Visual Acceptance Review

Community

Jason904

visual-acceptance-review

This skill should be used after spec-compliance-review and before visual-diff-fix. It captures or analyzes actual browser screenshots and compares them against the reference design, responsive spec, visual tokens, layout spec, component tree, UI type, layout paradigm, and asset strategy. It outputs structured visual diff reports and fix-tasks without modifying code.

Overview

Publisher	Jason904
Repository	`ui-skill-lab`
Skill name	`visual-acceptance-review`
Stars	144
Forks	9
Bundled files	14
License	MIT
Links	Skill source Repository

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.
14 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by Jason904 on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/Jason904/ui-skill-lab/tree/main/.codex/skills/visual-acceptance-review
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/Jason904/ui-skill-lab/tree/main/.codex/skills/visual-acceptance-review

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

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/Jason904/ui-skill-lab.git /tmp/ui-skill-lab
mkdir -p .claude/skills
cp -r /tmp/ui-skill-lab/.codex/skills/visual-acceptance-review .claude/skills/visual-acceptance-review

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Visual Acceptance 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 Visual Acceptance 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 Visual Acceptance 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.

Version: 2.0.0

visual-acceptance-review

Validate real browser rendering against the approved visual contract.

This skill performs screenshot-based visual acceptance and produces structured fix tasks.

It does not modify code. It does not redesign UI. It does not replace spec-compliance-review.

Trigger Conditions

Use this skill when:

implementation exists
spec-compliance-review has passed or user requests diagnostic-only review
a dev server URL is available
Playwright or screenshot capability is available
user asks to compare implementation against reference image
user asks for visual acceptance report or visual diff tasks

Required Inputs

reference.png
dev server URL or actual screenshot
UI workflow files under ui/03_visual_spec/
visual spec review files under ui/04_visual_spec_review/
design system files under ui/05_design_system/

Recommended:

spec compliance outputs under ui/06_spec_review/
package.json
playwright.config.*

Preflight Gates

Stop if:

ui/04_visual_spec_review/spec-review-report.md says Fail
ui/06_spec_review/compliance-report.md says Fail, unless user explicitly requests diagnostic-only mode
no screenshot capability exists and no actual screenshot is provided

Source of Truth

reference.png
actual browser screenshot
visual-analysis.md / UI Type Classification
layout-spec.md / Layout Paradigm
implementation-risks.md / Asset Strategy
component-tree.md
tokens.json
responsive-spec.md
05_design_system/
browser health logs

Main Workflow

Run preflight gates.
Capture or load screenshots.
Compare overall visual match.
Validate UI Type, Layout Paradigm, and Asset Strategy.
Compare regions using layout-spec.md.
Compare components using component-tree.md.
Compare colors, typography, spacing, and density.
Validate responsive screenshots against responsive-spec.md.
Capture browser health issues.
Generate reports and fix-tasks.json.

Hard Rules

Do not modify code.
Do not modify visual spec files.
Do not modify design system files.
Do not modify OpenSpec files.
Do not redesign UI.
Do not claim pixel-precision if no script-backed comparison exists.
Do not compare mobile/tablet directly against desktop reference.png.
Do not allow actual rendering to change UI Type, Layout Paradigm, or Asset Strategy.
Do not treat passing tests as visual acceptance.
Do not treat internal spec consistency as visual acceptance.
If a photorealistic/panorama/scene-led main visual is missing or redrawn with CSS/SVG/chart/map, mark as Fail.

Output

Write:

text
07_validation/visual_acceptance/
  screenshots/
    reference.png
    actual-desktop-hd.png
    actual-desktop.png
    actual-tablet.png
    actual-mobile.png
  comparison-report.md
  acceptance-summary.md
  fix-tasks.json
  region-diffs/
    overview.md
    layout.md
    components.md
    colors.md
    typography.md
    spacing.md
    responsive.md
    asset-strategy.md
    browser-health.md
  console-errors.log
  network-errors.log
  blocked-report.md

blocked-report.md is only required when preflight blocks the review.

Supporting Files

Read these references directly:

references/acceptance-workflow.md
references/preflight-gates.md
references/screenshot-rules.md
references/comparison-rules.md
references/ui-type-asset-validation.md
references/confidence-rules.md
references/fix-task-schema.md
references/external-reviewer-usage.md
references/output-files.md

Examples:

examples/acceptance-summary.example.md
examples/comparison-report.example.md
examples/region-diff.example.md
examples/fix-tasks.example.json
examples/blocked-report.example.md

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 Visual Acceptance Review AI skill do?

Why use Visual Acceptance Review on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Jason904/ui-skill-lab/tree/main/.codex/skills/visual-acceptance-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 Visual Acceptance 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 Visual Acceptance Review?

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

Is the Visual Acceptance Review AI skill free?

Yes. It is published on GitHub by Jason904 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

Brand Discovery

affaan-m

CommunityPopular

Use when a brand needs to discover or articulate its identity through structured multi-session interviews. Covers purpose, positioning, audience, personality, voice, narrative, and founder-brand…

Competitive Platform Analysis

affaan-m

CommunityPopular

Use when scoping a competitive landscape — identifying, categorising, and score-filtering a competitor set before any benchmarking begins. Decides who counts as a competitor, which tier they belong…

Frontend Slides

Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a…

Plan Canvas

Open plans and HTML artifacts in a local browser canvas where the human annotates elements, chats, and approves or requests changes without leaving the page. Use when presenting a plan for review, or…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

visual-acceptance-review

Trigger Conditions

Required Inputs

Preflight Gates

Source of Truth

Main Workflow

Hard Rules

Output

Supporting Files

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now