create-subagent
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。
Best use case
create-subagent is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
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。
Teams using create-subagent should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/reate-subagent/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How create-subagent Compares
| Feature / Agent | create-subagent | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
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。
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
SKILL.md Source
# 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：
```bash
# 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"
**你**:
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：
```json5
{
"agents": {
"list": [
{
"id": "main",
"subagents": { "allowAgents": ["main", "developer"] }
}
],
"defaults": {
"subagents": {
"maxConcurrent": 8,
"maxSpawnDepth": 2
}
}
}
}
```
需要重启 Gateway 使配置生效。Related Skills
Auto Create AI Team
## Description
superpowers-subagent-dev
Use when executing implementation plans with independent tasks - coordinates task execution by dispatching subagents per task with verification checkpoints, adapted for OpenClaw's isolated session model
create-task
Create a new task with a crypto bounty on OpenAnt. Use when the agent or user wants to post a job, create a bounty, hire someone, post work, or use AI to parse a task description. Covers "create task", "post a bounty", "hire someone for", "I need someone to", "post a job". Funding escrow is included by default.
create-dxf
Create RFQ-ready 2D DXF (and optional SVG preview) files from a strict, validated JSON spec derived from a natural-language design prompt. Use for sheet/plate parts (waterjet/laser/router) like mounting plates, gussets, brackets, hole patterns, and slots.
toingg-create-campaign
End-to-end Toingg ops: create campaigns, (optionally) schedule daily analytics pulls, and turn Excel contact sheets into WhatsApp outreach via add_contacts + send_whatsapp_templates. Use when Codex needs to automate Toingg voice/WhatsApp workflows and requires scripts for campaign POSTs, analytics cron setup, or bulk contact uploads.
create-telegram-agent
Create a new Telegram agent in OpenClaw with proper configuration. Use when user wants to create a new Telegram bot agent, including setting up agent workspace, Telegram binding, and bot token configuration. Requires user confirmation before modifying openclaw.json.
create-mcp-server
Create, deploy, and manage MCP (Model Context Protocol) servers using the MCPHero platform via the mcpheroctl CLI. Use this skill when the user wants to build an MCP server, deploy tools that wrap APIs or databases, automate MCP server creation, or connect AI clients (Claude Desktop, Cursor, etc.) to custom tools through MCPHero.
I'm not able to create a skill document for this project.
This repository is designed to artificially inflate TikTok metrics (views, likes, followers, shares) through automation, CAPTCHA bypassing, and proxy rotation to avoid detection. This is:
---
name: article-factory-wechat
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
tavily-search
Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.