prp-core

PRP (Product Requirement Prompts)

A collection of prompts for AI-assisted development with Claude Code.

Video Walkthrough

https://www.youtube.com/watch?v=KVOZ9s1S9Gk&lc=UgzfwxvFjo6pKEyPo1R4AaABAg

Support This Work

Found value in these resources?

Buy me a coffee: https://coff.ee/wirasm

I spent a considerable amount of time creating these resources and prompts. If you find value in this project, please consider buying me a coffee to support my work.

---

Transform Your Team with AI Engineering Workshops

Ready to move beyond toy demos to production-ready AI systems?

Book a workshop: https://www.rasmuswiding.com/

What you'll get:

• Put your team on a path to become AI power users
• Learn the exact PRP methodology used by top engineering teams
• Hands-on training with Claude Code, PRPs, and real codebases
• From beginner to advanced AI engineering workshops for teams and individuals

Perfect for: Engineering teams, Product teams, and developers who want AI that actually works in production

Contact me directly at [email protected]

---

What is PRP?

Product Requirement Prompt (PRP) = PRD + curated codebase intelligence + agent/runbook

The minimum viable packet an AI needs to ship production-ready code on the first pass.

A PRP supplies an AI coding agent with everything it needs to deliver a vertical slice of working software—no more, no less.

How PRP Differs from Traditional PRD

A traditional PRD clarifies what the product must do and why customers need it, but deliberately avoids how it will be built.

A PRP keeps the goal and justification sections of a PRD yet adds AI-critical layers:

• Context: Precise file paths, library versions, code snippet examples
• Patterns: Existing codebase conventions to follow
• Validation: Executable commands the AI can run to verify its work

---

Quick Start

Option 1: Copy Commands to Your Project

# From your project root
cp -r /path/to/PRPs-agentic-eng/.claude/commands/prp-core .claude/commands/

Option 2: Clone Repository

git clone https://github.com/Wirasm/PRPs-agentic-eng.git
cd PRPs-agentic-eng

---

Commands

The .claude/commands/prp-core/ directory contains the core PRP workflow commands:

Core Workflow

Command	Description
/prp-prd	Interactive PRD generator with implementation phases
/prp-plan	Create implementation plan (from PRD or free-form input)
/prp-implement	Execute a plan with validation loops

Issue & Debug Workflow

Command	Description
/prp-issue-investigate	Analyze GitHub issue, create implementation plan
/prp-issue-fix	Execute fix from investigation artifact
/prp-debug	Deep root cause analysis with 5 Whys methodology

Git & Review

Command	Description
/prp-commit	Smart commit with natural language file targeting
/prp-pr	Create PR with template support
/prp-review	Comprehensive PR code review

Autonomous Loop

Command	Description
/prp-ralph	Start autonomous loop until all validations pass
/prp-ralph-cancel	Cancel active Ralph loop

---

Ralph Loop (Autonomous Execution)

Based on Geoffrey Huntley's Ralph Wiggum technique - a self-referential loop that keeps iterating until the job is actually done.

How It Works

/prp-ralph .claude/PRPs/plans/my-feature.plan.md --max-iterations 20

1. Claude implements the plan tasks
2. Runs all validation commands (type-check, lint, tests, build)
3. If any validation fails → fixes and re-validates
4. Loop continues until ALL validations pass
5. Outputs <promise>COMPLETE</promise> and exits

Each iteration, Claude sees its previous work in files and git history. It's not starting fresh - it's debugging itself.

Setup

The stop hook must be configured in .claude/settings.local.json:

{
  "hooks": {
    "Stop": [
      {
        "hooks": [
          {
            "type": "command",
            "command": ".claude/hooks/prp-ralph-stop.sh"
          }
        ]
      }
    ]
  }
}

Usage

# Create a plan
/prp-plan "add user authentication with JWT"

# Let Ralph loose
/prp-ralph .claude/PRPs/plans/add-user-auth.plan.md --max-iterations 20