Problem-Based SRS

🎯 Overview

An Agent Skill following the Problem-Based Software Requirements Specification (SRS) methodology. Designed for integration with AI agents like GitHub Copilot and Claude Code.

📄 Background

This repository is a continuation of research presented in the paper: "Problem-Based SRS: A Novel Approach for Software Requirements Specification" by Gorski and Stadzisz.

The methodology addresses a critical challenge: accurately capturing business intents of stakeholders, which remains a major factor in software project failures. The Problem-Based SRS methodology consists of five main steps that systematically analyze business context and specify software requirements while considering solution design.

Supported Formats: This repository provides GitHub Copilot prompt files (.github/prompts/) and AgentSkills (skills/) for maximum compatibility with AI coding assistants.

🎯 Purpose

Enable software engineers and requirements analysts to leverage AI agents for better requirements engineering by providing:

📝 Structured Skills

For each phase of requirements gathering

🧩 Problem-First

Methodology ensuring requirements solve real needs

🤖 AI Integration

Compatible with Claude Code, Claude.ai, and Claude API

⚡ Lightweight

No heavy tooling or frameworks required

📚 Examples & Templates

Ready for immediate use

📊 The 5-Step Methodology

The Problem-Based SRS methodology consists of five structured steps that systematically analyze business context and specify software requirements:

Step 1: Customer Problems (CP)

Identify the WHY - understand and classify customer problems by severity

/cp

Step 2: Software Glance

Draft the software high-level components and solution approach

/glance

Step 3: Customer Needs (CN)

Define the WHAT - customer needs that should help solve the problems

/cn /zigzag (validate)

Step 4: Software Vision

Detail the software architecture, features, and constraints

/vision

Step 5: Functional Requirements (FR)

Define the HOW - detailed implementation requirements

/fr /zigzag (validate)

🔄 Development Workflow Integration

🔗 Artifact Traceability

Every requirement traces back to ensure it solves real problems. Each artifact is interconnected:

📊 Problem Classification

Customer Problems are classified by severity to prioritize what must be solved:

Obligation (Must/Required): High priority - severe consequences if unsolved (legal/contractual)
Expectation (Should/Expects): Medium priority - moderate impact if unsolved (business goals)
Hope (Wishes): Low priority - minimal penalty if unsolved (improvements)

🚀 Quick Start for Engineers

Using GitHub Copilot Prompt Files (Recommended)

The prompts are available as .prompt.md files in .github/prompts/. In VS Code, Visual Studio, or JetBrains IDEs:

/cp           # Start with Customer Problems
/glance       # Create Software Glance
/cn           # Generate Customer Needs
/vision       # Build Software Vision
/fr           # Specify Functional Requirements
/zigzag       # Validate traceability
/srs-coordinator  # Full methodology orchestration

Using with Any AI Agent (Universal)

The methodology works with any LLM (ChatGPT, DeepSeek, Claude, Llama, etc.).

Option 1: AgentSkills (Open Standard)

The skills/ directory follows the AgentSkills standard, compatible with any tool that implements it.

For Claude Code: The skill will auto-discover when this repository is in your workspace.
For Claude.ai: Upload the skill from skills/problem-based-srs/ (including the references folder).

For New Features

Simply describe your business context or problem:

I need to create requirements for [feature name]

Business Context: [describe current situation]

The skill will automatically:

Detect what step you're on
Load the appropriate reference guide
Walk you through the process
Ensure traceability back to business problems

Specific Step Examples

Start with Customer Problems:

Help me identify customer problems for my inventory management system

Create Software Glance:

I have customer problems documented, need to create a software glance

Validate Traceability:

Check if my requirements properly trace back to customer problems

💡 Usage Patterns

Pattern 1: Full Feature Development

When: Building a new feature from business need

Start with: /srs-coordinator

Follow: All 5 steps sequentially

Pattern 2: Requirements Refinement

When: You have draft requirements that need structure

Start with: /fr in review mode

Then: Work backwards to validate against CNs and CPs

Pattern 3: Problem Discovery

When: Stakeholders describe solutions, not problems

Start with: /cp in generation mode

Use: Discovery questions to elicit actual problems

Pattern 4: Quality Gate

When: Validating completeness before implementation

Start with: /zigzag

Verify: All CPs addressed, all CNs trace to CPs, all FRs trace to CNs

🔧 Integration with Development Workflow

During Sprint Planning

Use /cp to capture user stories as customer problems
Use /cn to define acceptance criteria
Use /fr to break down into technical requirements

During Feature Design

Reference /glance for high-level approach
Reference /vision for architectural decisions
Use /zigzag to ensure design addresses all needs

During Implementation

Keep /fr requirements as implementation checklist
Trace each requirement back to CN and CP for context
Update requirements if new problems discovered

During Code Review

Verify implementation satisfies /fr requirements
Check requirements still trace to customer needs
Validate no scope creep beyond identified problems

📚 Additional Resources

Repository Structure

This repository supports multiple formats:

GitHub Copilot Prompt Files

.github/prompts/ - For VS Code, Visual Studio, and JetBrains IDEs

srs-coordinator.prompt.md - Main orchestrator prompt
cp.prompt.md - Step 1: Customer Problems
glance.prompt.md - Step 2: Software Glance
cn.prompt.md - Step 3: Customer Needs
vision.prompt.md - Step 4: Software Vision
fr.prompt.md - Step 5: Functional Requirements
zigzag.prompt.md - Quality validation tool

AgentSkills Format

skills/problem-based-srs/ - For Claude Code and Claude.ai

SKILL.md - Main orchestrator skill
references/ - Detailed instructions for each step
- step1-customer-problems.md
- step2-software-glance.md
- step3-customer-needs.md
- step4-software-vision.md
- step5-functional-requirements.md
- zigzag-validator.md

Additional Documentation

docs/ - Full methodology and research paper
README.md - Quick start guide and examples
CONTRIBUTING.md - Contribution guidelines

Get Started Today

Ready to improve your requirements engineering with AI-assisted methodology?

View on GitHub Browse Prompts View Skills