web-design-reviewer
Skill1 starsChanged 2 months agoMITView on GitHub
Inspect local or remote website design, identify layout, responsive, accessibility, and visual consistency defects, and make source-level fixes. Use when users ask to "review website design", "check the UI", "fix the layout", "find design problems", or validate a web page after changes.
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-brainlabedited, first seen Nov 8, 2026
- Vepricov/claude-brainlabedited, first seen Nov 1, 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
Used with
Projects with it also use results-report, daily-coding and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
Galaxy-DawnSkillresults-report
This skill should be used when the user asks to "write an experiment report", "summarize experimental results", "do experiment retrospection", "write a results report", "写实验总结报告", "写实验复盘", or mentions turning completed experiment artifacts into a structured, decision-oriented research report. It assumes strict analysis should come from `results-analysis` first.
Also in 3 projects that use this
Clay-HHKSkilldaily-coding
Daily coding assistant that auto-triggers when writing/modifying code, providing a core checklist.
Also in 3 projects that use this
Clay-HHKSkillkaggle-learner
This skill should be used when the user asks to "learn from Kaggle", "study Kaggle solutions", "analyze Kaggle competitions", or mentions Kaggle competition URLs. Provides access to extracted knowledge from winning Kaggle solutions across NLP, CV, time series, tabular, and multimodal domains.
Also in 3 projects that use this
kharlamenkodevSkillbug-detective
Also in 3 projects that use this
Google CloudSkillcitation-verification
Verify that citations in a document resolve to real records and that claimed titles match. Use before trusting a document's reference list.
Also in 4 projects that use this
AnthropicSkillcommand-development
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
Also in 3 projects that use this
- +2 more from Clay-HHK
Other versions15 projects use a version of this.
Word for word · 1
- paulasilvatech/awesome-copilot-adventures★ 1100% same
Edited · 12
- github/awesome-copilot★ 41k83% same
- Galaxy-Dawn/claude-scholar★ 5.9k82% same
- microsoft/GitHubCopilot_Customized★ 6683% same
- shkodnik1917/claude-brainlab★ 3582% same
- Vepricov/claude-brainlab★ 3582% same
- itsthatladydev/my-agent-skills★ 683% same
- smart-coder-labs/nexus-mind★ 283% same
- birdmanmandbir/skills★ 183% same
- Clay-HHK/claude-skills★ 182% same
- ReaperOAK/ForgeOS★ 083% 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 repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- canvas-designSkill
- evidence-firstSkill
- frontend-dashboard-visualizationSkill
- frontend-experience-coreSkill
- frontend-form-interactionsSkill
- frontend-mobile-desktop-testingSkill
- frontend-requirements-and-storiesSkill
- frontend-visual-e2e-testingSkill
- frontend-visual-systemSkill
- ms-presentation-deckSkill
- official-docsSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
22 rules. 18 are common, 3 are distinctive, and 1 is very specific to this project.
18
Common
Most of the 14 edited versions we read keep these.
3
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 109
If the URL is not provided, ask the user:
- Common: line 115
When making fixes, gather the following information:
- Common: line 160
If additional pages exist, traverse through navigation
- Common: line 202
Test at the following viewports:
- Common: line 275
Search codebase by class name or ID
- Common: line 297
Minimal Changes: Only make the minimum changes necessary to resolve the issue
- Common: line 298
Respect Existing Patterns: Follow existing code style in the project
- Common: line 300
Add Comments: Add comments to explain the reason for fixes where appropriate
- Common: line 314
Verify that fixes haven't affected other areas
- Common: line 372
Iteration Limit: If more than 3 fix attempts are needed for a specific issue, consult the user
- Distinctive: line 477
Always save screenshots before making fixes
- Common: line 479
Follow the project's existing code style
- Distinctive: line 481
Document fix details thoroughly
- Very specific: line 496
Check dependencies in package.json
- Common: line 497
Consider the possibility of CSS-in-JS
- Common: line 498
Consider CSS generated at build time
- Common: line 499
Ask user about styling method
- Common: line 503
Check if development server HMR is working
- Common: line 506
Check CSS specificity issues
- Common: line 511
Use more specific selectors
- Common: line 512
Consider using CSS Modules or scoped styles
- Distinctive: line 518
Read bundled references only when the task needs that depth.
