bmad-create-story

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

Updated Jul 2, 2026
One-click install
npx skills add https://github.com/tuanpa-nhg-eng/nhg-ipms --skill bmad-create-story-tuanpa-nhg-eng
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: bmad-create-story
Source: https://github.com/tuanpa-nhg-eng/nhg-ipms/tree/main/.claude/skills/bmad-create-story
Command: npx skills add https://github.com/tuanpa-nhg-eng/nhg-ipms --skill bmad-create-story-tuanpa-nhg-eng

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Developer agents often fail because story files lack context: wrong libraries, wrong file locations, missed regressions, and vague acceptance criteria. This Skill creates a complete, context-rich story file that gives the dev agent everything needed for correct implementation. ## Core Features & Use Cases - Story Auto-Discovery: Reads sprint-status.yaml to find the next backlog story, or accepts an explicit epic-story number like "1-2-user-auth". - Exhaustive Artifact Analysis: Loads epics, PRD, architecture, and UX documents (whole or sharded) plus previous story learnings and recent git history to build developer guardrails. - Quality Validation Checklist: Validates the generated story against a competitive review checklist that catches critical omissions before handoff, then updates sprint status to ready-for-dev. - Use Case: After sprint planning, run this workflow to turn the next backlog story into a fully-contextualized implementation guide with architecture compliance rules, library versions, and testing requirements. ## Quick Start Ask the agent to create the next story from the sprint backlog, or specify one directly such as "create story 2-4".

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 a developer story from sprint backlog?

Run the workflow with no arguments to auto-discover the first backlog story in sprint-status.yaml, or provide an explicit epic-story number like "1-2-user-auth". The skill loads planning artifacts and writes a complete story file marked ready-for-dev.

What inputs does the create-story workflow need?

It reads sprint-status.yaml plus planning artifacts: epics, PRD, architecture, and UX documents, supporting both whole files and sharded directories. It also loads the previous story in the epic and recent git commits for continuity.

Can I customize the story creation workflow?

Yes, customize.toml supports activation step prepends/appends, persistent facts loaded from files, and an on_complete hook. Team and user-level TOML overrides merge with defaults using structural merge rules.

Why does story creation fail with no backlog stories found?

This happens when sprint-status.yaml has no story keys with status "backlog". Run sprint-planning to refresh tracking, add stories via correct-course, or check whether the current sprint is complete.

Is bmad-create-story deprecated?

Yes, the frontmatter marks it deprecated: bmad-build is now the official implementation method. Only use this skill when explicitly invoked by name.