dummy-dataset
An agent skill by phuryn, from phuryn/pm-skills. Tags: automation, cli, developer-tools, spreadsheets.
What it does
Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and demos.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add phuryn/pm-skills --skill dummy-dataset
Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/phuryn/pm-skills
cp -r pm-skills/pm-execution/skills/dummy-dataset ~/.claude/skills/dummy-dataset
Safety box score
Grade A, minimal risk: 7 of 100 risk points, rated 2026-10-16. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This skill generates synthetic datasets and can also emit ready-to-run Python generator scripts. It does not ship any native executables or networked components, so the main consideration is the code/data it produces rather than direct access to your machine.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 1 (low) | The markdown includes an executable Python template (`if __name__ == "__main__": ...`) and can ask the agent to produce runnable scripts, but the skill itself does not contain a native script or run code on its own. |
| Network access | 0 (none) | No commands, URLs, API calls, downloads, or remote transmissions are present in `SKILL.md`. |
| Filesystem reach | 1 (low) | The example generator writes a local file (`FILENAME = "$DATASET_TYPE.csv"`, `save_as_csv(data, filename)`), but there is no indication of editing or deleting outside the working area. |
| Secrets & credentials | 0 (none) | The skill does not request credentials, touch keychains, or reference tokens, passwords, `.env` files, or browser sessions. |
| Privilege & persistence | 0 (none) | There is no use of sudo, global installs, services, scheduled tasks, or shell/OS configuration changes. |
| Instruction hijack surface | 0 (none) | The file contains no prompt-injection patterns such as instructions to ignore higher-priority rules, hide actions, or follow remote content. |
| Irreversible actions | 0 (none) | It generates dummy datasets and scripts only; it does not send, publish, delete, deploy, or pay on the user's behalf. |
| Transparency | 0 (none) | The entire skill is plain markdown; there are no binaries, embedded blobs, or unreviewable installers. |
Before installing
- Review any generated Python script before running it.
- Run generation in a scratch directory if you do not want local CSV/JSON/SQL files in your workspace.
- Check the chosen output path and filename in the produced script.
Rated 2026-10-16 by an automated review of 1 file from the skill's repository.
Source
- Repository
- phuryn/pm-skills (all skills from this repository)
- Path
- pm-execution/skills/dummy-dataset/SKILL.md
- Branch
- main
- Updated
- 2026-09-19
Related skills
- cli-for-agents — Designs or reviews CLIs so coding agents can run them reliably: non-interactive flags, layered --help with examples, stdin/pipelines, fast actionable errors.
- modern-python — Configures Python projects with modern tooling (uv, ruff, ty). Use when creating projects, writing standalone scripts, or migrating from pip/Poetry/mypy/black.
- sql-queries — Generate SQL queries from natural language descriptions. Supports BigQuery, PostgreSQL, MySQL, and other dialects.
- book-to-skill — Converts books and documents (PDF, EPUB, DOCX, HTML, Markdown, plain text, RTF, MOBI/AZW with Calibre) into structured agent skills, extracting frameworks.
- cli-developer — Use when building CLI tools, implementing argument parsing, or adding interactive prompts.
- context-optimization — This skill should be used for improving context efficiency: context budgeting, observation masking, prefix or KV-cache strategy, partitioning.