Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Create SubAgent

v1.0.1

创建和管理 SubAgent(子智能体)。使用当用户需要:(1) 创建新的 SubAgent 执行特定任务,(2) 查看/管理已有的 SubAgent,(3) 终止或指导 SubAgent。支持多种预设类型:开发、研究、写作、数据分析等。

0· 470·1 current·1 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name and description match the SKILL.md: templates, creation steps, management commands, and configuration notes are all relevant to creating and managing SubAgents. There are no unrelated required binaries, env vars, or config paths declared.
Instruction Scope
Instructions stay within the SubAgent domain: ask user for requirements, choose mode, and call sessions_spawn / use /subagents management commands. It does recommend checking/modifying openclaw-config.json (to enable subagents) and restarting the gateway — this is appropriate but requires admin action outside the skill. Templates mention tools (e.g., exec(Python), web_search) that SubAgents may use; that is expected but means spawned SubAgents could execute code or fetch web content.
Install Mechanism
No install spec and no code files to run — instruction-only skill. No downloads or archive extraction; therefore low install risk.
Credentials
No environment variables, credentials, or config paths are requested by the skill. The only config referenced is openclaw-config.json, which is relevant to enabling SubAgents and is documented in the SKILL.md.
Persistence & Privilege
Skill is not always-enabled and is user-invocable. It instructs spawning SubAgents (run or session) which by design can act autonomously; this is expected for the capability but increases operational risk (e.g., spawned agents executing code or making external requests). The skill itself does not request elevated platform privileges.
Assessment
This skill is coherent with creating and managing SubAgents, but before installing check: (1) confirm your platform provides the sessions_spawn API and /subagents commands the skill expects, (2) review and back up openclaw-config.json before changing allowAgents or restarting gateway, (3) prefer 'run' mode until you trust behavior of spawned agents, since 'session' agents can persist and execute actions (including code execution or web fetches), (4) enforce limits (max concurrent, spawn depth) and monitor logs for unexpected activity, and (5) prefer installing only from a trusted source — the skill's homepage/source is listed as unknown, so verify provenance if you plan to enable it in production.

Like a lobster shell, security has layers — review code before you run it.

latestvk97e5st9jbm26pt1d2v45mmmdh821nbz

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Runtime requirements

🤖 Clawdis

SKILL.md

SubAgent 创建助手

帮助用户快速创建和管理 SubAgent(子智能体)。

何时使用

使用此 Skill 当:

  • "帮我创建一个开发助手"
  • "创建一个研究 SubAgent"
  • "我需要一个新的 SubAgent 来处理..."
  • "查看我有哪些 SubAgent"
  • "终止那个开发 SubAgent"

不使用此 Skill 当:

  • 直接使用 /subagents 命令(用户自己操作)
  • 简单的单次任务(不需要独立 SubAgent)

SubAgent 类型模板

1. 代码开发 (dev-agent)

task: |
  你是一个专业的全栈开发工程师,使用 Claude Code 帮助用户开发应用。
  
  职责:
  - 需求分析、架构设计
  - 代码编写、调试修复
  - 代码审查、优化建议
  - 文档编写
  
  技术栈:React/Vue、Node.js/Python、PostgreSQL/MongoDB 等
  
  等待用户的开发任务...
label: dev-agent

2. 研究助手 (research-agent)

task: |
  你是一个专业的研究助手,帮助用户进行信息搜集和分析。
  
  职责:
  - 网络搜索和信息搜集
  - 资料整理和归纳
  - 数据分析和总结
  - 生成研究报告
  
  使用工具:web_search, web_fetch, read, write
  
  等待用户的研究任务...
label: research-agent

3. 写作助手 (writer-agent)

task: |
  你是一个专业的写作助手,帮助用户撰写各种文档和内容。
  
  职责:
  - 文章撰写和编辑
  - 文档结构和大纲
  - 内容润色和优化
  - 风格调整和校对
  
  擅长:技术文档、博客文章、报告、邮件等
  
  等待用户的写作任务...
label: writer-agent

4. 数据分析 (data-agent)

task: |
  你是一个数据分析专家,帮助用户处理和分析数据。
  
  职责:
  - 数据清洗和预处理
  - 统计分析和可视化
  - 数据洞察和报告
  - Python 脚本编写
  
  工具:exec (Python), read, write
  
  等待用户的数据分析任务...
label: data-agent

5. 自定义 SubAgent

用户描述需求,你帮助设计 task 和 label。


创建流程

Step 1: 确认需求

询问用户:

  • 要创建什么类型的 SubAgent?
  • 主要职责是什么?
  • 需要什么特殊技能或工具?

Step 2: 选择模式

  • run(默认)- 一次性任务,完成后自动结束
  • session - 持久会话(需要 channel 支持 thread binding)

Step 3: 调用 sessions_spawn

使用以下参数:

task: [SubAgent 的系统提示词]
label: [简洁的标识名称]
mode: "run" | "session"
cleanup: "keep"

Step 4: 汇报结果

告知用户:

  • SubAgent 创建成功
  • Run ID 和 Session Key
  • 如何与 SubAgent 交互

管理命令

告知用户这些命令:

# 查看所有 SubAgent
/subagents list

# 查看详细信息
/subagents info <id|#>

# 查看日志
/subagents log <id|#>

# 发送消息
/subagents send <id|#> "消息内容"

# 指导调整
/subagents steer <id|#> "调整方向"

# 终止 SubAgent
/subagents kill <id|#|all>

示例对话

用户: "帮我创建一个开发 SubAgent"

: 好的!我来帮你创建一个代码开发 SubAgent。

这个 SubAgent 将能够:

  • 使用 Claude Code 进行开发
  • 帮你编写、调试、审查代码
  • 支持 React/Vue、Node.js/Python 等技术栈

创建中...

开发 SubAgent 已创建!

  • 标签: dev-agent
  • 模式: run (一次性任务)
  • 状态: 运行中

你可以用这些命令管理它:

  • /subagents send #1 "帮我创建一个 Express API"
  • /subagents log #1 查看进度
  • /subagents kill #1 终止

现在要给它分配什么开发任务吗?


注意事项

  1. Webchat 限制 - 当前渠道不支持 session 模式(需要 thread binding)
  2. 资源配置 - 确保 openclaw-config.json 中配置了 subagents.allowAgents
  3. 自动归档 - SubAgent 完成后 60 分钟自动归档
  4. 并发限制 - 默认最多 8 个并发 SubAgent

配置检查

如果创建失败,检查:

{
  "agents": {
    "list": [
      {
        "id": "main",
        "subagents": { "allowAgents": ["main", "developer"] }
      }
    ],
    "defaults": {
      "subagents": {
        "maxConcurrent": 8,
        "maxSpawnDepth": 2
      }
    }
  }
}

需要重启 Gateway 使配置生效。

Files

3 total
Select a file
Select a file to preview.

Comments

Loading comments…