roast

Automate multi-perspective UI/UX critique and generate iterative reports with fixes.

1|Updated Jan 30, 2026
One-click install
npx skills add https://github.com/muspelheim/claude-roaster --skill roast
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: roast
Source: https://github.com/muspelheim/claude-roaster/tree/main/skills/roast
Command: npx skills add https://github.com/muspelheim/claude-roaster --skill roast

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Roast automates brutal, multi-perspective UI/UX critique to produce actionable improvements across designer, developer, user, accessibility, and marketing perspectives.

Core Features & Use Cases

  • Multi-perspective analysis: Designers, developers, users, A11y, and marketing specialists evaluate UI/UX from diverse viewpoints.
  • Iterative improvement cycles: Roast → Fix → Roast through configurable iterations to progressively improve interfaces.
  • Structured outputs: Generates reports with findings, screenshots, and recommended fixes for each iteration, including flow and audit analyses.
  • Use Case: A design team roasts a new onboarding flow, implements fixes, and re-roasts until usability goals are met.

Quick Start

Run roast in screen mode for a single target: /roast screen login Then flow mode for a journey: /roast flow onboarding Or audit mode for a full app review: /roast audit

Frequently Asked Questions about roast

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

FAQPage Schema
How do I get multi-perspective UI/UX critique for my design?

Multi-perspective UI/UX critique evaluates interfaces from designer, developer, user, accessibility, and marketing viewpoints to deliver actionable improvements. It analyzes screen-level journeys and audits to produce structured reports with recommended fixes.

Can I automate iterative design reviews for an onboarding flow?

Iterative design reviews automate the roast, fix, and re-roast cycle through configurable iterations. You can run flow mode on an onboarding journey to progressively improve usability until your interface goals are met.

What is the best way to run an accessibility and usability audit on a full app?

Running a full app accessibility and usability audit uses audit mode to review the entire application. It generates structured outputs containing findings, recommended fixes, and screenshots from multiple specialist perspectives.

Does brutal UI critique provide actionable improvements or just feedback?

Brutal UI critique provides actionable improvements by delivering structured reports with specific findings and recommended fixes. It evaluates screen-level and flow-based journeys across multiple perspectives to ensure usability goals are met.

How do I evaluate a single login screen for usability and accessibility issues?

Evaluating a single login screen uses screen mode to target one specific UI component. This mode analyzes the interface from multiple perspectives including usability and accessibility, generating a report with recommended fixes.

When do I need multi-perspective design critique instead of a standard review?

Multi-perspective design critique is needed when an interface requires evaluation across design, development, usability, accessibility, and marketing viewpoints. It provides comprehensive actionable improvements that standard single-viewpoint reviews often miss.