Jira Epic logo

Jira Epic

Organization
Gentleman-Programming
jira-epic

Creates Jira epics for large features following Prowler's standard format. Trigger: When user asks to create an epic, large feature, or multi-task initiative.

Overview

PublisherGentleman-Programming
RepositoryGentleman-Skills
Skill namejira-epic
Stars
658
Forks
98
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Gentleman-Programming on GitHub. Read the source before you install it.

Installation

Install the Jira Epic AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Gentleman-Programming/Gentleman-Skills/tree/main/curated/jira-epic
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Gentleman-Programming/Gentleman-Skills.git /tmp/Gentleman-Skills
mkdir -p .claude/skills
cp -r /tmp/Gentleman-Skills/curated/jira-epic .claude/skills/jira-epic
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Jira Epic in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Jira Epic on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Jira Epic is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

When to Use

Use this skill when creating Jira epics for:

  • Large features spanning multiple components
  • New views/pages in the application
  • Major refactoring initiatives
  • Features requiring API + UI + SDK work

Epic Template

markdown
# {Epic Title}

**Figma:** {figma link if available}

## Feature Overview

{2-3 paragraph description of what this feature does and why it's needed}

## Requirements

### {Section 1: Major Functionality Area}

#### {Subsection}
- Requirement 1
- Requirement 2
- Requirement 3

#### {Another Subsection}
- Requirement 1
- Requirement 2

### {Section 2: Another Major Area}

#### {Subsection}
- Requirement 1
- Requirement 2

## Technical Considerations

### Performance
- {Performance requirement 1}
- {Performance requirement 2}

### Data Integration
- {Data source}
- {Integration points}

### UI Components
- {Component 1}
- {Component 2}

## Implementation Checklist

- [ ] {Major deliverable 1}
- [ ] {Major deliverable 2}
- [ ] {Major deliverable 3}

## Diagrams

{Mermaid diagrams for architecture, flow, data model, etc.}

Epic Title Conventions

Format: [EPIC] Feature Name

Examples:

  • [EPIC] Findings View
  • [EPIC] Multi-tenant Support
  • [EPIC] Compliance Dashboard Redesign
  • [EPIC] GovCloud Support

Required Sections

1. Feature Overview

Brief but complete description of:

  • What the feature does
  • Who uses it
  • Why it's needed

2. Requirements

Organized by functional area:

  • Group related requirements together
  • Use clear headers and subheaders
  • Be specific and testable

3. Technical Considerations

Always include:

  • Performance: Large dataset handling, pagination, caching
  • Data Integration: Data sources, APIs, relationships
  • UI Components: Reusable components, design system usage

4. Implementation Checklist

High-level deliverables that will become individual tasks:

  • Each checkbox = potential Jira task
  • Order by dependency (API before UI)
  • Include testing milestones

Diagrams

Use Mermaid for:

Architecture Diagrams

Data Flow Diagrams

State Diagrams

Entity Relationship Diagrams

Splitting Epic into Tasks

After creating the epic, generate individual tasks using the jira-task skill:

Task Naming Pattern

From epic [EPIC] Findings View, create:

  • [FEATURE] Findings table with pagination (UI)
  • [FEATURE] Findings filters - provider and account (UI)
  • [FEATURE] Findings detail panel - Overview tab (UI)
  • [FEATURE] Findings detail panel - Resources tab (UI)
  • [FEATURE] Findings bulk actions - mute/suppress (API + UI)
  • [FEATURE] Findings search functionality (API + UI)

Task Dependencies

Always specify in each task:

markdown
## Related Tasks
- Epic: [EPIC] Findings View
- Blocked by: [task if any]
- Blocks: [task if any]

Figma Integration

When Figma links are provided:

  • Include main Figma link at top
  • Reference specific frames in relevant sections
  • Example: https://www.figma.com/design/xxx?node-id=1830-44712&m=dev

Output Format

markdown
## Epic: [EPIC] {Title}

{Full epic content following template}

---

## Suggested Tasks

Based on this epic, create the following tasks:

| # | Title | Component | Blocked By |
|---|-------|-----------|------------|
| 1 | [FEATURE] Task name | API | - |
| 2 | [FEATURE] Task name | UI | Task 1 |
| 3 | [FEATURE] Task name | UI | Task 2 |

Would you like me to generate the full task descriptions?

