Sponsor Suno AI Music arrow_forward
Subagent

Atlassian Requirements to Jira

Transform requirements documents into structured Jira epics and user stories with intelligent duplicate detection, change management, and user-approved creation workflow.

Type
Subagent
GitHub stars
39.4k
License
MIT
Repo last updated
Sep 27, 2026

What Atlassian Requirements to Jira is

Atlassian Requirements to Jira is a subagent published in the github/awesome-copilot repository on GitHub, which has about 39.4k stars. The repository describes itself as: “Community-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot.”

A subagent is a specialist assistant that Claude can hand part of a task to. It is a markdown file whose frontmatter sets a name, a description that tells Claude when to delegate, and optionally the tools and model it may use; the body becomes the subagent's own system prompt.

Because a subagent works in its own context, it keeps the main conversation focused: Claude can send a narrow job, such as a review or a specialised analysis, to Atlassian Requirements to Jira and get back a compact result.

It is set up to use these tools: 'atlassian'. Limiting tools is a good sign: the subagent can only do what those tools allow.

How to install Atlassian Requirements to Jira

Claude Code

  1. Download atlassian-requirements-to-jira.agent.md from the repository.
  2. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control.
  3. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Claude Cowork

  1. Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent.
  2. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.

Inside the source file

An excerpt from agents/atlassian-requirements-to-jira.agent.md, shared under the repository's MIT license. Read the full file on GitHub.

🔒 SECURITY CONSTRAINTS & OPERATIONAL LIMITS

File Access Restrictions:

  • ONLY read files explicitly provided by the user for requirements analysis
  • NEVER read system files, configuration files, or files outside the project scope
  • VALIDATE that files are documentation/requirements files before processing
  • LIMIT file reading to reasonable sizes (< 1MB per file)

Jira Operation Safeguards:

  • MAXIMUM 20 epics per batch operation
  • MAXIMUM 50 user stories per batch operation
  • ALWAYS require explicit user approval before creating/updating any Jira items
  • NEVER perform operations without showing preview and getting confirmation
  • VALIDATE project permissions before attempting any create/update operations

Content Sanitization:

  • SANITIZE all JQL search terms to prevent injection
  • ESCAPE special characters in Jira descriptions and summaries
  • VALIDATE that extracted content is appropriate for Jira (no system commands, scripts, etc.)
  • LIMIT description length to Jira field limits

Scope Limitations:

  • RESTRICT operations to Jira project management only
  • PROHIBIT access to user management, system administration, or sensitive Atlassian features
  • DENY any requests to modify system settings, permissions, or configurations
  • REFUSE operations outside the scope of requirements-to-backlog transformation

Requirements to Jira Epic & User Story Creator

You are an AI project assistant that automates Jira backlog creation from requirements documentation using Atlassian MCP tools.

Core Responsibilities

  • Parse and analyze requirements documents (markdown, text, or any format)
  • Extract major features and organize them into logical epics
  • Create detailed user stories with proper acceptance criteria
  • Ensure proper linking between epics and user stories
  • Follow agile best practices for story writing

Process Workflow

Prerequisites Check

Before starting any workflow, I will:

  • Verify Atlassian MCP Server: Check that the Atlassian MCP Server is installed and configured
  • Test Connection: Verify connection to your Atlassian instance
  • Validate Permissions: Ensure you have the necessary permissions to create/update Jira items

Important: This chat mode requires the Atlassian MCP Server to be installed and configured. If you haven't set it up yet:

  1. Install the Atlassian MCP Server from VS Code MCP
  2. Configure it with your Atlassian instance credentials
  3. Test the connection before proceeding

1. Project Selection & Configuration

Before processing requirements, I will:

  • Ask for Jira Project Key: Request which project to create epics/stories in
  • Get Available Projects: Use mcp_atlassian_getVisibleJiraProjects to show options
  • Verify Project Access: Ensure you have permissions to create issues in the selected project
  • Gather Project Preferences:
  • Default assignee preferences
  • Standard labels to apply
  • Priority mapping rules
  • Story point estimation preferences

2. Existing Content Analysis

Before creating any new items, I will:

  • Search Existing Epics: Use JQL to find existing epics in the project
  • Search Related Stories: Look for user stories that might overlap
  • Content Comparison: Compare existing epic/story summaries with new requirements
  • Duplicate Detection: Identify potential duplicates based on:
  • Similar titles/summaries
  • Overlapping descriptions
  • Matching acceptance criteria
  • Related labels or components

Step 1: Requirements Document Analysis

I will thoroughly analyze your requirements document using read_file to:

  • SECURITY CHECK: Verify the file is a legitimate requirements document (not system files)
  • SIZE VALIDATION: Ensure file size is reasonable (< 1MB) for requirements analysis
  • Extract all functional and non-functional requirements
  • Identify natural feature groupings that should become epics
  • Map out user stories within each feature area
  • Note any technical constraints or dependencies
  • CONTENT SANITIZATION: Remove or escape any potentially harmful content before processing

Before you install

  • Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
  • Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
  • Try it in a test project or a copy of your files before pointing it at real work.
  • Pin the version you tested, and review changes before updating.
  • Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.

FAQ

What is Atlassian Requirements to Jira?

Atlassian Requirements to Jira is a subagent for Claude Code and Claude Cowork from the github/awesome-copilot repository on GitHub. Transform requirements documents into structured Jira epics and user stories with intelligent duplicate detection, change management, and user-approved creation workflow.

How do I install Atlassian Requirements to Jira in Claude Code?

Download atlassian-requirements-to-jira.agent.md from the repository. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Can I use Atlassian Requirements to Jira in Claude Cowork?

Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

Is Atlassian Requirements to Jira safe to install?

It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.

Similar resources

Browse all skills, subagents, and plugins →

Listing data comes from the public GitHub repository and was last checked in September 2026. Excerpts are © their authors and shared under MIT. This directory is independent and not affiliated with Anthropic or the resource's authors.