web-design-reviewer
Skill35 starsChanged 2 months agoMITView on GitHub
Inspects a rendered website in a browser and fixes demonstrated layout, visual and responsive design problems in the source code. Use when the user says 'review this page's design', 'the layout is broken on mobile', 'check responsive behavior' or asks to find and fix visual issues on a running site.
15 other projects use a version of this, 12 of them edited.
Adopted by
Most recently taken up by
- smart-coder-labs/nexus-mindedited, first seen Nov 8, 2026
- shkodnik1917/claude-brainlabword for word, first seen Nov 8, 2026
- github/awesome-copilotedited, first seen Oct 25, 2026
- PracticalSwan/agent-skillstheir own version, first seen Oct 19, 2026
- birdmanmandbir/skillsedited, first seen Oct 9, 2026
- navikt/copilottheir own version, first seen Sep 14, 2026
Other versions15 projects use a version of this.
Word for word · 1
- shkodnik1917/claude-brainlab★ 35100% same
Edited · 12
- github/awesome-copilot★ 41k94% same
- Galaxy-Dawn/claude-scholar★ 5.9k96% same
- microsoft/GitHubCopilot_Customized★ 6696% same
- itsthatladydev/my-agent-skills★ 696% same
- smart-coder-labs/nexus-mind★ 296% same
- birdmanmandbir/skills★ 194% same
- Clay-HHK/claude-skills★ 196% same
- paulasilvatech/awesome-copilot-adventures★ 157% same
- workshop-gbb/awesome-copilot-adventures★ 157% same
- ReaperOAK/ForgeOS★ 096% same
2 more not listed
Wrote their own version · 2
- navikt/copilot★ 61same name
- PracticalSwan/agent-skills★ 22same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository68 other files it gives its agents.
- rules/agents.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- academic-plottingSkill
- agent-identifierSkill
- architecture-designSkill
- astar-paper-reviewSkill
- bug-detectiveSkill
- call-notesSkill
- cavemanSkill
- citation-verificationSkill
- code-ingestSkill
- code-librarySkill
- code-review-excellenceSkill
- command-developmentSkill
- create-projectSkill
- daily-codingSkill
- defuddleSkill
- diagnoseSkill
- doc-coauthoringSkill
- experiment-runsSkill
- frontend-designSkill
- git-guardrails-claude-codeSkill
- git-workflowSkill
- google-workspace-mcpSkill
- grill-meSkill
- grill-with-docsSkill
- handoffSkill
- handoff-to-jarvisSkill
- hook-developmentSkill
- improve-codebase-architectureSkill
- json-canvasSkill
- kaggle-learnerSkill
- lab-knowledgeSkill
- latex-conference-template-organizerSkill
- mcp-integrationSkill
- ml-paper-writingSkill
- obsidian-basesSkill
- obsidian-cliSkill
- obsidian-experiment-logSkill
- obsidian-markdownSkill
- operon-obsidian-setupSkill
- paper-ingestSkill
- paper-searchSkill
- paper-to-socialSkill
- paper-venue-formattingSkill
- pdf-readerSkill
- planning-with-filesSkill
- plugin-structureSkill
- presentationSkill
- presenter-modeSkill
- prototypeSkill
- research-cycleSkill
- research-ideationSkill
- restore-sessionSkill
- results-analysisSkill
- results-reportSkill
- reverse-outline-flow-checkSkill
- review-responseSkill
- setup-pre-commitSkill
- skill-developmentSkill
- The first 60 shown.
The file
Show its rules and text
We split this skill into the rules it gives an agent
18 rules. 17 are common, 0 are distinctive, and 1 is very specific to this project.
17
Common
Most of the 14 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Common: line 54
If the URL is not provided, ask the user:
- Common: line 60
When making fixes, gather the following information:
- Common: line 105
If additional pages exist, traverse through navigation
- Common: line 145
Test at the following viewports:
- Common: line 175
Search codebase by class name or ID
- Common: line 197
Minimal Changes: Only make the minimum changes necessary to resolve the issue
- Common: line 198
Respect Existing Patterns: Follow existing code style in the project
- Common: line 200
Add Comments: Add comments to explain the reason for fixes where appropriate
- Common: line 214
Verify that fixes haven't affected other areas
- Common: line 226
Iteration Limit: If more than 3 fix attempts are needed for a specific issue, consult the user
- Very specific: line 352
Check dependencies in package.json
- Common: line 353
Consider the possibility of CSS-in-JS
- Common: line 354
Consider CSS generated at build time
- Common: line 355
Ask user about styling method
- Common: line 359
Check if development server HMR is working
- Common: line 362
Check CSS specificity issues
- Common: line 367
Use more specific selectors
- Common: line 368
Consider using CSS Modules or scoped styles
“Common” is measured: kept by at least 6 in 10 of the 14 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Web Design Reviewer
This skill enables visual inspection and validation of website design quality, identifying and fixing issues at the source code level.
