roundtable
robbyczgw-cla 作
Web & Frontend Development概要
Multi-agent debate council — spawns 3 specialized sub-agents in parallel (Scholar, Engineer, Muse) for Round 1.
説明
このスキルでできること
Spawns three specialized sub-agents (Scholar, Engineer, Muse) in parallel to analyze a question from research, logic, and creative angles. A coordinator agent synthesizes their outputs, with an optional second round where agents cross-examine each other's findings and update their positions. Models per role are configurable via flags or a saved config file.
Running parallel specialist agents with an optional cross-examination round surfaces contradictions and blind spots that a single-agent response typically misses.
使いどころ
- Comparing database or infrastructure options for a new project
- Getting a code review from research, logic, and readability angles at once
- Evaluating a financial or investment decision with structured debate
- Stress-testing architectural trade-offs before committing to an approach
- Diagnosing a complex problem that has no obvious single correct answer
ワークフロー例
User asks: /roundtable Should I use PostgreSQL or MongoDB for a new SaaS app?
- 1
Captain parses the command and decomposes the question into role-specific sub-tasks
- 2
Scholar, Engineer, and Muse sub-agents are spawned in parallel with focused prompts and security wrappers
- 3
Each agent returns structured findings with confidence ratings and dissent notes
- 4
Captain summarizes Round 1, then spawns three Round 2 agents to challenge each other's conclusions
- 5
Captain synthesizes consensus, conflicts, and any changed positions into a final answer
A structured council answer with confidence level, points of agreement, dissent rationale, and consolidated source citations
インストール
clawhub install robbyczgw-cla/roundtableCLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。