ds-plan

Generates editable, traceable plans for Kubernetes-based AI projects.

19|5|Updated Jan 4, 2026
One-click install
npx skills add https://github.com/edwinhu/workflows --skill ds-plan
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ds-plan
Source: https://github.com/edwinhu/workflows/tree/main/lib/skills/ds-plan
Command: npx skills add https://github.com/edwinhu/workflows --skill ds-plan

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill addresses the critical need for structured data profiling and task breakdown in data science workflows, preventing common pitfalls like starting analysis without understanding the data or creating vague, unexecutable plans.

Core Features & Use Cases

  • Data Profiling: Comprehensive checks on data shape, types, missing values, duplicates, and distributions.
  • Task Breakdown: Generates an ordered list of actionable analysis tasks.
  • ETL Strategy Assessment: Guides decisions on filtering, parallelism, caching, and incremental scaling for efficient data processing.
  • Use Case: Before starting a complex data analysis project, use this Skill to thoroughly profile your datasets, identify potential data quality issues, and create a detailed, step-by-step plan for cleaning, transformation, and analysis, ensuring a robust and efficient workflow.

Quick Start

Use the ds-plan skill to profile the data and create an analysis plan based on the spec.

Frequently Asked Questions about ds-plan

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a data science analysis plan before starting a project?

Data profiling checks assess data shape, types, missing values, duplicates, and distributions to identify data quality issues. This mechanism prevents starting analysis without understanding the data and avoids creating vague, unexecutable plans.

How do I assess ETL strategies for efficient data processing?

Assess ETL strategies by evaluating filter push-down, parallelism, intermediate caching, and incremental scale-up. This guides decisions on filtering and scaling to ensure an efficient data processing workflow for your analysis tasks.

What is the best way to profile datasets and identify data quality issues?

The best way to profile datasets is performing comprehensive checks on data shape, types, missing values, duplicates, and distributions. This approach identifies potential data quality issues and creates a robust, step-by-step cleaning and transformation plan.

Can I generate an ASCII flowchart for my data analysis task breakdown?

When your data science analysis plan not working is caused by vague tasks, task breakdown generates an ordered list of actionable analysis tasks. This prevents common pitfalls by ensuring a robust, executable workflow for cleaning, transformation, and analysis.