create-stories

Decompose epic specifications into traceable story files with TR-IDs.

1|Updated May 15, 2026
One-click install
npx skills add https://github.com/dnkrow/skill --skill create-stories-dnkrow
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: create-stories
Source: https://github.com/dnkrow/skill/tree/main/claude-global/create-stories
Command: npx skills add https://github.com/dnkrow/skill --skill create-stories-dnkrow

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It converts a large epic specification (GDD + governing ADRs + control manifest + TR registry) into a set of small, traceable, implementation-ready story documents that match acceptance criteria and architectural decisions.

Core Features & Use Cases

  • Epic-to-story decomposition: Groups GDD acceptance criteria into focused stories with correct ordering (foundational first, edge cases last, UI last).
  • Traceability by TR-IDs and ADR governance: Embeds the right TR requirement IDs and includes ADR decision summaries plus implementation guidance, stopping early if any governing ADR files are missing.
  • Review and QA gating: Runs a QA lead readiness gate in full mode, then requires concrete automated test specs for Logic/Integration stories (manual verification steps for Visual/Feel/UI) before proceeding.
  • Output organization: Writes production/epics/[epic-slug]/story-NNN-[slug].md files and updates the epic’s EPIC.md stories table.

Quick Start

Use create-stories on a foundation epic by running /create-stories <epic-slug> to generate all story markdown files for that epic in production/epics/.

Frequently Asked Questions about create-stories

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

FAQPage Schema
How do I decompose an epic specification into implementable stories?

Epic decomposition breaks a large epic specification into small, traceable story documents by grouping GDD acceptance criteria into focused Logic, Integration, Visual, UI, or Config stories with correct implementation ordering.

How does story decomposition handle requirements traceability?

Requirements traceability is maintained by embedding TR requirement IDs from the registry into each story document, ensuring end-to-end mapping from GDD acceptance criteria to implementation tasks.

Do I need ADR files to generate story documents from an epic?

ADR files are required to generate story documents. The process validates ADR file existence and stops early if any governing Architecture Decision Records are missing, incorporating ADR summaries into the stories.

What is the best way to enforce QA readiness gates during story generation?

QA readiness gates are enforced by running a QA lead gate in full mode, requiring concrete automated test specs for Logic and Integration stories, and manual verification steps for Visual or UI stories before proceeding.

Can I use Claude Code to automate epic-to-story decomposition for game design documents?

Claude Code can automate epic-to-story decomposition by loading GDD and epic markdown paths, assigning TR-IDs, spawning QA gates, and writing structured story markdown files plus an updated EPIC stories table.

What are the limitations of automated story decomposition for complex epics?

Automated story decomposition requires complete inputs including GDD, ADRs, control manifest, and TR registry. It halts if governing ADR files are missing and mandates specific test specs or manual verification steps before completing.