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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills --skill stata-run命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | stata-run |
| description | Run arbitrary Stata code or a .do file and display the result. |
The argument is the Stata code or absolute path to a .do file to execute.
If the argument ends in .do or .ado, call:
stata_run(code=<argument>, is_file=True, echo=True, as_json=True)
Otherwise call:
stata_run(code=<argument>, echo=True, as_json=True)
If success is true, display the stdout output. Note the output is truncated to 5,000 chars; if the response includes a log_path, offer to tail the full log with /stata-log <log_path>.
If success is false, display the error message and rc code. Suggest using /stata-lint <path> for syntax issues or /stata-help <command> for documentation.
If the command produces graphs, note that /stata-graph can export them.
If using background mode (background=True): you may do other work or fire parallel tasks, but you MUST call stata_task_status(task_id=<id>, wait=True, timeout=<N>, tail_lines=<M>) for every task before returning to the user. Set timeout to match expected runtime; set tail_lines to how much output you want inline vs. reading separately via stata_read_log. Loop on timeout until status is 'done' or 'failed'.