Capital, Decision Science Expert) via Lenny's Podcast