Agent skill

Visual QA

by dylanfeltus in dylanfeltus/skills

Use vision models to self-review screenshots against design intent.

MITAuto-check passedFrontend & Design

Install Visual QA

skills CLI
$ npx skills add dylanfeltus/skills --skill visual-qa -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install dylanfeltus/skills visual-qa --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/dylanfeltus/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/visual-qa .claude/skills/visual-qa && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
visual-qa
GitHub stars
179
Token cost
~2.4k tokens
SKILL.md length
841 words
Files
2
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

Use vision models to self-review screenshots against design intent.

  • Works in 10 steps: Capture the Screenshot → Analyze with Vision → Structured Review → …
  • Reviewing designs
  • SKILL.md covers When to Use, Core Philosophy, How to Review and Review Categories, plus 4 more sections
  • Calls go

What it does

Visual QA is an agent skill from dylanfeltus/skills. Use vision models to self-review screenshots against design intent. Catches spacing issues, alignment problems, color inconsistencies, responsive bugs, and accessibility gaps. Use when reviewing designs, comparing implementations to mockups, or doing pre-ship QA.

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `README.md`).

It sits in Frontend & Design, covering Visual regression testing, Computer vision and Accessibility. The repository describes itself as: A library of AI agent skills for research and design. The licence is MIT.

When your agent uses it

  • Reviewing designs
  • Comparing implementations to mockups
  • Doing pre-ship QA

Example prompts

  • “/visual-qa”

Workflow steps

10 steps, taken from the step headings in SKILL.md.

  1. Capture the Screenshot
  2. Analyze with Vision
  3. Structured Review
  4. Layout & Spacing
  5. Typography
  6. Color & Contrast
  7. Visual Hierarchy
  8. Component Quality
  9. Polish & Micro-details
  10. Responsive Issues (if multiple viewports available)

What it can do on your machine

Read from SKILL.md and the folder at commit b97a48f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • go

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Visual QA loads about 2.4k tokens when it runs. Until then it costs about 68 tokens; SKILL.md has 841 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~68
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from dylanfeltus/skills at commit b97a48f, republished under its MIT licence (© dylanfeltus). 841 words, ~2,415 tokens.

Download SKILL.mdSave it as .claude/skills/visual-qa/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
visual-qa
description
Use vision models to self-review screenshots against design intent. Catches spacing issues, alignment problems, color inconsistencies, responsive bugs, and accessibility gaps. Use when reviewing designs, comparing implementations to mockups, or doing pre-ship QA.

Visual QA

Use vision models to self-review screenshots against design intent. Catch spacing issues, alignment problems, color inconsistencies, responsive bugs, and accessibility gaps before shipping.

When to Use

  • User asks to "review this design" or "check this screenshot"
  • After building a page/component, before shipping
  • User wants to compare implementation vs mockup/reference
  • User asks "does this look right?" or "what's off about this?"
  • Automated design QA step in a build workflow

Core Philosophy

  • Screenshot first, then critique. Always look at the actual rendered output, not just the code.
  • Be specific. "The spacing looks off" is useless. "The gap between the heading and paragraph is 32px but should be 16px based on the surrounding spacing rhythm" is useful.
  • Prioritize impact. Not every pixel matters. Focus on what users will actually notice.
  • Reference the intent. Compare against design tokens, mockups, or stated design goals.

How to Review

Step 1: Capture the Screenshot

Use one of these methods to get a screenshot:

Via browser tool:

browser: screenshot (captures the current page)

Via node screen capture (if available):

nodes: screen_record

Via Peekaboo (macOS):

exec: peekaboo screenshot

User-provided: The user may paste/attach a screenshot directly.

