Webdesign Review logo

Webdesign Review

Community
flitzrrr
webdesign-review

Meta-skill for comprehensive web design reviews. Orchestrates all 20 domain skills for systematic analysis of websites, designs, and prototypes against enterprise design standards.

Overview

Publisherflitzrrr
Repositoryfrontend-design-skills
Skill namewebdesign-review
Stars
9
Forks
2
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by flitzrrr on GitHub. Read the source before you install it.

Installation

Install the Webdesign Review AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/flitzrrr/frontend-design-skills/tree/main/skills-src/webdesign-review
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/flitzrrr/frontend-design-skills.git /tmp/frontend-design-skills
mkdir -p .claude/skills
cp -r /tmp/frontend-design-skills/skills-src/webdesign-review .claude/skills/webdesign-review
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Webdesign Review in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Webdesign Review on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Webdesign Review is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Webdesign-Review

Systematic design reviews through orchestrated application of all domain skills.

Scope

Use this skill when: You are conducting a comprehensive design review of a website, prototype, or design. This meta-skill coordinates the analysis across all relevant design domains and ensures that no dimension is overlooked.

Principles

1. Rigor Over Gut Feeling

A design review follows a defined structure, not personal preferences. Every assessment must be substantiated by a specific rule or principle from the domain skills.

2. Prioritize by Impact

Not all issues carry equal weight. Prioritize: accessibility and usability before aesthetics. Functional defects before stylistic preferences.

3. Constructive Criticism With Actionable Solutions

Every identified weakness is accompanied by a concrete improvement recommendation. "This is bad" is not a review -- "This violates rule X; a better approach would be Y" is a review.

4. Completeness Through Checklists

The checklists from individual domain skills form the foundation of the review. No item is skipped.

Rules

Review Workflow

  • DO: ALWAYS begin with an overall assessment before drilling into details.
  • DO: Work through the domains in the following order (by priority):
    1. accessibility -- Accessibility (legal obligation, BFSG)
    2. usability -- Usability
    3. ux-design -- User experience and flows
    4. ui-design -- Layout, hierarchy, components
    5. web-typography -- Typography, readability, scale
    6. color-theory -- Color, contrast, scheme
    7. responsive-design -- Behavior across breakpoints
    8. navigation-design -- Navigation structure and clarity
    9. images-media -- Images, video, performance
    10. branding-identity -- Brand consistency
    11. landing-pages -- Conversion optimization (if landing page)
    12. customer-journey -- User journey and touchpoints
    13. component-patterns -- Component architecture
    14. ui-patterns -- Interaction patterns
    15. visual-direction -- Visual direction and trends
    16. design-trends -- Currency and contemporaneity
    17. design-process -- Process quality
    18. ai-design-workflow -- AI integration in design
    19. website-audit -- Technical quality
    20. agent-ui-design -- Agent interfaces (if applicable)
  • DO: Walk through the corresponding checklist for each domain.
  • DO: Categorize findings by severity: Critical / Important / Recommendation.
  • DON'T: Skip domains just because they are "probably fine."
  • DON'T: Record subjective opinions without a rule reference as findings.

Assessment Structure

  • DO: Structure every finding as: Domain > Rule > Finding > Severity > Solution.
  • DO: Attach screenshots or code examples as evidence where possible.
  • DO: Explicitly call out positive aspects -- not just deficiencies.
  • DON'T: Exceed 20 findings per domain. Prioritize the most impactful ones.

Severity Levels

  • Critical: Accessibility violations (BFSG), functional defects, security issues. MUST be resolved immediately.
  • Important: Usability problems, inconsistencies, performance deficiencies. SHOULD be resolved before launch.
  • Recommendation: Stylistic improvements, optimizations, best practices. CAN be addressed in future iterations.

Patterns

Quick Review (30 Minutes)

Focus on the top 6 domains: accessibility, usability, ux-design, ui-design, web-typography, color-theory. Checklist pass without deep analysis.

Standard Review (2 Hours)

All 20 domains. Checklists completed in full. Findings documented with severity and solution. Summary with top 5 priorities.

Deep Audit (1 Day)

Full review plus: screen reader testing, Lighthouse analysis, performance measurement, cross-browser testing, mobile device testing. Detailed report with prioritized action items.

Comparative Review

Analyze a website against competitors. Identify the strongest solution per domain. Provide recommendations for differentiation and improvement.

Anti-Patterns

Cherry-Picking

Only flagging the obvious issues while overlooking systemic deficiencies. Solution: Work through checklists in full.

Aesthetics Bias

Rating well-designed websites more leniently despite poor usability or accessibility. Solution: ALWAYS evaluate accessibility and usability first.

Reviewing Without Context

Evaluating a design without understanding the target audience, business goals, or industry. Solution: Gather context first, then evaluate.

Forgetting the Solution

Listing problems without improvement recommendations. Solution: Every finding requires at least one concrete suggestion.

Checklist

Before the Review

  • Target audience and business goals known?
  • Industry and competitors identified?
  • Pages/screens to review defined?
  • Review depth determined (Quick / Standard / Deep)?

During the Review

  • All relevant domains covered?
  • Domain checklists completed in full?
  • Findings categorized by severity?
  • Solution recommendations for every finding?
  • Positive aspects acknowledged?

After the Review

  • Summary with top 5 priorities prepared?
  • Critical findings clearly flagged?
  • Next steps defined?

Cross-References

This meta-skill orchestrates all 20 domain skills:

Core Design: ui-design, ux-design, web-typography, color-theory, accessibility Structure & Navigation: usability, responsive-design, navigation-design Content & Media: images-media, branding-identity Strategy & Process: customer-journey, design-process, ai-design-workflow Pages & Audit: landing-pages, website-audit Patterns & Trends: design-trends, ui-patterns, visual-direction, component-patterns Specialized: agent-ui-design

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Webdesign Review AI skill do?

Meta-skill for comprehensive web design reviews. Orchestrates all 20 domain skills for systematic analysis of websites, designs, and prototypes against enterprise design standards.

Why use Webdesign Review on TypingMind?

Because you install it once and use it with any model. Webdesign Review is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Webdesign Review in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/flitzrrr/frontend-design-skills/tree/main/skills-src/webdesign-review. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Webdesign Review?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Webdesign Review?

As many as you like. As long as a model supports skills, you can use Webdesign Review with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Webdesign Review AI skill free?

Yes. It is published on GitHub by flitzrrr under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