“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
Inspect local or remote websites visually, identify layout, responsive, accessibility, and consistency defects, then make source-level fixes when the workspace contains the code.
When to invoke
- "Review this website design."
- "Check the UI for layout problems."
- "Fix the responsive layout."
- "Find design problems on this page."
- "Validate the web design after my changes."
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 and context
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
Procedure
---
config:
theme: base
look: classic
themeVariables:
darkMode: false
background: "#ffffff"
primaryColor: "#f5f5f5"
primaryTextColor: "#111111"
primaryBorderColor: "#555555"
secondaryColor: "#e0e0e0"
secondaryTextColor: "#111111"
secondaryBorderColor: "#666666"
tertiaryColor: "#bdbdbd"
tertiaryTextColor: "#111111"
tertiaryBorderColor: "#444444"
lineColor: "#444444"
textColor: "#111111"
mainBkg: "#f5f5f5"
nodeBorder: "#555555"
clusterBkg: "#ffffff"
clusterBorder: "#999999"
edgeLabelBackground: "#ffffff"
actorBkg: "#e0e0e0"
actorBorder: "#555555"
actorTextColor: "#111111"
actorLineColor: "#777777"
signalColor: "#333333"
signalTextColor: "#111111"
labelBoxBkgColor: "#f5f5f5"
labelBoxBorderColor: "#777777"
labelTextColor: "#111111"
loopTextColor: "#111111"
activationBkgColor: "#bdbdbd"
activationBorderColor: "#555555"
noteBkgColor: "#f5f5f5"
noteTextColor: "#111111"
noteBorderColor: "#777777"
attributeBackgroundColorOdd: "#f5f5f5"
attributeBackgroundColorEven: "#e0e0e0"
---
flowchart TD
accTitle: Web design review procedure
accDescr: Information gathering leads to visual inspection, issue fixing and re-verification; remaining issues return to inspection, otherwise the review ends in a completion report.
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"]Legend. Rectangles are review steps; the diamond is the decision after re-verification. Solid arrows show the normal order; the labeled branches show the two outcomes.
Explanation. Inspection and fixing repeat until re-verification finds nothing left. The report is written from the verified state, not from the first pass.
Information gathering
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 |
Visual inspection criteria
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
Work through references/visual-checklist.md during inspection and again during post-fix verification.
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 |
Source-level fixing
3.1 Issue Prioritization
---
config:
theme: base
look: classic
themeVariables:
darkMode: false
background: "#ffffff"
primaryColor: "#f5f5f5"
primaryTextColor: "#111111"
primaryBorderColor: "#555555"
secondaryColor: "#e0e0e0"
secondaryTextColor: "#111111"
secondaryBorderColor: "#666666"
tertiaryColor: "#bdbdbd"
tertiaryTextColor: "#111111"
tertiaryBorderColor: "#444444"
lineColor: "#444444"
textColor: "#111111"
mainBkg: "#f5f5f5"
nodeBorder: "#555555"
clusterBkg: "#ffffff"
clusterBorder: "#999999"
edgeLabelBackground: "#ffffff"
actorBkg: "#e0e0e0"
actorBorder: "#555555"
actorTextColor: "#111111"
actorLineColor: "#777777"
signalColor: "#333333"
signalTextColor: "#111111"
labelBoxBkgColor: "#f5f5f5"
labelBoxBorderColor: "#777777"
labelTextColor: "#111111"
loopTextColor: "#111111"
activationBkgColor: "#bdbdbd"
activationBorderColor: "#555555"
noteBkgColor: "#f5f5f5"
noteTextColor: "#111111"
noteBorderColor: "#777777"
attributeBackgroundColorOdd: "#f5f5f5"
attributeBackgroundColorEven: "#e0e0e0"
---
flowchart TD
accTitle: Fix priority order
accDescr: Layout defects that affect functionality are fixed first, then visual defects that degrade the experience, then minor inconsistencies.
P1["P1 · fix immediately<br/>layout defects affecting functionality"] --> P2["P2 · fix next<br/>visual defects degrading the experience"]
P2 --> P3["P3 · fix if possible<br/>minor visual inconsistencies"]Legend. Each rectangle is a priority band; the arrows show the order in which the bands are addressed.