Scope of Application
- Static sites (HTML/CSS/JS)
- SPA frameworks such as React / Vue / Angular / Svelte
- Full-stack frameworks such as Next.js / Nuxt / SvelteKit
- CMS platforms such as WordPress / Drupal
- Any other web application
Prerequisites
Required
- Target website must be running
- Local development server (e.g.,
http://localhost:3000) - Staging environment
- Production environment (for read-only reviews)
- Local development server (e.g.,
- Browser automation must be available
- Screenshot capture
- Page navigation
- DOM information retrieval
- Access to source code (when making fixes)
- Project must exist within the workspace
Workflow Overview
flowchart TD
A[Step 1: Information Gathering] --> B[Step 2: Visual Inspection]
B --> C[Step 3: Issue Fixing]
C --> D[Step 4: Re-verification]
D --> E{Issues Remaining?}
E -->|Yes| B
E -->|No| F[Completion Report]Step 1: Information Gathering Phase
1.1 URL Confirmation
If the URL is not provided, ask the user:
Please provide the URL of the website to review (e.g.,
http://localhost:3000)
1.2 Understanding Project Structure
When making fixes, gather the following information:
| Item | Example Question |
| Framework | Are you using React / Vue / Next.js, etc.? |
| Styling Method | CSS / SCSS / Tailwind / CSS-in-JS, etc. |
| Source Location | Where are style files and components located? |
| Review Scope | Specific pages only or entire site? |
1.3 Automatic Project Detection
Attempt automatic detection from files in the workspace:
Detection targets:
├── package.json → Framework and dependencies
├── tsconfig.json → TypeScript usage
├── tailwind.config → Tailwind CSS
├── next.config → Next.js
├── vite.config → Vite
├── nuxt.config → Nuxt
└── src/ or app/ → Source directory1.4 Identifying Styling Method
| Method | Detection | Edit Target |
| Pure CSS | *.css files | Global CSS or component CSS |
| SCSS/Sass | *.scss, *.sass | SCSS files |
| CSS Modules | *.module.css | Module CSS files |
| Tailwind CSS | tailwind.config.* | className in components |
| styled-components | styled. in code | JS/TS files |
| Emotion | @emotion/ imports | JS/TS files |
| CSS-in-JS (other) | Inline styles | JS/TS files |
Step 2: Visual Inspection Phase
2.1 Page Traversal
- Navigate to the specified URL
- Capture screenshots
- Retrieve DOM structure/snapshot (if possible)
- If additional pages exist, traverse through navigation
2.2 Inspection Items
Layout Issues
| Issue | Description | Severity |
| Element Overflow | Content overflows from parent element or viewport | High |
| Element Overlap | Unintended overlapping of elements | High |
| Alignment Issues | Grid or flex alignment problems | Medium |
| Inconsistent Spacing | Padding/margin inconsistencies | Medium |
| Text Clipping | Long text not handled properly | Medium |
Responsive Issues
| Issue | Description | Severity |
| Non-mobile Friendly | Layout breaks on small screens | High |
| Breakpoint Issues | Unnatural transitions when screen size changes | Medium |
| Touch Targets | Buttons too small on mobile | Medium |
Accessibility Issues
| Issue | Description | Severity |
| Insufficient Contrast | Low contrast ratio between text and background | High |
| No Focus State | Cannot determine state during keyboard navigation | High |
| Missing alt Text | No alternative text for images | Medium |
Visual Consistency
| Issue | Description | Severity |
| Font Inconsistency | Mixed font families | Medium |
| Color Inconsistency | Non-unified brand colors | Medium |
| Spacing Inconsistency | Non-uniform spacing between similar elements | Low |
2.3 Viewport Testing (Responsive)
Test at the following viewports:
| Name | Width | Representative Device |
| Mobile | 375px | iPhone SE/12 mini |
| Tablet | 768px | iPad |
| Desktop | 1280px | Standard PC |
| Wide | 1920px | Large display |
Step 3: Issue Fixing Phase
3.1 Issue Prioritization
block-beta
columns 1
block:priority["Priority Matrix"]
P1["P1: Fix Immediately\n(Layout issues affecting functionality)"]
P2["P2: Fix Next\n(Visual issues degrading UX)"]
P3["P3: Fix If Possible\n(Minor visual inconsistencies)"]
end3.2 Identifying Source Files
Identify source files from problematic elements:
- Selector-based Search
- Search codebase by class name or ID
- Explore style definitions with
grep_search
- Component-based Search
- Identify components from element text or structure
- Explore related files with
semantic_search
- File Pattern Filtering
Style files: src/**/*.css, styles/**/* Components: src/components/**/* Pages: src/pages/**, app/**
3.3 Applying Fixes
Framework-specific Fix Guidelines
See references/framework-fixes.md for details.
