dummy-dataset

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.

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./pm-execution/skills/dummy-dataset/SKILL.md

Quality

Content

50%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is reasonably organized and offers a usable template plus a concrete example spec, but it is held back by a skeletal, placeholder-laden code template, abstract validation with no feedback loop, and some redundant explanation. It is competent but not yet lean or fully executable.

Suggestions

Replace the placeholder comments in generate_dataset() with concrete value generators (names, emails, timestamps, ratings) so the template is copy-paste executable.

Turn step 8 into an explicit validation checkpoint with a feedback loop — e.g., run a check script, report failing rows, fix constraints, and re-run until clean — instead of 'Ensure data quality and completeness'.

Trim explanation Claude already knows (the CSV/JSON/SQL/Python format blurbs) and remove the restated 8-step list or fold it into the template to reduce redundancy.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient but includes explanation Claude already knows (e.g., 'CSV: Flat tabular format, easy to import into spreadsheets and databases') and an 8-step list that largely restates the description, so it could be tightened.	3 / 5
Actionability	A concrete Python template and example spec are provided, but the template is a skeleton with placeholder comments ('# Add more columns...', '# Generate values based on column definitions') rather than fully executable value generators, leaving key details incomplete.	3 / 5
Workflow Clarity	An 8-step sequence is present and step 8 names validation, but for a batch data-generation operation the validation is described abstractly ('Ensure data quality and completeness') with no concrete validate→fix→retry feedback loop, capping clarity at 3.	3 / 5
Progressive Disclosure	Sections are organized with clear headers, but with no bundle files present the ~115-line body inlines content (full template, output-format descriptions) that is reasonably structured yet could be better separated; it sits between minimal and good structure.	3 / 5
	Total	12 / 20 Passed

Description

88%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that cleanly answers both what the skill does and when to use it, with concrete output formats and natural trigger synonyms. The only gaps are a few missing keyword variations and minor overlap risk with general data tools.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions and outputs — 'Generate realistic dummy datasets' with 'customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script)' — giving comprehensive coverage of capabilities.	5 / 5
Completeness	It explicitly states both what ('Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats') and when ('Use when creating test data, building mock datasets, or generating sample data for development and demos') with concrete trigger phrases.	5 / 5
Trigger Term Quality	It includes natural user phrases ('test data', 'mock datasets', 'sample data', 'development', 'demos') with useful synonym coverage, but misses some common variations a user might say such as file extensions or 'fake data'.	4 / 5
Distinctiveness Conflict Risk	The niche (dummy/test dataset generation across named formats) is mostly distinct with clear triggers, with only minor overlap risk against general data-handling skills.	4 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: phuryn/pm-skills
Path: pm-execution/skills/dummy-dataset/SKILL.md
Commit: 18468a9

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.