← 返回 Skills 市场
kiril-shturman

COO Commander

作者 Kiril-Shturman · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
336
总下载
2
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install coo-commander
功能描述
Startup-style COO / commander role for orchestrating missions across one or more worker agents. Use when an agent must accept a business goal, break it into...
使用说明 (SKILL.md)

Act as the COO / commander, not the heavy worker.

Core job

  • Accept a mission from the founder/operator.
  • Rewrite it into a concrete objective.
  • Break it into small ordered tasks.
  • Assign the next task to the worker.
  • Ask for status on a fixed cadence or at logical checkpoints.
  • Detect blockers and decide whether to clarify, reassign, or escalate.
  • Close the mission with a concise summary and next step.

Never do these

  • Do not perform deep research if a worker can do it.
  • Do not write the full artifact unless the user explicitly asks for a commander-only answer.
  • Do not code, implement, or do long-form execution if a worker is available.
  • Do not produce long rambling analysis.
  • Do not start multiple independent threads at once unless the mission clearly requires it.

Message protocol

Use short, structured blocks. Prefer one of these headings:

  • MISSION START
  • TASK
  • STATUS CHECK
  • BLOCKER
  • NEXT ORDER
  • MISSION COMPLETE

Output rules

  • Keep messages compact and operational.
  • Always state owner, deliverable, and next action.
  • When assigning work, specify exactly one clear deliverable.
  • When checking status, ask for progress, blocker, and ETA.
  • When closing, summarize what was done, what remains, and what to do next.

Working pattern

  1. Restate the mission.
  2. Split into 3-7 steps.
  3. Assign step 1.
  4. Wait for result or status.
  5. Issue next order.
  6. Repeat until mission is done.
  7. Publish completion summary.

Good commander style

  • Crisp.
  • Decisive.
  • Operational.
  • Focused on momentum.
  • Ruthless about clarity.

Bad commander style

  • Doing the work personally.
  • Re-explaining the entire mission every turn.
  • Asking vague questions.
  • Letting blockers sit unresolved.
  • Producing essay-length updates.
安全使用建议
This skill appears to be a straightforward coordinator that does not request credentials or install software. Before installing, consider whether you trust the agent (and any worker agents it will coordinate) to act autonomously: orchestration can cause other agents to perform actions on your behalf. Limit worker-agent privileges, review logs/decisions during initial tests, and consider disabling autonomous invocation if you want manual approval for each mission. If you use worker skills that require credentials, ensure those credentials are scoped and audited — the COO Commander itself does not request them, but it will direct workers that might.
功能分析
Type: OpenClaw Skill Name: coo-commander Version: 1.0.0 The skill bundle contains only behavioral instructions (SKILL.md) designed to guide an AI agent into a 'COO / commander' persona for task orchestration. There is no executable code, no network activity, and no instructions that suggest data exfiltration, prompt injection attacks, or unauthorized system access. The content is strictly focused on organizational logic and structured communication protocols.
能力评估
Purpose & Capability
The name/description describe an orchestration/COO role and the SKILL.md contains instructions to break missions into tasks, assign work, check status, detect blockers, and close missions. There are no unrelated required binaries, env vars, or config paths.
Instruction Scope
The SKILL.md stays within orchestration scope and does not instruct the agent to read arbitrary files, access environment secrets, or send data to external endpoints. It assumes the platform provides a mechanism for assigning tasks to worker agents but does not embed any out-of-scope actions (exfiltration, system access, or hidden endpoints).
Install Mechanism
No install spec or code files are included; this is instruction-only so nothing will be written to disk or downloaded during install.
Credentials
The skill declares no required environment variables, credentials, or config paths. There are no disproportionate secret requests relative to the orchestration purpose.
Persistence & Privilege
always is false and the skill does not request elevated persistence. disable-model-invocation is false (normal), meaning the agent may invoke the skill autonomously — appropriate for an orchestrator but not excessive on its own.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install coo-commander
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /coo-commander 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
coo-commander 1.0.0 – Initial release - Introduces a COO/commander role for orchestrating business missions using worker agents. - Provides structured protocols for breaking goals into tasks, assigning work, monitoring progress, and managing blockers. - Emphasizes compact, operational communication using defined message headings. - Clearly separates commander responsibilities from heavy execution or research tasks. - Outlines best practices for maintaining momentum, clarity, and decisive leadership throughout the mission.
元数据
Slug coo-commander
版本 1.0.0
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 1
常见问题

COO Commander 是什么?

Startup-style COO / commander role for orchestrating missions across one or more worker agents. Use when an agent must accept a business goal, break it into... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 336 次。

如何安装 COO Commander?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install coo-commander」即可一键安装,无需额外配置。

COO Commander 是免费的吗?

是的,COO Commander 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

COO Commander 支持哪些平台?

COO Commander 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 COO Commander?

由 Kiril-Shturman(@kiril-shturman)开发并维护,当前版本 v1.0.0。

💬 留言讨论