Fix Principles
- Minimal Changes: Only make the minimum changes necessary to resolve the issue
- Respect Existing Patterns: Follow existing code style in the project
- Avoid Breaking Changes: Be careful not to affect other areas
- Add Comments: Add comments to explain the reason for fixes where appropriate
Step 4: Re-verification Phase
4.1 Post-fix Confirmation
- Reload browser (or wait for development server HMR)
- Capture screenshots of fixed areas
- Compare before and after
4.2 Regression Testing
- Verify that fixes haven't affected other areas
- Confirm responsive display is not broken
4.3 Iteration Decision
flowchart TD
A{Issues Remaining?}
A -->|Yes| B[Return to Step 2]
A -->|No| C[Proceed to Completion Report]Iteration Limit: If more than 3 fix attempts are needed for a specific issue, consult the user
Output Format
Review Results Report
# Web Design Review Results
## Summary
| Item | Value |
|------|-------|
| Target URL | {URL} |
| Framework | {Detected framework} |
| Styling | {CSS / Tailwind / etc.} |
| Tested Viewports | Desktop, Mobile |
| Issues Detected | {N} |
| Issues Fixed | {M} |
## Detected Issues
### [P1] {Issue Title}
- **Page**: {Page path}
- **Element**: {Selector or description}
- **Issue**: {Detailed description of the issue}
- **Fixed File**: `{File path}`
- **Fix Details**: {Description of changes}
- **Screenshot**: Before/After
### [P2] {Issue Title}
...
## Unfixed Issues (if any)
### {Issue Title}
- **Reason**: {Why it was not fixed/could not be fixed}
- **Recommended Action**: {Recommendations for user}
## Recommendations
- {Suggestions for future improvements}Required Capabilities
| Capability | Description | Required |
| Web Page Navigation | Access URLs, page transitions | ✅ |
| Screenshot Capture | Page image capture | ✅ |
| Image Analysis | Visual issue detection | ✅ |
| DOM Retrieval | Page structure retrieval | Recommended |
| File Read/Write | Source code reading and editing | Required for fixes |
| Code Search | Code search within project | Required for fixes |
Reference Implementation
Implementation with Playwright MCP
Playwright MCP is recommended as the reference implementation for this skill.
| Capability | Playwright MCP Tool | Purpose |
| Navigation | browser_navigate | Access URLs |
| Snapshot | browser_snapshot | Retrieve DOM structure |
| Screenshot | browser_take_screenshot | Images for visual inspection |
| Click | browser_click | Interact with interactive elements |
| Resize | browser_resize | Responsive testing |
| Console | browser_console_messages | Detect JS errors |
Configuration Example (MCP Server)
{
"mcpServers": {
"playwright": {
"command": "npx",
"args": ["-y", "@playwright/mcp@latest", "--caps=vision"]
}
}
}Other Compatible Browser Automation Tools
| Tool | Features |
| Selenium | Broad browser support, multi-language support |
| Puppeteer | Chrome/Chromium focused, Node.js |
| Cypress | Easy integration with E2E testing |
| WebDriver BiDi | Standardized next-generation protocol |
The same workflow can be implemented with these tools. As long as they provide the necessary capabilities (navigation, screenshot, DOM retrieval), the choice of tool is flexible.
Best Practices
DO (Recommended)
- ✅ Always save screenshots before making fixes
- ✅ Fix one issue at a time and verify each
- ✅ Follow the project's existing code style
- ✅ Confirm with user before major changes
- ✅ Document fix details thoroughly
DON'T (Not Recommended)
- ❌ Large-scale refactoring without confirmation
- ❌ Ignoring design systems or brand guidelines
- ❌ Fixes that ignore performance
- ❌ Fixing multiple issues at once (difficult to verify)
Troubleshooting
Problem: Style files not found
- Check dependencies in
package.json - Consider the possibility of CSS-in-JS
- Consider CSS generated at build time
- Ask user about styling method
Problem: Fixes not reflected
- Check if development server HMR is working
- Clear browser cache
- Rebuild if project requires build
- Check CSS specificity issues
Problem: Fixes affecting other areas
- Rollback changes
- Use more specific selectors
- Consider using CSS Modules or scoped styles
- Consult user to confirm impact scope
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