Checklist Before Submitting

  1. ✅ Title follows [EPIC] Feature Name format
  2. ✅ Feature Overview explains what/who/why
  3. ✅ Requirements are organized by functional area
  4. ✅ Technical Considerations cover performance, data, UI
  5. ✅ Implementation Checklist has high-level deliverables
  6. ✅ Diagrams included where helpful (Mermaid format)
  7. ✅ Figma links included if available
  8. ✅ Suggested tasks table provided at the end

Formatting Rules

CRITICAL: All output MUST be in Markdown format, ready to paste into Jira.

  • Use # for epic title, ## for main sections, ### for subsections
  • Use **bold** for emphasis
  • Use - [ ] for checkboxes in Implementation Checklist
  • Use ``` for code blocks and Mermaid diagrams
  • Use backticks for file paths, commands, and code references
  • Use tables for Suggested Tasks section
  • Use --- to separate epic from suggested tasks

Jira MCP Integration

CRITICAL: When creating epics via MCP, use these exact parameters:

Required Fields

json
{
  "project_key": "PROWLER",
  "summary": "[EPIC] Feature name",
  "issue_type": "Epic",
  "additional_fields": {
    "customfield_10359": {"value": "UI"}
  }
}

Team Field (REQUIRED)

The customfield_10359 (Team) field is REQUIRED. Options:

  • "UI" - Frontend epics
  • "API" - Backend epics
  • "SDK" - Prowler SDK epics

Work Item Description Field

IMPORTANT: The project uses customfield_10363 (Work Item Description) instead of the standard description field for display in the UI.

CRITICAL: Use Jira Wiki markup, NOT Markdown:

  • h2. instead of ##
  • *text* for bold instead of **text**
  • * item for bullets (same)
  • ** subitem for nested bullets

After creating the epic, update the description with:

json
{
  "customfield_10363": "h2. Feature Overview\n\n{overview}\n\nh2. Requirements\n\n*{Section 1}*\n* {requirement 1}\n* {requirement 2}\n\n*{Section 2}*\n* {requirement 1}\n* {requirement 2}\n\nh2. Technical Considerations\n\n*Performance:*\n* {consideration 1}\n\n*Data Integration:*\n* {consideration 2}\n\nh2. Implementation Checklist\n\n* [ ] {deliverable 1}\n* [ ] {deliverable 2}\n* [ ] {deliverable 3}"
}

Linking Tasks to Epic

When creating child tasks, use the epic key as parent:

json
{
  "additional_fields": {
    "parent": "PROWLER-XXX"
  }
}

Workflow Transitions

Backlog (10037) → To Do (14) → In Progress (11) → Done (21)
                → Blocked (10)

MCP Commands Sequence

  1. Create epic:
mcp__mcp-atlassian__jira_create_issue (issue_type: "Epic")
  1. Update Work Item Description:
mcp__mcp-atlassian__jira_update_issue with customfield_10363
  1. Create child tasks:
mcp__mcp-atlassian__jira_create_issue with parent: EPIC-KEY
  1. Assign and transition:
mcp__mcp-atlassian__jira_update_issue (assignee)
mcp__mcp-atlassian__jira_transition_issue (status)

Keywords

jira, epic, feature, initiative, prowler, large feature

Frequently asked questions

What does the Jira Epic AI skill do?

Creates Jira epics for large features following Prowler's standard format. Trigger: When user asks to create an epic, large feature, or multi-task initiative.

Why use Jira Epic on TypingMind?

Because you install it once and use it with any model. Jira Epic is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Jira Epic in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Gentleman-Programming/Gentleman-Skills/tree/main/curated/jira-epic. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Jira Epic?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Jira Epic?

As many as you like. As long as a model supports skills, you can use Jira Epic with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Jira Epic AI skill free?

Yes. It is published on GitHub by Gentleman-Programming under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