jason904/ui-skill-lab/visual-acceptance-review
Claude Code and agent skill by jason904/ui-skill-lab
- community
Checking that the SKILL.md file is still in the repository.
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.
Install
npx vskill@latest install jason904/ui-skill-lab/visual-acceptance-reviewSKILL.md
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.jsonplaywright.config.*
Preflight Gates
Stop if:
ui/04_visual_spec_review/spec-review-report.mdsays Failui/06_spec_review/compliance-report.mdsays 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 Classificationlayout-spec.md / Layout Paradigmimplementation-risks.md / Asset Strategycomponent-tree.mdtokens.jsonresponsive-spec.md05_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:
blocked-report.md is only required when preflight blocks the review.
Supporting Files
Read these references directly:
references/acceptance-workflow.mdreferences/preflight-gates.mdreferences/screenshot-rules.mdreferences/comparison-rules.mdreferences/ui-type-asset-validation.mdreferences/confidence-rules.mdreferences/fix-task-schema.mdreferences/external-reviewer-usage.mdreferences/output-files.md
Examples:
examples/acceptance-summary.example.mdexamples/comparison-report.example.mdexamples/region-diff.example.mdexamples/fix-tasks.example.jsonexamples/blocked-report.example.md
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/visual-acceptance-review/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/jason904/ui-skill-lab/visual-acceptance-review)