bmad-create-story

Generates developer-ready story files from epics, architecture, and sprint status artifacts.

Updated May 7, 2026
One-click install
npx skills add https://github.com/jgabriellima/deep-agent-skill --skill bmad-create-story-jgabriellima
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: bmad-create-story
Source: https://github.com/jgabriellima/deep-agent-skill/tree/main/skills/bmad-create-story
Command: npx skills add https://github.com/jgabriellima/deep-agent-skill --skill bmad-create-story-jgabriellima

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Development agents often fail because stories lack context: wrong libraries, wrong file locations, broken regressions, and vague acceptance criteria. This Skill creates a comprehensive story file that gives the dev agent everything needed for correct implementation, preventing common LLM developer mistakes. ## Core Features & Use Cases - Automatic Story Discovery: Reads sprint-status.yaml to find the next backlog story, or accepts an explicit epic-story identifier like "1-2-user-auth". - Exhaustive Context Analysis: Loads and analyzes epics, PRD, architecture, and UX documents plus previous story learnings and git history to build complete developer guardrails. - Quality Validation: Validates the generated story against a checklist that hunts for missing requirements, regression risks, and LLM-optimization issues before finalizing. - Use Case: After sprint planning, ask the agent to create the next story; it auto-selects the first backlog story, analyzes all planning artifacts, and writes a ready-for-dev story file with architecture compliance rules, testing requirements, and file structure guidance. ## Quick Start Ask the agent to create the next story from the sprint backlog, for example by saying "create the next story" or "create story 1-2-user-auth".

Frequently Asked Questions about bmad-create-story

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

FAQPage Schema
How do I create the next story from my sprint backlog?▼

Run the create-story workflow with no arguments and it reads sprint-status.yaml to find the first story with backlog status. It then analyzes your epics, architecture, and previous stories to generate a complete story file marked ready-for-dev.

How do I create a specific story by epic and story number?▼

Provide the story identifier directly, such as "create story 1-2-user-auth" or "2-4". The workflow parses the epic number, story number, and title from your input and skips the auto-discovery step.

What input documents does the create-story workflow need?▼

It loads epics, PRD, architecture, and UX documents from your planning artifacts directory, supporting both whole files and sharded folders. The epics file is the primary source; PRD and architecture serve as fallbacks and guardrail references.

What happens if no sprint-status.yaml file exists?▼

The workflow halts and asks you to either run sprint-planning first to initialize tracking, provide a specific epic-story number, or supply a path to story documents. It will not proceed without a target story.

Does the workflow update sprint status after creating a story?▼

Yes. After saving the story file, it updates the story's status from backlog to ready-for-dev in sprint-status.yaml, refreshes the last_updated field, and marks the parent epic as in-progress when its first story is created.

How does the story file prevent developer agent mistakes?▼

The generated story includes architecture compliance rules, library and version requirements, file structure guidance, testing standards, previous story learnings, and git history insights. A final checklist validation pass catches missing requirements before the story is finalized.