User Story Splitting

Takes a bloated epic or story and runs it through eight splitting patterns to break it down into shippable increments. Based on the Humanizing Work framework, it walks you through workflow steps, business rule variations, data types, acceptance criteria, and a few others until something clicks. The best part is the anti-pattern warnings: it won't let you split horizontally into frontend and backend stories, which is the amateur move everyone makes. When you've got a story with five different "When/Then" scenarios or an epic that won't fit in a sprint, this gives you a systematic way to decompose it without losing user value. Pattern four on acceptance criteria complexity is probably where you'll land most often.

skills.sh installs: 2.6K
GitHub stars: 7.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add deanpeters/product-manager-skills --skill user-story-splitting --agent claude-code

Installs into .claude/skills of the current project.

Files

Purpose

Break down large user stories, epics, or features into smaller, independently deliverable stories using systematic splitting patterns. Use this to make work more manageable, reduce risk, enable faster feedback cycles, and maintain flow in agile development. This skill applies to user stories, epics, and any work that's too large to complete in a single sprint.

This is not arbitrary slicing—it's strategic decomposition that preserves user value while reducing complexity.

Input

Works best with: The story or epic that's too big — paste it as written. Also useful: Why it's too big (can't estimate, can't finish in a sprint, can't release independently) and your team's sizing ceiling.

Anything supplied with the invocation itself — text after the skill name, a pasted context dump, or an appended ARGUMENTS: line — counts as answers already given. Use it and skip whatever it covers; don't re-ask.

Arriving empty-handed? That works too. The skill asks for the story text, then walks the split patterns against it.

SKILL.md on GitHub