Ask me what skills you need
What are you building?
Tell me what you're working on and I'll find the best agent skills for you.
Multi-agent deep discussion through intelligent Orchestrator coordination with agenda checklist tracking.
User: "深入讨论预制菜行业现状,使用 5 个专家"
Assistant:
1. Check maxSpawnDepth
2. Align topic (自然对话式)
3. Confirm experts
4. Spawn Orchestrator subagent (thinking: "high")
Result: Agenda items × 3 rounds = 根据议程数量而定
每个讨论会生成以下文件(保存到 workspace/deep-discussion/{topic-slug}/):
| 文件 | 内容 |
|---|---|
agenda.md | 议程清单(checklist 格式),追踪讨论进度 |
discussion-log.md | 完整讨论记录,包含所有专家的原始输出(必须!) |
report.md | 结构化报告,提炼关键决策和行动计划 |
action-plan.md | 详细行动计划,包含时间线和负责人 |
⚠️ 讨论完成后不要创建其他文件(如 discussion.md),避免与 discussion-log.md 重复。
议程清单采用 checklist 格式,追踪讨论进度:
# 议程清单 - {topic}
## Phase 1: 价值定位
- [ ] 1. 讨论是否要修改议程
- [ ] 2. 学习规划功能的价值主张是什么?
- [ ] 3. 与自适应引擎如何协同?
## Phase 2: 实现方式
- [ ] 4. 时长预测技术路径?
- [ ] 5. 数据需求与特征工程?
...
## 讨论进度
- 总议题数:{N}
- 已完成:{M}
- 进行中:{K}
Orchestrator 职责:
agenda.md必须包含所有专家的原始输出!
# 完整讨论记录 - {topic}
npx skills add LeoYeAI/openclaw-master-skills --skill deep-discussionHow clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
Clear and well structured, with only minor parts that might need a second read.
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
Mostly actionable with clear steps; only a few small gaps remain.