Step 2: Analyze with Vision

Use the image tool to analyze the screenshot:

image: [path or URL to screenshot]
prompt: "Review this UI screenshot for design quality..."
Step 3: Structured Review

Analyze the screenshot against these categories (in priority order):


Review Categories

1. Layout & Spacing

Check for:

  • Consistent spacing rhythm (is everything on the spacing grid?)
  • Alignment — are elements that should be aligned actually aligned?
  • Padding consistency within similar components
  • Container widths and max-widths
  • Responsive behavior (if multiple viewport screenshots available)

Common issues:

  • Inconsistent padding in cards (e.g., 24px top, 16px sides)
  • Elements slightly off-grid (15px instead of 16px)
  • Text not aligned with adjacent elements
  • Sections with wildly different vertical spacing
2. Typography

Check for:

  • Hierarchy — is it clear what's a heading vs body vs caption?
  • Line length — body text should be 45–75 characters per line
  • Line height — too tight or too loose for the font size?
  • Font weight usage — are weights used consistently for the same role?
  • Orphans/widows — single words on their own line in headings

Common issues:

  • Heading that doesn't look like a heading (weight/size too close to body)
  • Body text line length > 80 characters (hard to read)
  • Inconsistent heading sizes across sections
  • All-caps text without letter-spacing adjustment
3. Color & Contrast

Check for:

  • Text/background contrast (does it look readable?)
  • Consistent use of brand colors
  • Color meaning consistency (is the same blue used for links AND errors?)
  • Dark mode issues (if applicable)
  • Hover/active state visibility

Common issues:

  • Light gray text on white background (contrast fail)
  • Primary color used for too many different purposes
  • Borders that are nearly invisible
  • Status colors that conflict (green for danger, red for success)
4. Visual Hierarchy

Check for:

  • Eye flow — where does the eye go first? Is that correct?
  • CTA prominence — is the primary action the most visible element?
  • Information density — too sparse or too crowded?
  • Grouping — are related items visually grouped?
  • White space — is it used intentionally or just leftover?

Common issues:

  • Two equally prominent CTAs competing for attention
  • Important information buried below less important elements
  • Sections that feel disconnected from each other
  • Dense walls of text without visual breaks
Show full SKILL.md (330 more words)Show less
5. Component Quality

Check for:

  • Button sizing and padding consistency
  • Input field styling consistency
  • Card styling consistency (shadows, borders, radius)
  • Icon sizing and alignment with text
  • Image aspect ratios and cropping

Common issues:

  • Buttons with inconsistent padding or height
  • Mixed border-radius values (some 8px, some 12px, some 4px)
  • Icons misaligned with adjacent text baselines
  • Images stretched or poorly cropped
6. Polish & Micro-details

Check for:

  • Hover states exist and are visible
  • Focus states for keyboard navigation
  • Loading states (skeleton screens, spinners)
  • Empty states (what shows when there's no data?)
  • Transitions between states (abrupt vs smooth)
  • Favicon and OG image (if reviewing a full page)

Common issues:

  • No hover state on interactive elements
  • Focus ring removed with no replacement
  • Abrupt content shifts when data loads
  • No empty state — just a blank area
7. Responsive Issues (if multiple viewports available)

Check for:

  • Content readable on mobile (not too small)
  • Touch targets ≥ 44px on mobile
  • Navigation accessible on small screens
  • Images not overflowing containers
  • Horizontal scroll (almost always a bug)

Output Format

Full Review
### Visual QA Review

**Overall impression:** [One sentence — first gut reaction]
**Quality score:** [1-10] / 10

#### 🔴 Critical Issues (fix before shipping)
1. **[Category]:** [Specific issue with exact details]
   → **Fix:** [Actionable recommendation]

#### 🟡 Improvements (should fix)
1. **[Category]:** [Specific issue]
   → **Fix:** [Recommendation]

#### 🟢 Minor Polish (nice to fix)
1. **[Category]:** [Specific issue]
   → **Fix:** [Recommendation]

#### ✅ What's Working Well
- [Specific praise — what's well-executed]
- [Another positive]
Quick Review
### Quick QA: [Page/Component Name]

Score: [X]/10

Top 3 fixes:
1. [Most impactful issue + fix]
2. [Second issue + fix]
3. [Third issue + fix]

Looks good: [What's working]
Comparison Review (Implementation vs Mockup)
### Design vs Implementation Review

**Fidelity score:** [1-10] / 10

#### Deviations Found
1. **[Element]:** Mockup shows [X], implementation has [Y]
   Impact: [High/Medium/Low]
   → **Fix:** [How to match the mockup]

#### Matching Well
- [Elements that accurately match the design]

Review Prompts for Vision Model

Use these prompts with the image tool depending on what you need:

General Review
Review this UI screenshot for design quality. Check spacing consistency,
typography hierarchy, color contrast, visual hierarchy, and component
quality. Be specific about issues — reference exact elements and suggest
fixes. Prioritize by impact.
Spacing & Layout Focus
Analyze the spacing and layout of this UI. Check if elements follow a
consistent spacing grid, if padding within similar components matches,
if alignment is correct, and if the overall spacing rhythm feels right.
Note any elements that appear off-grid or inconsistently spaced.
Comparison Review
Compare these two images. The first is the design mockup, the second is
the implementation. Identify every deviation — differences in spacing,
color, typography, alignment, or missing elements. Rate the fidelity
on a 1-10 scale.
Responsive Check
Review this mobile screenshot for responsive design quality. Check that
text is readable, touch targets are large enough (≥44px), nothing
overflows the viewport, and the layout adapts well to the narrow width.
Accessibility Focus
Review this UI screenshot for visual accessibility. Check text contrast
against backgrounds, focus indicator visibility, touch target sizes,
color-only information (anything that relies solely on color to convey
meaning), and text readability at the shown sizes.

Integration with Build Workflow

After Building a Component
  1. Render the component in the browser
  2. Take a screenshot
  3. Run visual QA review
  4. Fix issues
  5. Re-screenshot and verify
After Building a Full Page
  1. Screenshot at desktop (1440px), tablet (768px), and mobile (375px)
  2. Run responsive review across all three
  3. Run full review on the desktop version
  4. Fix issues, prioritizing critical ones
Comparing to a Mockup
  1. Get the mockup image (Figma export, screenshot, user-provided)
  2. Screenshot the implementation at the same viewport size
  3. Run comparison review
  4. Fix deviations by priority

Examples

Example 1: "Review this landing page screenshot"
image: [screenshot path]
prompt: "Review this landing page for design quality. Check spacing
consistency, typography hierarchy, visual hierarchy (where does the eye
go first?), CTA prominence, color contrast, and overall polish. Be
specific about issues and suggest fixes. Rate 1-10."
Example 2: "Does my implementation match this Figma design?"
image: [mockup.png, implementation.png]
prompt: "Compare these two images. First is the Figma mockup, second
is the implementation. Identify every deviation in spacing, color,
typography, alignment, and missing elements. Rate fidelity 1-10."
Example 3: "Check if this component looks good on mobile"
image: [mobile-screenshot.png]
prompt: "Review this mobile UI. Is text readable? Are touch targets
large enough (≥44px)? Does anything overflow? Is the layout well-adapted
to mobile width? Check contrast and spacing."

© dylanfeltus, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in visual-qa of dylanfeltus/skills.

  • SKILL.md
  • README.md

Open the folder on GitHubat commit b97a48f

Compare with similar skills

Visual QA next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Visual QA compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Visual QA this skilldylanfeltus/skills179—~2.4kAutomated safety check: PassMIT
Vrtmarigold-ui/marigold146—~787Automated safety check: PassMIT
Control UIcursor/plugins10k2 repos~1.2kAutomated safety check: PassNone
Browser QAaffaan-m/ECC275k2 repos~1kAutomated safety check: PassMIT
Design QAplugin87/ux-ui-agent-skills1.5k—~635Automated safety check: PassMIT
UI UX Auditchmonitor/chmonitor299—~2kAutomated safety check: NotesGPL-3.0

Similar skills

  • Vrt

    marigold-ui/marigold

    DST — Trigger the Visual-Regression-Tests (Chromatic) GitHub Actions workflow on the current or a given branch.

    146 GitHub stars~787 tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • Control UI

    cursor/plugins

    Official

    Build or adapt a local browser/CDP harness to drive and inspect a web, IDE, or Electron UI.

    10k GitHub starsUsed in 2 repos~1.2k tokens
    Frontend & DesignAuto-check passed
  • Browser QA

    affaan-m/ECC

    Run automated post-deploy UI verification with a browser automation MCP (claude-in-chrome, Playwright, or Puppeteer): console-error and Core Web Vitals smoke checks, form and auth-flow interaction…

    275k GitHub starsUsed in 2 repos~1k tokens
    Frontend & DesignAuto-check passed
  • Design QA

    plugin87/ux-ui-agent-skills

    Set up or run design QA gates — token + hardcoded-value lint, automated a11y (axe), contrast, visual regression across variants/states/themes/RTL, and the manual a11y checklist.

    1.5k GitHub stars~635 tokensUpdated today
    Frontend & DesignAuto-check passed
  • UI UX Audit

    chmonitor/chmonitor

    Automated UI/UX + accessibility audit for the ClickHouse Monitor dashboard (apps/dashboard-tsr).

    299 GitHub stars~2k tokensUpdated 2 days ago
    Frontend & DesignAuto-check: notes
  • UI Visual Validator

    aiskillstore/marketplace

    Rigorous visual validation expert specializing in UI testing, design system compliance, and accessibility verification.

    430 GitHub starsUsed in 7 repos~2.5k tokens
    Frontend & DesignAuto-check passed

More from dylanfeltus/skills

All 10 skills in this repo
  • App Store Intelligence

    dylanfeltus/skills

    Looks up app details, ratings and reviews and searches the iOS and Mac App Stores through Apple's free iTunes APIs, with a web-search fallback for Google Play.

    179 GitHub stars~2k tokensUpdated 20 days ago
    Auto-check passed
  • AI Image Creative Direction

    dylanfeltus/skills

    Gives prompt templates, a model-selection guide and anti-generic rules for AI-generated visuals: hero images, feature illustrations, OG cards, icons and backgrounds.

    179 GitHub stars~2.6k tokensUpdated 20 days ago
    Auto-check passed
  • Design Token Generator

    dylanfeltus/skills

    Generates type scales, color palettes, spacing systems, WCAG contrast checks and dark mode palettes from formulas, as CSS custom properties, a Tailwind config or JSON tokens.

    179 GitHub stars~2.9k tokensUpdated 20 days ago
    Auto-check passed
  • Hacker News Search

    dylanfeltus/skills

    Searches and monitors Hacker News stories, comments and users through the free Algolia HN Search API, with tag, points and date filters.

    179 GitHub stars~1.7k tokensUpdated 20 days ago
    Auto-check passed
  • Framer Motion (Motion) patterns for React: spring presets, staggers, layout animations, micro-interactions, scroll effects and page transitions, with performance rules.

    179 GitHub stars~3k tokensUpdated 20 days ago
    Auto-check passed
  • Privacy.com Virtual Cards

    dylanfeltus/skills

    Creates, updates, and monitors Privacy.com virtual payment cards with spending limits for an agent making controlled purchases.

    179 GitHub stars~2.2k tokensUpdated 20 days ago
    Auto-check passed

Questions about Visual QA

What does Visual QA do?

Use vision models to self-review screenshots against design intent. Visual QA is an agent skill from dylanfeltus/skills. Use vision models to self-review screenshots against design intent.

When should I use Visual QA?

Visual QA fits situations like: reviewing designs; comparing implementations to mockups; doing pre-ship QA.

How do I install Visual QA in Claude Code?

Run `npx skills add dylanfeltus/skills --skill visual-qa -a claude-code`. Or copy the skill folder (visual-qa in dylanfeltus/skills) into .claude/skills/visual-qa in your project. Claude Code loads it when a task matches its description.

How do I install Visual QA in Codex?

Run `npx skills add dylanfeltus/skills --skill visual-qa -a codex`. Or copy the skill folder (visual-qa in dylanfeltus/skills) into .agents/skills/visual-qa in your project. Codex loads it when a task matches its description.

Can I use Visual QA in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add dylanfeltus/skills --skill visual-qa -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/visual-qa, .gemini/skills/visual-qa, .github/skills/visual-qa and .opencode/skills/visual-qa in your project.

What does Visual QA need to run?

Going by SKILL.md and its folder, Visual QA needs the command-line tools its instructions call (go).

Does Visual QA access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Visual QA safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Visual QA use?

Visual QA is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Visual QA use?

About 2.4k tokens (SKILL.md is roughly 9.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Visual QA?

Skills that share tags, products or a category with Visual QA: Vrt (marigold-ui/marigold, 146 stars), Control UI (cursor/plugins, 10k stars), Browser QA (affaan-m/ECC, 275k stars) and Design QA (plugin87/ux-ui-agent-skills, 1.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Visual QA?

dylanfeltus (a GitHub user) maintains it in dylanfeltus/skills, which has 179 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on September 17, 2026.

Source: dylanfeltus/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.