create-epics

Name: create-epics
Availability: InStock
Author: easonlao

Generate bounded epic definitions per architectural module from approved GDDs and ADRs.

Updated Apr 25, 2026

Search Tags:#epics #requirements coverage #project governance #gdd #production planning #adr traceability #architecture-module mapping

Ready to run

npx skills add https://github.com/easonlao/jiazi-game --skill create-epics-easonlao

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: create-epics
Source: https://github.com/easonlao/jiazi-game/tree/main/.claude/skills/create-epics
Command: npx skills add https://github.com/easonlao/jiazi-game --skill create-epics-easonlao

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps teams convert approved GDDs and architecture decisions into clear, bounded epic definitions so engineering scope is aligned before story breakdown begins.

Core Features & Use Cases

Layer- and system-aware epic creation: Creates one epic per architectural module with in-scope filtering by layer (foundation/core/feature/presentation) or a specific system name.
ADR-governed scope mapping: Determines governing ADRs and engine risk by cross-referencing ADR domains with the TR registry and engine reference metadata.
Traceability guardrails: Detects untraced requirements (TR-IDs without Accepted ADR coverage) and blocks or warns prior to writing, while guiding the next steps to run /architecture-decision or proceed with placeholders.

Quick Start

Run create-epics with your target scope by typing: /create-epics layer: core.

Frequently Asked Questions about create-epics

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

FAQPage Schema

How do I create bounded epics from approved GDDs and architecture documentation?▼

You create bounded epics by parsing GDD summaries and loading in-scope ADRs, architecture metadata, and TR registries. The process maps each architectural module to an epic with ADR coverage validation, writing EPIC.md files without creating stories.

What is ADR traceability for epic scope mapping?▼

ADR traceability cross-references ADR domains with the TR registry and engine metadata to determine governing ADRs for each epic. It detects untraced requirements lacking Accepted ADR coverage, blocking or warning before writing EPIC.md files.

Can I filter epic creation by architectural layer or specific system name?▼

Yes, you can filter epic creation by specific architectural layer or system name. The workflow supports in-scope filtering across foundation, core, feature, and presentation layers, generating one bounded epic per matching architectural module.

How do I handle untraced technical requirements when generating epics?▼

When generating epics, untraced technical requirements are identified by validating TR-IDs against Accepted ADR coverage. The workflow blocks or warns prior to writing, guiding you to run architecture-decision or proceed using placeholders.

What is the best way to structure epic definitions for production planning workflows?▼

The best way to structure epic definitions for production planning is generating one bounded epic per architectural module across foundation, core, feature, and presentation layers. This aligns engineering scope before story decomposition begins.

Why does epic generation stop before creating user stories?▼

Epic generation stops before creating user stories to enforce separation between scope definition and story decomposition. It writes EPIC.md and index.md files only, ensuring architectural module boundaries and ADR governance are validated before story breakdown.