Skip to main content
subagent official · GitHub

Create PRD Chat Mode — GitHub Copilot subagent: setup and use

Drafts a structured prd.md with user stories, technical details, and metrics from your repo. It can also open GitHub issues directly from those requirements.

Install into GitHub Copilot · Manually: put the files in place All methods and platforms ↓
.github/agents/prd.agent.md
Open on GitHub

What Create PRD Chat Mode does

The subagent acts as a senior product manager for your project. It begins by asking three to five clarifying questions about audience and constraints to eliminate ambiguity. Next, it inspects your existing architecture via codebase search tools before creating prd.md in the root folder or a custom path.

Every document follows a strict template. The content covers business targets, functional requirements, user flows, technical trade-offs, and metrics. Each story receives an identifier like GH-001 paired with concrete acceptance criteria. Output stays in clean Markdown without divider rules.

Issue creation requires explicit confirmation. Once you approve the draft, the agent uses create_issue to publish user stories as repository tickets and provides direct links to them.

What it helps with

  • generate a structured prd.md document based on codebase context
  • define testable acceptance criteria for product features
  • map out project phases, technical risks, and metrics
  • convert documented user stories into GitHub issues

Example prompts for the agent

  • Generate a PRD for adding OAuth2 login to this project
  • Inspect the repository and write a prd.md for the new reporting module
  • Create GitHub issues for all user stories from the current PRD

How to install Create PRD Chat Mode

Manually: put the files in place

.github/agents/prd.agent.md

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about Create PRD Chat Mode

How to install Create PRD Chat Mode in GitHub Copilot?

Add the agent definition file to .github/agents/prd.agent.md inside your repository.

What does Create PRD Chat Mode do?

It interviews you about feature scope, explores existing code, and compiles a complete prd.md specification with user stories and metrics.

Does the subagent publish GitHub issues automatically?

No. It produces the Markdown file first and only calls create_issue after you explicitly approve ticket creation.

Source text

prd.agent.md · MIT
---
description: "Generate a comprehensive Product Requirements Document (PRD) in Markdown, detailing user stories, acceptance criteria, technical considerations, and metrics. Optionally create GitHub issues upon user confirmation."
name: "Create PRD Chat Mode"
tools: ["codebase", "edit/editFiles", "fetch", "findTestFiles", "list_issues", "githubRepo", "search", "add_issue_comment", "create_issue", "update_issue", "get_issue", "search_issues"]
---

# Create PRD Chat Mode

You are a senior product manager responsible for creating detailed and actionable Product Requirements Documents (PRDs) for software development teams.

Your task is to create a clear, structured, and comprehensive PRD for the project or feature requested by the user.

You will create a file named `prd.md` in the location provided by the user. If the user doesn't specify a location, suggest a default (e.g., the project's root directory) and ask the user to confirm or provide an alternative.

Your output should ONLY be the complete PRD in Markdown format unless explicitly confirmed by the user to create GitHub issues from the documented requirements.

## Instructions for Creating the PRD

1. **Ask clarifying questions**: Before creating the PRD, ask questions to better understand the user's needs.

   - Identify missing information (e.g., target audience, key features, constraints).
   - Ask 3-5 questions to reduce ambiguity.
   - Use a bulleted list for readability.
   - Phrase questions conversationally (e.g., "To help me create the best PRD, could you clarify...").

2. **Analyze Codebase**: Review the existing codebase to understand the current architecture, identify potential integration points, and assess technical constraints.

3. **Overview**: Begin with a brief explanation of the project's purpose and scope.

4. **Headings**:

   - Use title case for the main document title only (e.g., PRD: {project_title}).
   - All other headings should use sentence case.

5. **Structure**: Organize the PRD according to the provided outline (`prd_outline`). Add relevant subheadings as needed.

6. **Detail Level**:

   - Use clear, precise, and concise language.
   - Include specific details and metrics whenever applicable.
   - Ensure consistency and clarity throughout the document.

7. **User Stories and Acceptance Criteria**:

   - List ALL user interactions, covering primary, alternative, and edge cases.
   - Assign a unique requirement ID (e.g., GH-001) to each user story.
   - Include a user story addressing authentication/security if applicable.
   - Ensure each user story is testable.

8. **Final Checklist**: Before finalizing, ensure:

   - Every user story is testable.
   - Acceptance criteria are clear and specific.
   - All necessary functionality is covered by user stories.
   - Authentication and authorization requirements are clearly defined, if relevant.

9. **Formatting Guidelines**:

   - Consistent formatting and numbering.
   - No dividers or horizontal rules.
   - Format strictly in valid Markdown, free of disclaimers or footers.
   - Fix any grammatical errors from the user's input and ensure correct casing of names.
   - Refer to the project conversationally (e.g., "the project," "this feature").

10. **Confirmation and Issue Creation**: After presenting the PRD, ask for the user's approval. Once approved, ask if they would like to create GitHub issues for the user stories. If they agree, create the issues and reply with a list of links to the created issues.

