Back to Skills

create-epic

majiayu000
Updated Today
1 views
58
9
58
View on GitHub
Metaaidata

About

This skill creates Epics using the T-Minus-15 process template for structuring large, multi-feature initiatives. It automatically generates comprehensive metadata including background, objectives, hypothesis, and delivery strategy sections. Use it when you need to draft a well-structured Epic document for significant product development work.

Quick Install

Claude Code

Recommended
Plugin CommandRecommended
/plugin add https://github.com/majiayu000/claude-skill-registry
Git CloneAlternative
git clone https://github.com/majiayu000/claude-skill-registry.git ~/.claude/skills/create-epic

Copy and paste this command in Claude Code to install this skill

Documentation

Create Epic Skill (T-Minus-15)

You are an expert Product Manager creating Epics following the T-Minus-15 process template. Epics are large bodies of work that contain multiple Features and represent significant business initiatives.

T-Minus-15 Epic Metadata

General Section

FieldDescriptionGuidance
TitleShort, descriptive nameInclude phase/version if applicable
StateWorkflow statusNew, Funnel, Validation, Proposing, Pending, Scheduled, Implementing
Epic TypeCategoryEpic, Initiative, Theme
OwnerResponsible personProduct Manager or Business Owner
AreaBusiness area/product lineHierarchical path (e.g., "Company > Division > Product")
Start DatePlanned startWhen work begins
Target End DateExpected completionDelivery target

Background & Objective Section

FieldWord CountDescription
Background50-200 wordsContext for delivery teams and sponsors. Why does this Epic exist? What problem does it solve?
Objective50-200 wordsConcise primary goal statement. What will be achieved?

Epic Hypothesis Section

FieldWord CountDescription
Value Statement30-200 wordsElevator pitch using format: FOR [target] WHO [need] THE [solution] IS A [category] THAT [benefit]
Business Outcome Hypothesis30-200 wordsHow success will be measured. What business outcomes are expected?
Leading Indicators30-200 wordsTangible, measurable indicators that predict success before outcomes are realized
Non-Functional Requirements30-200 wordsSystem operational characteristics: performance, security, reliability, availability, scalability

Analysis Section

FieldWord CountDescription
Impact: Products, Programs, Services30-200 wordsWhat existing solutions may be affected?
Impacted Users and Markets30-200 wordsWho will be affected? What markets?
Return30-200 wordsFinancial or other benefits expected
Anticipated Business Impact50-200 wordsExpected effects on operations, revenue, reputation

Delivery Strategy Section

FieldWord CountDescription
Funnel Entry DateDateWhen Epic entered the pipeline
In/Out-houseChoiceInternal development or external/vendor
Innovation Start-up25-200 wordsHypothesis about user outcomes. What do we believe will happen?
Pre-requisites50-200 wordsEssential requirements from customer, dependencies
Incremental Implementation Strategy50-200 wordsHow will Epic be delivered in stages?
Sequence and Dependencies50-200 wordsOrder of implementation, what depends on what
Milestones or Checkpoints100-300 wordsKey milestones, governance checkpoints, review gates
Other Notes0-300 wordsAdditional information, risks, constraints

Approval Section

FieldDescription
SponsorsKey stakeholders and financial backers
Go or No-GoFinal approval decision
Approved ByWho authorized
Approved DateWhen approved

Epic Description Template

## Background
[50-200 words: Context for why this Epic exists. What business problem does it solve? What is the current state?]

## Objective
[50-200 words: What will be achieved when this Epic is complete? What is the primary goal?]

---

## Epic Hypothesis

### Value Statement
FOR [target users/customers]
WHO [have this need/problem]
THE [solution name]
IS A [category/type of solution]
THAT [key benefit/value proposition]
UNLIKE [current alternatives]
OUR SOLUTION [key differentiator]

### Business Outcome Hypothesis
[30-200 words: How will we measure success? What business outcomes do we expect?]

### Leading Indicators
[30-200 words: What early signals will tell us we're on track?]
- [Indicator 1]
- [Indicator 2]
- [Indicator 3]

### Non-Functional Requirements
[30-200 words: Performance, security, reliability, scalability requirements]
- **Performance:** [Requirements]
- **Security:** [Requirements]
- **Reliability:** [Requirements]
- **Scalability:** [Requirements]

---

## Analysis

### Impact: Products, Programs, Services
[30-200 words: What existing systems/products will be affected?]

### Impacted Users and Markets
[30-200 words: Who will use this? What markets?]

### Return
[30-200 words: Expected financial or strategic benefits]

### Anticipated Business Impact
[50-200 words: How will this affect business operations?]

---

## Delivery Strategy

### Pre-requisites
[50-200 words: What must be in place before work can begin?]
- [ ] [Pre-requisite 1]
- [ ] [Pre-requisite 2]

### Incremental Implementation Strategy
[50-200 words: How will this be delivered in phases?]
1. **Phase 1:** [Description]
2. **Phase 2:** [Description]
3. **Phase 3:** [Description]

### Sequence and Dependencies
[50-200 words: What order must things happen?]

### Milestones or Checkpoints
[100-300 words: Key review points]
| Milestone | Description | Target Date |
|-----------|-------------|-------------|
| [M1] | [Description] | [Date] |
| [M2] | [Description] | [Date] |

---

## Features

| ID | Feature Name | Type | MoSCoW | Description |
|----|--------------|------|--------|-------------|
| F1 | [Name] | Feature/Enabler | Must/Should/Could | [Brief description] |
| F2 | [Name] | Feature/Enabler | Must/Should/Could | [Brief description] |

---

## Risks and Issues

| ID | Type | Description | Impact | Mitigation |
|----|------|-------------|--------|------------|
| R1 | Risk | [Description] | High/Med/Low | [Mitigation strategy] |
| I1 | Issue | [Description] | High/Med/Low | [Resolution plan] |

Example: BOM App Phase 2 Epic

## Background
Medite Smartply manufacturing requires efficient Bill of Materials management for their wood panel products. The existing Power App has served Phase 1 needs but requires migration to React for improved performance, maintainability, and developer experience. The current app handles Master Panel, Cut to Size, Tongue & Groove, and Coating BOMs with complex calculated fields.

## Objective
Rebuild the existing Power App as a modern React application with identical functionality and visual appearance. The new app must match all existing calculations exactly, integrate with the same SQL database and SysPro ERP, and provide a foundation for future enhancements.

---

## Epic Hypothesis

### Value Statement
FOR manufacturing engineers
WHO need efficient BOM management with accurate calculations
THE React BOM App
IS A modern web application
THAT provides responsive UI, real-time calculated fields, and SysPro integration
UNLIKE the current Power App
OUR SOLUTION offers improved performance, easier maintenance, and better developer experience

### Business Outcome Hypothesis
Success will be measured by: (1) Zero calculation discrepancies vs Power App, (2) Page load times under 2 seconds, (3) User adoption rate >90% within 30 days, (4) Reduced maintenance overhead for IT team.

### Leading Indicators
- Development velocity tracking (story points per sprint)
- Test coverage >80% for calculation engine
- User feedback during UAT sessions
- Performance benchmarks during development

### Non-Functional Requirements
- **Performance:** Page loads <2s, calculations <100ms
- **Security:** Azure AD authentication, role-based access
- **Reliability:** 99.9% uptime during business hours
- **Browser Support:** Chrome, Edge, Firefox (latest 2 versions)

---

## Features

| ID | Feature Name | Type | MoSCoW |
|----|--------------|------|--------|
| F1 | Enabler: Project Setup & Architecture | Enabler | Must Have |
| F2 | Enabler: Database Integration | Enabler | Must Have |
| F3 | Enabler: Calculated Fields Engine | Enabler | Must Have |
| F4 | React App - Home Screen | Feature | Must Have |
| F5 | React App - Master Panel CRUD | Feature | Must Have |
| F6 | React App - Cut to Size CRUD | Feature | Must Have |
| F7 | React App - Tongue & Groove CRUD | Feature | Must Have |
| F8 | React App - Coating CRUD | Feature | Must Have |

Workflow

  1. Define the business problem - What are we solving?
  2. Write Background - Context for the Epic (50-200 words)
  3. Write Objective - Primary goal (50-200 words)
  4. Craft Value Statement - Elevator pitch in standard format
  5. Define success measures - Business outcomes and leading indicators
  6. Specify NFRs - Performance, security, reliability
  7. Analyze impact - Products, users, markets affected
  8. Plan delivery - Phases, sequence, milestones
  9. List Features - Break Epic into Features
  10. Identify Risks - What could go wrong?

Tips

  • Epics are big - If it's less than 3-4 Features, it might just be a Feature
  • Time-bound - Epics should have target dates
  • Measurable outcomes - Define how you'll know it succeeded
  • Phase appropriately - Break large Epics into MVP + increments
  • Features not tasks - Epics contain Features, not Tasks or User Stories directly
  • Stakeholder alignment - Sponsors section ensures accountability

GitHub Repository

majiayu000/claude-skill-registry
Path: skills/create-epic

Related Skills

content-collections

Meta

This skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.

View skill

sglang

Meta

SGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.

View skill

evaluating-llms-harness

Testing

This Claude Skill runs the lm-evaluation-harness to benchmark LLMs across 60+ standardized academic tasks like MMLU and GSM8K. It's designed for developers to compare model quality, track training progress, or report academic results. The tool supports various backends including HuggingFace and vLLM models.

View skill

langchain

Meta

LangChain is a framework for building LLM applications using agents, chains, and RAG pipelines. It supports multiple LLM providers, offers 500+ integrations, and includes features like tool calling and memory management. Use it for rapid prototyping and deploying production systems like chatbots, autonomous agents, and question-answering services.

View skill