Visual Validation logo

Visual Validation

Community
alinaqi
visual-validation

Autonomous screenshot verification — captures, compares, and AI-evaluates UI changes for visual regressions

Overview

Publisheralinaqi
Repositorymaggy
Skill namevisual-validation
Stars
707
Forks
57
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Visual Validation 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/alinaqi/maggy/tree/main/skills/visual-validation
  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/alinaqi/maggy.git /tmp/maggy
mkdir -p .claude/skills
cp -r /tmp/maggy/skills/visual-validation .claude/skills/visual-validation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Visual Validation 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 Visual Validation 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 Visual Validation 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.

Visual Validation — Autonomous Screenshot Verification

Philosophy

Every UI change should be visually verified before it ships. Peekaboo captures pixel-accurate screenshots. The system compares before/after and flags visual regressions. No manual "looks good to me" — the machine verifies what the machine built.

Autonomous Flow

static/* files modified (detected by auto-review-hook or E2E testkit)
    ↓
peekaboo image --mode screen → ~/.maggy/visual-verify/after-{ts}.png
    ↓
Compare with latest baseline (previous after-*.png)
    ↓
AI evaluation: Gemini Flash analyzes screenshot for visual regressions
    ↓
Report: CLEAN or REGRESSION_DETECTED with specific issues

Quick Commands

bash
# Install
brew install steipete/tap/peekaboo

# Capture full system screenshot
peekaboo image --mode screen --retina --path /tmp/screen.png

# Capture specific window
peekaboo image --mode window --app "Google Chrome" --path /tmp/window.png

# Verify Maggy dashboard after code change
peekaboo image --mode window --app "Google Chrome" --path ~/.maggy/visual-verify/after-$(date -u +%Y%m%d-%H%M%S).png

# Compare two screenshots
ls -la ~/.maggy/visual-verify/after-*.png  # review before/after pairs

Autonomous Verification Flow (Claude Code)

bash
# After making any static/ file change, Claude should:
1. git add maggy/maggy/static/ && git diff --stat HEAD  # check what changed
2. Restart Maggy: lsof -ti :8080 | xargs kill && python3 -m maggy.main &
3. Wait for health: curl -s http://localhost:8080/api/health
4. Capture screenshot: peekaboo image --mode screen --path ~/.maggy/visual-verify/after-$(date -u +%Y%m%d-%H%M%S).png
5. Compare with latest baseline in ~/.maggy/visual-verify/
6. AI evaluation: ~/bin/gemini-api --flash "Analyze this screenshot for visual regressions"
7. Report findings

Maggy Dashboard Verification

bash
# One-shot verification
curl -s http://localhost:8080/api/health && \
peekaboo image --mode screen --path ~/.maggy/visual-verify/verify.png && \
echo "✓ Dashboard verified — screenshot at ~/.maggy/visual-verify/verify.png"

Integration Points

Auto-Review Hook (already wired)

  • Detects static/ changes in git diff
  • Auto-captures Peekaboo screenshot
  • Saves before/after pairs in ~/.maggy/visual-verify/

E2E Testkit Plugin

  • Visual regression testing as part of POST /api/testkit/run
  • Compares screenshots against baselines
  • Flags pixel differences above threshold

Build-in-Public Plugin

  • Peekaboo screenshots replace AI-generated images
  • Real product captures for LinkedIn/X posts

When to Use

ScenarioCommand
After static/ changepeekaboo image --mode screen --path ~/.maggy/visual-verify/after.png
Before committing UI changeRun verification flow above
Reviewing dashboardScreenshot + AI analysis
Build-in-public postAuto-captured by plugin
Cross-browser checkpeekaboo image --mode window --app "Safari"

Frequently asked questions

What does the Visual Validation AI skill do?

Autonomous screenshot verification — captures, compares, and AI-evaluates UI changes for visual regressions

Why use Visual Validation on TypingMind?

Because you install it once and use it with any model. Visual Validation 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 Visual Validation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/alinaqi/maggy/tree/main/skills/visual-validation. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Visual Validation?

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 Visual Validation?

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

Is the Visual Validation AI skill free?

Yes. It is published on GitHub by alinaqi 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 👇