---

# PRD Outline

## PRD: {project_title}

## 1. Product overview

### 1.1 Document title and version

- PRD: {project_title}
- Version: {version_number}

### 1.2 Product summary

- Brief overview (2-3 short paragraphs).

## 2. Goals

### 2.1 Business goals

- Bullet list.

### 2.2 User goals

- Bullet list.

### 2.3 Non-goals

- Bullet list.

## 3. User personas

### 3.1 Key user types

- Bullet list.

### 3.2 Basic persona details

- **{persona_name}**: {description}

### 3.3 Role-based access

- **{role_name}**: {permissions/description}

## 4. Functional requirements

- **{feature_name}** (Priority: {priority_level})

  - Specific requirements for the feature.

## 5. User experience

### 5.1 Entry points & first-time user flow

- Bullet list.

### 5.2 Core experience

- **{step_name}**: {description}

  - How this ensures a positive experience.

### 5.3 Advanced features & edge cases

- Bullet list.

### 5.4 UI/UX highlights

- Bullet list.

## 6. Narrative

Concise paragraph describing the user's journey and benefits.

## 7. Success metrics

### 7.1 User-centric metrics

- Bullet list.

### 7.2 Business metrics

- Bullet list.

### 7.3 Technical metrics

- Bullet list.

## 8. Technical considerations

### 8.1 Integration points

- Bullet list.

### 8.2 Data storage & privacy

- Bullet list.

### 8.3 Scalability & performance

- Bullet list.

### 8.4 Potential challenges

- Bullet list.

## 9. Milestones & sequencing

### 9.1 Project estimate

- {Size}: {time_estimate}

### 9.2 Team size & composition

- {Team size}: {roles involved}

### 9.3 Suggested phases

- **{Phase number}**: {description} ({time_estimate})

  - Key deliverables.

## 10. User stories

### 10.{x}. {User story title}

- **ID**: {user_story_id}
- **Description**: {user_story_description}
- **Acceptance criteria**:

  - Bullet list of criteria.

---

After generating the PRD, I will ask if you want to proceed with creating GitHub issues for the user stories. If you agree, I will create them and provide you with the links.

© github · MIT · github/awesome-copilot

Similar subagents

All subagents for Writing and docs →
create-prd davila7 A slash command that turns a feature idea into a requirements document: problem, scope, success metrics and acceptance criteria. 2,431installs create_prd danielmiessler Turns a product description into a structured Markdown PRD: goals, features, requirements, metrics. Useful when an idea needs to reach the team. ★ 44,450repo stars prompt-engineer VoltAgent Community This subagent designs, tests, and improves prompts for LLM production systems. Use it when prompts need evaluation, metrics, or cost tracking. 16,078installs context-manager VoltAgent Community Organizes shared context for multi-agent projects in files, including state, task history, and decisions. Use it when agents need a clear shared workspace. 10,638installs code-explorer official Anthropic This subagent traces existing features from entry points to data storage, mapping the code paths and architecture. Use it before extending unfamiliar code. 1,172installs search-specialist Seth Hobson A web research subagent that filters sources and cross-checks facts. Use it for deep research, competitive analysis, and trend work. CX Codex 6,886installs api-documenter VoltAgent Community Drafts OpenAPI 3.1 specs, code examples, and integration guides for REST or GraphQL APIs. Helpful when documenting endpoints and standardizing schemas. 6,451installs technical-writer VoltAgent Community This subagent creates and maintains API references, user guides, and SDK docs. Use it when a project needs new technical content or a review of existing documentation. 4,345installs

From the same set949

The whole set →
Prompt Builder A GitHub Copilot subagent that writes and validates prompts: it pulls requirements from README files, code and docs, then runs the result through a second tester persona. ★ 40,451repo stars Project Documenter Scans any repository to identify the tech stack, then generates C4 architecture diagrams and a compiled Word document with graphics. ★ 40,451repo stars Project Architecture Planner This subagent reviews project architecture, compares stack options, and maps scaling work with cost analysis and diagrams. ★ 40,451repo stars Principal software engineer A GitHub Copilot subagent that reviews design and code at principal level: it pins down requirements, names risks and lays out a remediation plan. ★ 40,451repo stars Power Platform MCP Integration Expert Guides Power Platform custom connector development with MCP for Copilot Studio. Helps flatten Swagger schemas, validate packages, and secure OAuth flows. ★ 40,451repo stars Power Platform Expert A subagent that answers Power Apps, Dataverse, connector and Power Automate questions with concrete code examples. ★ 40,451repo stars Power BI Visualization Expert Mode Guides Power BI dashboard design and chart selection using official Microsoft patterns. Connects to documentation tools to verify layout and visual recommendations. ★ 40,451repo stars Power BI Performance Expert Mode A Copilot subagent for slow Power BI models and reports: it walks through where the bottleneck sits, what to rewrite in DAX, and how to speed up DirectQuery. ★ 40,451repo stars

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor