Agent skill
magi-brainstorm
三機(Claude/Gemini/Codex)平行分析創意，評估可行性、維護性、安全風險後投票共識
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/magi-brainstorm
SKILL.md
MAGI Brainstorm 快捷指令
/magi-brainstorm [idea]- 創意發想與可行性分析
此指令為 /magi brainstorm [idea] 的快捷方式。
使用方式
/magi-brainstorm 實現即時通知系統的最佳方式
執行內容
自動啟動 MAGI 三機平行分析：
| 機體 | 引擎 | 分析重點 |
|---|---|---|
| MELCHIOR-1 | Claude Opus | 創新可行性、技術選型 |
| BALTHASAR-2 | Gemini | 實作可維護性、團隊匹配度 |
| CASPER-3 | Codex/GPT | 安全風險、合規性要求 |
🚨 強制執行規則
禁止事項：
- ❌ 禁止委派給其他 agent 處理
- ❌ 禁止使用非指定的工具
必須使用：
- ✅ MELCHIOR-1:
Tasktool withsubagent_type="general-purpose",model="opus" - ✅ BALTHASAR-2:
mcp__gemini__ask-gemini(先用 ToolSearch 載入) - ✅ CASPER-3:
mcp__codex-cli__ask-codex(先用 ToolSearch 載入)
執行步驟：
- 先調用
ToolSearch載入mcp__gemini__ask-gemini和mcp__codex-cli__ask-codex - 在單一訊息中同時發出三個 tool calls（Task + Gemini + Codex）
- 等待三機回應後彙整共識報告 </MANDATORY>
模型設定（brainstorm 任務）
| 機體 | 模型 | 參數 |
|---|---|---|
| MELCHIOR-1 | opus |
- |
| BALTHASAR-2 | gemini-3-pro-preview |
- |
| CASPER-3 | gpt-5.2 |
reasoningEffort: "high" |
請參考 /magi-system 了解完整的投票機制與共識報告格式。
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?