Explanation. A defect that blocks a task outranks one that only looks wrong. Work down the bands so a long tail of cosmetic issues never delays a functional fix.
3.2 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
Re-verification
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
---
config:
theme: base
look: classic
themeVariables:
darkMode: false
background: "#ffffff"
primaryColor: "#f5f5f5"
primaryTextColor: "#111111"
primaryBorderColor: "#555555"
secondaryColor: "#e0e0e0"
secondaryTextColor: "#111111"
secondaryBorderColor: "#666666"
tertiaryColor: "#bdbdbd"
tertiaryTextColor: "#111111"
tertiaryBorderColor: "#444444"
lineColor: "#444444"
textColor: "#111111"
mainBkg: "#f5f5f5"
nodeBorder: "#555555"
clusterBkg: "#ffffff"
clusterBorder: "#999999"
edgeLabelBackground: "#ffffff"
actorBkg: "#e0e0e0"
actorBorder: "#555555"
actorTextColor: "#111111"
actorLineColor: "#777777"
signalColor: "#333333"
signalTextColor: "#111111"
labelBoxBkgColor: "#f5f5f5"
labelBoxBorderColor: "#777777"
labelTextColor: "#111111"
loopTextColor: "#111111"
activationBkgColor: "#bdbdbd"
activationBorderColor: "#555555"
noteBkgColor: "#f5f5f5"
noteTextColor: "#111111"
noteBorderColor: "#777777"
attributeBackgroundColorOdd: "#f5f5f5"
attributeBackgroundColorEven: "#e0e0e0"
---
flowchart TD
accTitle: Iteration decision after re-verification
accDescr: If issues remain the review returns to visual inspection; otherwise it proceeds to the completion report.
A{"Issues remaining?"} -->|Yes| B["Return to step 2"]
A -->|No| C["Proceed to the completion report"]Legend. The diamond is the decision after re-verification; the two labeled branches are its outcomes.
Explanation. Re-verification decides whether the loop continues. Stopping before it passes leaves the defect in the product with a report that says it was reviewed.
Iteration Limit: If more than 3 fix attempts are needed for a specific issue, consult the user
Report format
## Web design review result
## 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 | Yes |
| Screenshot Capture | Page image capture | Yes |
| Image Analysis | Visual issue detection | Yes |
| 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 |
Browser automation options
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.
Gotchas
Do
- 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
Do not
- 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
Progressive disclosure and bundled resources
Read bundled references only when the task needs that depth.
references/visual-checklist.md: detailed inspection checklist for layout, responsive, accessibility, and visual consistency passes.references/framework-fixes.md: framework-specific source fix guidance for React, Vue, Angular, Svelte, Next.js, Nuxt, SvelteKit, Tailwind CSS, CSS Modules, and CSS-in-JS.
Output template
## Web design review result
**Status:** complete | needs fixes | blocked
**Target URL:** `<http://localhost:3000 or remote URL>`
**Framework:** `<React/Vue/Angular/Svelte/Next.js/Nuxt/SvelteKit/CMS/unknown>`
**Styling:** `<CSS/SCSS/Sass/Tailwind CSS/CSS Modules/styled-components/Emotion/unknown>`
**Tested viewports:** `375px`, `768px`, `1280px`, `1920px`
| Priority | Page | Element | Issue | Evidence | Fixed file | Verification |
| --- | --- | --- | --- | --- | --- | --- |
| P1 | `<path>` | `<selector or description>` | `<overflow/overlap/contrast/focus/etc.>` | `<screenshot or DOM evidence>` | `{File path}` | `<Before/After result>` |
**Unfixed issues**
- `<issue>`: `<reason and recommended action>`Quality gate
nameisweb-design-reviewerand matches the parent directory.- The target URL is reachable, including
http://localhost:3000when the local server is running. - Screenshots or DOM snapshots were inspected before any edit.
references/visual-checklist.mdis used for inspection and post-fix verification when detailed review is requested.references/framework-fixes.mdis used before framework-specific edits.- Mobile
375px, tablet768px, desktop1280px, and wide1920pxviewports are tested when responsive behavior is in scope. - Fixes are minimal, source-level, and verified with screenshots or DOM evidence after reload/HMR/rebuild.
- More than three failed fix attempts on one issue are reported instead of continuing blindly.
References
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.

