Dummy Dataset Generator Skill for Codex
Generate synthetic development or demo data with defined fields, row counts, and business constraints. It can produce CSV or JSON files or a generator you can run again.
中文Install in Codex
Use a Codex environment that can discover project skills. The example can be tested in a local project.
- In a temporary directory, run git clone https://github.com/bssm-oss/pm-skills-codex.git. Enter the clone, run git checkout --detach 9f19e3ff563a1cb4024cfb9a290d6002607b9dc9, and review the pinned SKILL.md.
- Copy the entire pm-execution/skills/dummy-dataset folder to .agents/skills/dummy-dataset in your own project, keeping its scripts, templates, and references together.
- Open Codex in that project. Choose the skill with /skills or mention $dummy-dataset, then run the example below. Restart Codex if the list does not refresh.
Example task
Request a 12-row fictional equipment CSV with a unique asset_id, a status of active or retired, purchase_date, and retired_date. Use YYYY-MM-DD for both date columns. Only retired records may include retired_date.What to check
The CSV has a header and 12 rows with distinct IDs. Status stays within the two allowed values, active rows have no retired date, and all dates parse in the chosen format.
Original SKILL.md on GitHub · Updated
Frequently asked question
How do I validate synthetic data against business rules?
Check individual column types and allowed values, then test cross-field constraints. Ask for a fixed random seed if you need to regenerate the same dataset.