requirements

Generate testable feature specifications with user stories and acceptance criteria.

1|Updated Feb 28, 2026
One-click install
npx skills add https://github.com/glwr/ai-coding-base --skill requirements-glwr
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: requirements
Source: https://github.com/glwr/ai-coding-base/tree/main/apple/.claude/skills/requirements
Command: npx skills add https://github.com/glwr/ai-coding-base --skill requirements-glwr

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill turns informal project descriptions and feature ideas into structured, testable feature specifications so teams avoid vague requirements, duplicated work, and mismatched expectations.

Core Features & Use Cases

  • Init Mode: Interactive new-project setup that fills README and CLAUDE.md, creates GitHub labels and a v1.0 milestone, and generates initial feature specs linked to issues.
  • Feature Mode: Add a single feature by creating a GitHub issue first, then authoring a spec with user stories, acceptance criteria, and edge cases, and updating features/INDEX.md and roadmap tables.
  • Use Case: Ideal for initializing Apple platform projects or adding discrete, testable features to an existing codebase while preserving traceability to GitHub.

Quick Start

Create detailed feature specifications for a new Apple app to track habits, including user stories, acceptance criteria, and edge cases.

Frequently Asked Questions about requirements

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate testable feature specifications from informal project ideas?

Yes, you can generate feature specifications for Apple platform projects by creating a GitHub issue first, then authoring a spec with user stories and acceptance criteria. It populates README and CLAUDE.md files while preserving traceability to GitHub.

What is the best way to initialize a new Apple platform project with feature specs?

The best way to initialize a new project is using an interactive setup that fills README and CLAUDE.md, creates GitHub labels and a v1.0 milestone, and generates initial feature specs linked to issues. This ensures full traceability from the start.

How do I add a single feature to an existing codebase while preserving GitHub traceability?

You add a single feature by creating a GitHub issue first, then authoring a spec with user stories, acceptance criteria, and edge cases. Finally, update features/INDEX.md and roadmap tables to preserve traceability within your existing codebase.

Do I need to create GitHub issues before writing feature spec files?

Yes, you must create GitHub issues before writing spec files. This workflow ensures every feature specification is directly linked to a tracked issue, maintaining strict traceability across your project management and development lifecycle.