OpenParable
Skip to content
← Back to skills

Stata Run

Apps & Automation
stata-run

Stata Run is an Agent Skill for apps & automation published in the brycewang-stanford/Auto-Empirical-Research-Skills repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Run arbitrary Stata code or a .do file and display the result.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/blob/HEAD/skills/64-tmonk-mcp-stata/skills/stata-run/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/stata-run, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

The argument is the Stata code or absolute path to a .do file to execute.

  1. 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)
    
  2. 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>.

  3. 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.

  4. 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'.