菜单
Run an AI Lab division meeting with research and build agents (no AI Startup agents). Use when the user requests to "start a lab meeting", "convene the lab", or "run a sprint retrospective for the lab".
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/SirNosh/bmad-ml --skill bmad-ml-lab-meeting命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | bmad-ml-lab-meeting |
| description | Run an AI Lab division meeting with research and build agents (no AI Startup agents). Use when the user requests to "start a lab meeting", "convene the lab", or "run a sprint retrospective for the lab". |
Follow the instructions in ./workflow.md.
When to use. If CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 is set at session start, assemble a team instead of dispatching serially. Nosh is team lead; the 13 AI Lab specialists are teammates (8 Research: bmad-sova, bmad-sage, bmad-cypher, bmad-viper, bmad-breach, bmad-fade, bmad-astra, bmad-killjoy; 5 Build: bmad-chamber, bmad-jett, bmad-gekko, bmad-omen, bmad-kayo). Team coordination happens via the shared task list and inter-agent mailbox.
Fallback contract. If the env var is unset, this workflow runs as serial Task-tool invocations per ./workflow.md. Users who don't opt in see no behavior change. The installer never writes CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS; users export it from their shell.
