command-center
Skill1 starsChanged 3 months agoMITView on GitHub
总指挥调度中枢。当用户提出任何任务/需求/想法时,先判断任务属于哪个垂直领域(自媒体/办公文档/游戏/情报),路由到对应垂直 Agent;无匹配领域则走通用流程(need-first-solutions)。知道"何时何地什么情况下调用哪个垂直 Agent"。垂直 Agent 注册表持续扩充。
4 other projects use a version of this.
Adopted by
Most recently taken up by
- genericService/claude-skillstheir own version, first seen Nov 8, 2026
- heypastel/pastel-outbound-systemtheir own version, first seen Nov 8, 2026
- dgoomeez002-afk/claude-skillstheir own version, first seen Oct 20, 2026
- jontsai/openclaw-command-centertheir own version, first seen Feb 3, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- jontsai/openclaw-command-center★ 247same name
- heypastel/pastel-outbound-system★ 2same name
- genericService/claude-skills★ 1same name
- dgoomeez002-afk/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository5 other files it gives its agents.
- cn-platform-intelSkill
- feel-calibratorSkill
- skill-orchestratorSkill
- structured-handleSkill
- video-distillSkill
The file
Files
总指挥 · 垂直 Agent 调度中枢
配套说明:本技能是一个"路由框架",它引用的垂直 Agent(如 creator-agent)和通用流程(need-first-solutions)是外部依赖,不包含在本仓库——需要你自行安装或编写对应技能后才能完整运行。没有这些依赖时,本技能退化为"任务分类建议"。
何时使用(When to Use)
- 用户提出任何任务/需求/想法,需要判断该交给哪个垂直 Agent。
- 用户说"做内容/发小红书/写公众号/做视频/处理文档/查情报"等跨领域任务。
- 不确定任务归属时,用本技能做路由判断。
- 何时不用(Do NOT use for):单领域内已有明确技能的任务(直接调技能);纯闲聊;不涉及 Agent 分工的简单问答。
定位
收到任何用户任务 → 判断属于哪个垂直领域 → 路由到对应垂直 Agent。只做"选路",不做"干活"(干活交给垂直 Agent 和它的技能)。
垂直 Agent 注册表(持续扩充)
| 领域 | 入口(垂直 Agent) | 触发场景 | 状态 |
| 自媒体内容生产 | creator-agent | 做内容/发小红书/写公众号/做视频/文案/封面 | ✅ 已上线 |
| 办公文档 | (规划中 doc-agent) | PDF/Word/PPT/Excel 处理 | ⏳ 第2期 |
| 游戏/模拟器 | (规划中 game-agent) | 手游辅助/拍卖行抢购 | ⏳ 第2期 |
| 情报选品 | (规划中 intel-agent) | 热搜/选品/竞品分析 | ⏳ 第2期 |
路由流程
- 理解任务:用户要达成什么结果(先想真实需求,见 need-first-solutions Step 1)
- 匹配领域:对照注册表——任务属于哪个垂直领域?
- 内容创作类 → creator-agent
- (未来)文档类 → doc-agent;游戏类 → game-agent;情报类 → intel-agent
- 检查目标 Agent 状态:注册表里是 ✅ 已上线 → 路由;是 ⏳ 规划中 → 不空转,降级走通用流程(need-first-solutions),并在结果里注明"该领域 Agent 尚在建设中,先用通用方案"。
- 路由:把任务+上下文交给对应垂直 Agent,并显式交代下一步:"收到任务后,由你触发 skill-orchestrator 做技能编排"(接力棒交接清楚,防止链条断在中间)。
- 兜底:无匹配领域 → 走 need-first-solutions 通用流程(需求→方案→推荐),不硬套垂直 Agent
与 skill-orchestrator 的分工
- command-center(本技能):任务来了"选领域"(跨领域路由)
- skill-orchestrator:领域内"编排技能"(拆需求→映射→调用)
- 调用链:任务 → command-center 选领域 → 垂直 Agent → skill-orchestrator 编排具体技能
扩展规则(新增垂直 Agent 时)
- 每新增一个垂直 Agent,在注册表加一行(领域/入口/触发场景/状态)
- 新增前先查现成(市场/GitHub/外网有无同类 agent 可直接用)
- 垂直 Agent 成熟后(流程跑通、验证过),用 expert-manager 包装成 WorkBuddy 专家(可发布/变现)
使用示例
示例 1 · 内容任务路由:
用户:"帮我写一篇小红书笔记推荐我的桌宠"
→ 匹配领域:自媒体内容生产(✅ 已上线)
→ 路由给 creator-agent,交代"收到任务后触发 skill-orchestrator 编排技能"示例 2 · 无匹配领域兜底:
用户:"帮我算一下这个月电费平均每天多少"
→ 注册表无匹配领域
→ 降级走 need-first-solutions 通用流程(需求→方案→推荐)示例 3 · 目标 Agent 未建成:
用户:"帮我做一个拍卖行抢购脚本"
→ 匹配领域:游戏/模拟器(⏳ 规划中)
→ 不空转,降级走通用流程,并注明"游戏 Agent 建设中,先用通用方案"坑(Gotchas)
- 别把任务硬套到不匹配的领域(宁可走通用流程)
- 垂直 Agent 只做编排,不重复技能内容
- 用户是小白:路由决策不用告诉他技术细节,直接给他结果
禁止(Do NOT)
- 禁止替垂直 Agent 执行具体任务(只路由,不干活)。
- 禁止对不匹配领域的任务硬套垂直 Agent(走通用流程兜底)。
- 禁止在注册表里虚构"已上线"的 Agent(没建就是规划中)。
- 禁止把任务细节一股脑塞给用户(给他结果,不给过程)。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

