northseadl/norix-skills / agent-brainstorm
agent-brainstorm
VerifiedMulti-agent brainstorming: async opinion collision with expert personas. Mixed Codex/Claude Code engine. Use when multiple AI agents need to collaboratively discuss, debate, and converge on solutions through structured dialog. Triggers: brainstorm, multi-perspective discussion, opinion collision, expert debate, war room, collective intelligence, 头脑风暴, 多视角讨论, 集思广益.
| File | Kind | Size |
|---|---|---|
| .gitignore | other | 14 B |
| SKILL.md | skill md | 10.1 KB |
| agents/openai.yaml | config | 295 B |
| evals/evals.json | config | 4.1 KB |
| package.json | manifest | 454 B |
| references/agent-protocol.md | markdown | 3.4 KB |
| scripts/brainstorm.mjs | script | 49.3 KB |
| scripts/panel.html | other | 46.5 KB |
evals/evals.json
View on GitHub{
"skill_name": "agent-brainstorm",
"evals": [
{
"id": 1,
"prompt": "我想让几个 Agent 一起讨论一下我们项目的技术选型,用 Codex 和 Claude 混合跑,比如架构师用 Claude,性能工程师用 Codex",
"expected_output": "Agent 读取 SKILL.md,创建含 mixed engine 配置的 session JSON,执行 brainstorm.mjs",
"should_trigger": true
},
{
"id": 2,
"prompt": "帮我做个头脑风暴,我需要 5 个不同视角的专家来讨论我们新产品的 UI 方案,用 Claude Code 来跑",
"expected_output": "Agent 生成 5-agent session config with engine: claude,启动讨论",
"should_trigger": true
},
{
"id": 3,
"prompt": "brainstorm session about whether we should use event sourcing or CQRS for our payment system, run a war room with 4 experts",
"expected_output": "Agent creates session JSON with 4 domain experts, launches brainstorm engine",
"should_trigger": true
},
{
"id": 4,
"prompt": "我有个架构决策想集思广益,让多个 AI 从安全、性能、可维护性的角度辩论一下",
"expected_output": "Agent 识别「集思广益」「辩论」触发词,创建多角色 session",
"should_trigger": true
},
{
"id": 5,
"prompt": "需要方案选型讨论,微服务 vs 单体 vs serverless,3 个 agent 各自代表一个方案的支持者来辩论",
"expected_output": "Agent 创建 3-agent advocate session",
"should_trigger": true
},
{
"id": 6,
"prompt": "让 devil's advocate 和架构师针对我的 API 设计展开多视角讨论",
"expected_output": "Agent 识别 devil's advocate + 多视角讨论,启动 2-agent brainstorm",
"should_trigger": true
},
{
"id": 7,
"prompt": "我想让 AI agents 从不同角度分析这个 PRD 然后收敛出最优方案",
"expected_output": "Agent 识别意图,生成基于 PRD 的 brainstorm session",
"should_trigger": true
},
{
"id": 8,
"prompt": "把这个 PRD 拆成独立的开发任务,然后用 Codex 并行执行",
"expected_output": "应触发 agent-task-orchestration 而非 agent-brainstorm",
"should_trigger": false
},
{
"id": 9,
"prompt": "帮我写一个前端组件的技术方案文档",
"expected_output": "直接写文档,不需要多 agent 讨论",
"should_trigger": false
},
{
"id": 10,
"prompt": "用 Claude 帮我 review 这段代码有没有安全漏洞",
"expected_output": "单 agent 任务,不需要多 agent 碰撞",
"should_trigger": false
},
{
"id": 11,
"prompt": "画一个系统架构图来展示模块之间的关系",
"expected_output": "应触发 pm-toolkit 画 Mermaid 图而非 brainstorm",
"should_trigger": false
},
{
"id": 12,
"prompt": "帮我把这个功能实现一下,创建用户认证模块",
"expected_output": "直接编码任务,不需要讨论",
"should_trigger": false
},
{
"id": 13,
"prompt": "我在考虑数据库选型,能不能帮我比较一下 PostgreSQL 和 MySQL 的优劣",
"expected_output": "边界用例:单 agent 就能比较,不需要多 agent 讨论,除非用户明确要求多视角",
"should_trigger": false
},
{
"id": 14,
"prompt": "组织一个 agent 讨论会,让 3 个 Claude Code agent 和 2 个 Codex agent 一起分析我们的安全策略",
"expected_output": "Agent 识别混合引擎 + 多 agent 讨论意图,生成 mixed-engine session",
"should_trigger": true
}
]
}Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |