一键导入
update-subagent
在用户需要添加和更新自己的子智能体(subagent)列表时立即使用。
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
在用户需要添加和更新自己的子智能体(subagent)列表时立即使用。
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
Expert in building cross-platform desktop applications using web technologies (HTML/CSS/JS) with the Electron framework.
TypeScript and JavaScript expert with deep knowledge of type-level programming, performance optimization, monorepo management, migration strategies, and modern tooling.
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.
Refine academic writing for computer science research papers targeting top-tier venues (NeurIPS, ICLR, ICML, AAAI, IJCAI, ACL, EMNLP, NAACL, CVPR, WWW, KDD, SIGIR, CIKM, and similar). Use this skill whenever a user asks to improve, polish, refine, edit, or proofread academic or research writing — including paper drafts, abstracts, introductions, related work sections, methodology descriptions, experiment write-ups, or conclusion sections. Also trigger when users paste LaTeX content and ask for writing help, mention "camera-ready", "rebuttal", "paper revision", or reference any academic venue or conference. This skill handles both full paper refinement and section-by-section editing.
The Baidu Baike Component is a knowledge service tool designed to query authoritative encyclopedia explanations for various nouns. Its core function is given a specific "noun" (object, person, location, concept, event, etc.) provided by the user, it returns a standardized, detailed entry explanation sourced from Baidu Baike.
Baidu Scholar Search - Search Chinese and English academic literature (journals, conferences, papers, etc.)
基于 SOC 职业分类
| name | update_subagent |
| description | 在用户需要添加和更新自己的子智能体(subagent)列表时立即使用。 |
智能助手的subagent列表配置文件一般在用户的工作目录下,文件名称为:SUBAGENT_CONFIG.json,包括CodeExecutorAgent、DrSaiAgent、HepAIWorkerAgent三种类型:
具体的格式为:
{
"agent_01": { // the name of the agent
"type": "CodeExecutorAgent", // the type of the agent
"description": "The descrpiption of the agent",
"tools": [],
"prompt": "The system prompt for the agent.",
"venv_path": "/path/to/workerspace" // the path of the venv environment
},
"agent_02": {
"type": "DrSaiAgent",
"description": "The descrpiption of the agent",
"tools": ["run_bash", "run_read", "run_write", "run_edit"], // the tools name that the agent can use
"prompt": "The system prompt for the agent.",
"model": "openai/gpt-5.2", // the model name
"model_type": "openai", // or anthropic
"base_url": "https://aiapi.ihep.ac.cn/apiv2" // if model_type is anthropic, using "https://aiapi.ihep.ac.cn/apiv2/anthropic"
},
"agent_03": {
"type": "HepAIWorkerAgent", // the type of the agent
"description": "The descrpiption of the agent",
"tools": [],
"prompt": "The system prompt for the agent.",
"model_remote_configs": {
"name": "remote_model_name",
"url": "https://aiapi.ihep.ac.cn/apiv2" // or any other url
}
},
"agent_04": {
"type": "RemoteAgent", // the type of the agent
"description": "The descrpiption of the agent",
"tools": [],
"prompt": "The system prompt for the agent.",
"model_remote_configs": {
"model": "openclaw",
"url": "http://127.0.0.1:18789/v1/chat/completions",
"headers": {
"Authorization": f"Bearer {token}",
"Content-Type": "application/json",
"x-openclaw-agent-id": "main"
}
}
}
注意:
DrSaiAgent智能体可以不添加model、model_type、base_url,系统将使用默认的基座模型。但是如果添加基座模型是必须说明model和model_type。DrSaiAgent智能体添加默认的基座模型或者为HepAIWorkerAgent智能体添加远程模型时,提醒用户模型与远程智能体名称是否在https://aiapi.ihep.ac.cn/中存在。base_url或者url,默认为"https://aiapi.ihep.ac.cn/apiv2",anthropic的模型默认为"https://aiapi.ihep.ac.cn/apiv2/anthropic"。CodeExecutorAgent类型的子智能体时未否指定venv环境路径,则系统将使用用户工作目录下的.venv环境进行代码块执行。~/.openclaw/gateway/openclaw.json设置chatCompletions为true:{
"gateway": {
"http": {
"endpoints": {
"chatCompletions": {
"enabled": true
}
}
}
}
}
SUBAGENT_CONFIG.json。CodeExecutorAgent子智能体,名称为code_executor_agent,描述为用于代码执行的子智能体,系统提示为The system prompt for the agent.,venv的环境路径为/home/xiongdb/work/synchrotron_agent/runs/abc。那么可以按照以下的格式添加:
{
"code_executor_agent": {
"type": "CodeExecutorAgent",
"description": "用于代码执行的子智能体",
"tools": [],
"prompt": "The system prompt for the agent.",
"venv_path": "/home/xiongdb/work/synchrotron_agent/runs/abc"
}
}
HepAIWorkerAgent子智能体,名称为remote_agent,远程智能体的名称为BOSS8Agent,描述为可执行BOSS作业提交的智能体。,提示词为The system prompt for the agent.。那么可以按照以下的格式添加:
{
"remote_agent": {
"type": "HepAIWorkerAgent",
"description": "可执行BOSS作业提交的智能体。",
"tools": [],
"prompt": "The system prompt for the agent.",
"model_remote_configs": {
"name": "BOSS8Agent",
"url": "https://aiapi.ihep.ac.cn/apiv2"
}
}
}
DrSaiAgent子智能体,名称为test_agent,描述为用于PDF文件检索的智能体,工具为["pdf_manual_search"],提示词为你是一个PDF文档检索智能体,你需要基于pdf_manual_search工具查询《spec - X-Ray Diffraction Software》等手册内容。,基座模型为openai/gpt-5.2。那么可以按照以下的格式添加:
{
"test_agent": {
"type": "DrSaiAgent",
"description": "用于PDF文件检索的智能体",
"tools": ["pdf_manual_search"],
"prompt": "你是一个PDF文档检索智能体,你需要基于pdf_manual_search工具查询《spec - X-Ray Diffraction Software》等手册内容。",
"model": "openai/gpt-5.2",
"model_type": "openai",
"base_url": "https://aiapi.ihep.ac.cn/apiv2"
}
}
RemoteAgent,如openclaw的聊天接口,名称为openclaw_agent,描述为A openclaw agent.,提示词为The system prompt for the agent.,访问的配置为:{
"model": "openclaw",
"url": "http://127.0.0.1:18789/v1/chat/completions",
"headers": {
"Authorization": f"Bearer {token}",
"Content-Type": "application/json",
"x-openclaw-agent-id": "main"
}
}
那么可以按照以下的格式添加:
{
"openclaw_agent": {
"type": "RemoteAgent",
"description": "A openclaw agent.",
"tools": [],
"prompt": "The system prompt for the agent.",
"model_remote_configs": {
"model": "openclaw",
"url": "http://127.0.0.1:18789/v1/chat/completions",
"headers": {
"Authorization": f"Bearer {token}",
"Content-Type": "application/json",
"x-openclaw-agent-id": "main"
}
}
}
}
命令列表: /help —— 显示此帮助 /agents —— 查看可用的子智能体 /agent <agent_name> —— 设置当前会话的默认子智能体 /agent clear —— 取消当前会话的默认子智能体设置 其他文字 —— 与当前 session 的 AI 助手对话