plan-prd

Create a comprehensive Product Requirements Document.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "plan-prd" with this command: npx skills add dthompson-jti/safety-check-app-concept/dthompson-jti-safety-check-app-concept-plan-prd

Plan PRD

Create a comprehensive Product Requirements Document.

When to Use

  • Large features or epics

  • New user-facing functionality

  • Features requiring UX exploration

Artifacts

  • PRD-[EPIC-NAME].md in docs/working/

  • task.md updated via task_boundary

Approach

Phase 1: Discovery & Scope

  • Proof of Understanding: Summarize core user problem in one sentence.

  • User Stories: "As a [user], I want [action], so that [benefit]"

  • Non-Goals: Explicitly state out-of-scope items.

Phase 2: Design Options (Forced Diversity)

Generate 4-6 architecturally distinct options varying:

  • Information architecture

  • Interaction model

  • Visual hierarchy

Use Socratic Debate for complex decisions:

  • Proponent argues for option

  • Adversary critiques

  • Synthesis resolves

Phase 3: Detailed UX Specification

State Matrix

State Visual Behavior

Default ... ...

Hover ... ...

Focus ... ...

Active ... ...

Disabled ... ...

Empty ... ...

Loading ... ...

Error ... ...

ASCII Wireframes

Use var(--token-name) syntax. Reference existing patterns.

Accessibility Requirements

  • Keyboard navigation path

  • ARIA labels/roles

  • Screen reader announcements

  • Reduced motion considerations

Phase 4: Validation

  • UX Risks & Mitigations table

  • Definition of Done checklist

  • Reflexion: Hostile Accessibility Auditor critique

Constraints

  • No technical architecture — handled in plan/architecture

  • All options must consider light/dark mode, accessibility

  • Flag as "Hallucination" if using non-existent design tokens

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

debug-standard

No summary provided by upstream source.

Repository SourceNeeds Review
General

explore-ui-design

No summary provided by upstream source.

Repository SourceNeeds Review
General

implement-quick-fix

No summary provided by upstream source.

Repository SourceNeeds Review
General

explore-ux

No summary provided by upstream source.

Repository SourceNeeds Review