Do agent
Skill brycewang-stanford/Auto-Empirical-Research-Skills/skills/67-econfin-workflow-toolkit/do-agent
🔬 A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | 精选 23,000+ AI Agent 技能库,覆盖8大社会科学学科的实证研究。CoPaper.AI 20分钟完成一篇可复现的规范实证论文,并支持用户上传 Skills。-- Maintained by CoPaper.AI from Stanford REAP.
npx -y skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill do-agentAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
What its author says it does
Copied from the file, not written here
This skill should be used when the user asks to "/do-agent", asks for "Execute complex tasks using multi-agent architecture with context protection", or needs the workflow previously provided by the /do-agent slash command.
SKILL.md
1.9 KB, as published. Nobody here has run it
Explore and ultrathink to design a systematic multi-agent, multi-stage (up to 10 subagents in parallel in each stage) execution plan to accomplish: $ARGUMENTS
执行模式:explore → ultrathink → plan → track → execute → review → revise → deliver final output
Note:
- Get the current Date and Time (Beijing time)
- 创建临时工作目录
agent_tasks/{short task description}_yyyyddmmhh/作为临时工作空间(if a folder with this name already exists, make a new one to avoid overwriting existing materals) - When assigning tasks to subagents, specify their input and output files explicitly
- 每个子代理必须自己将处理结果立即保存到本地文件,不要返回给主代理!子代理自己马上保存,不要返回给主代理!
- 严禁将子代理完整输出返回主代理;只返回状态摘要
- 第一个本地输出文件:multi-agent execution plan 文档
agent_tasks/{short task description}_yyyyddmmhh/plan.md - The main/mother agent must allow all Read + Write + Bash tools for all sub-agents
- Apply context engineering — main agent context is scarce
- The execution plan must include (at minimum) these four phases, each with multiple agents (in parallel when possible):
- 规划阶段:信息收集与方案规划
- 实施阶段:执行与整合任务结果
- 对任务结果进行审阅与反馈
- 根据审阅反馈,对任务结果进行全面修订
- Do not ask for plan approval, just set up the tasks tracking and do it once the planning phase finished
- Complete automation of the entire process, from planning to execution to review and revision, without any human intervention