How do the clarifying questions work?

The skill asks 3-5 essential questions one at a time to determine success metrics, data availability, and constraints before generating the document.

Is this skill tied to a specific ML framework?

No, it is stack-agnostic and focuses on the logic and requirements of the ML task rather than specific implementation code.

Where is the generated PRD stored?

PRDs are automatically saved as Markdown files in the 'tasks/' directory with a naming convention of 'prd-[feature-name].md'.

ML-Ralph is a specialized ML development agent pattern that uses these PRDs to iteratively build and refine models based on logged evidence.

What makes this different from a standard PRD?

This PRD is specifically designed for Machine Learning, focusing on data context, evaluation strategies (like stratified or time-based splits), leakage prevention, and hypothesis-driven user stories.

ML PRD Generator

Name: ML PRD Generator
Author: JoaquinCampo

byJoaquinCampo

Data Science & ML

Generates structured, evidence-driven Product Requirements Documents (PRDs) specifically tailored for Machine Learning workflows and experiments.

About

The ML PRD Generator skill streamlines the planning phase of machine learning projects by enforcing an evidence-driven approach before any code is written. It guides users through a series of essential clarifying questions regarding objectives, data context, and evaluation metrics to ensure a robust foundation. The skill produces a comprehensive, stack-agnostic PRD that includes ML-centric user stories, success metrics, and evaluation plans, saving the output directly to your tasks directory for immediate use by agents like ML-Ralph.

Key Features

0 GitHub stars
Automated file generation in kebab-case format within the tasks/ directory
Standardized ML PRD structure including evaluation plans and leakage rules
ML-centric user stories with hypotheses and logging requirements
Evidence-driven framework compatible with ML-Ralph dynamic backlogs
Interactive clarifying question phase to define project scope and constraints

Use Cases

Creating a structured experiment plan before starting data exploration
Defining the scope and metrics for a new regression or classification model
Standardizing documentation for ML features within a collaborative team

About

Key Features

0 GitHub stars
Automated file generation in kebab-case format within the tasks/ directory
Standardized ML PRD structure including evaluation plans and leakage rules
ML-centric user stories with hypotheses and logging requirements
Evidence-driven framework compatible with ML-Ralph dynamic backlogs
Interactive clarifying question phase to define project scope and constraints

Use Cases

Creating a structured experiment plan before starting data exploration
Defining the scope and metrics for a new regression or classification model
Standardizing documentation for ML features within a collaborative team