visual-tester — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited visual-tester (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Extends the agent-browser skill with visual testing workflows for UI/UX bug detection.
# One-command visual review
bash .claude/scripts/visual-review.sh https://localhost:3000
# Review a specific section
bash .claude/scripts/visual-review.sh https://localhost:3000 "#hero"agent-browser --session visual-review open https://localhost:3000
agent-browser --session visual-review wait --load networkidle
agent-browser --session visual-review screenshot --annotate
# Analyze the annotated screenshot for visual issues
# Report findings with @eN references
agent-browser --session visual-review closeagent-browser --session visual-review open https://localhost:3000
agent-browser --session visual-review wait --load networkidle
agent-browser --session visual-review snapshot -i -s "[data-testid='section-hero']"
agent-browser --session visual-review screenshot --annotate
agent-browser --session visual-review close# Capture baseline
agent-browser --session visual-baseline open https://localhost:3000
agent-browser --session visual-baseline wait --load networkidle
agent-browser --session visual-baseline screenshot baseline.png
agent-browser --session visual-baseline close
# After changes, capture and diff
agent-browser --session visual-after open https://localhost:3000
agent-browser --session visual-after wait --load networkidle
agent-browser --session visual-after diff screenshot --baseline baseline.png
agent-browser --session visual-after close# Desktop capture
agent-browser --session desktop open https://localhost:3000
agent-browser --session desktop wait --load networkidle
agent-browser --session desktop screenshot --annotate
# Mobile capture (iOS Simulator)
agent-browser -p ios --device "iPhone 16 Pro" open https://localhost:3000
agent-browser -p ios screenshot mobile.png
agent-browser -p ios close
agent-browser --session desktop closeUse the project's data-testid convention to scope reviews:
| Section | Selector |
|---|---|
| Hero | [data-testid="section-hero"] |
| Benefits | [data-testid="section-benefits"] |
| FAQ | [data-testid="section-faq"] |
| Convert Form | [data-testid="convert-form"] |
| Pricing | [data-testid="convert-pricing"] |
Always report findings in this structure:
**Visual Review: [page/component]**
**Findings:**
- [CRITICAL] @eN — description of issue
- [WARNING] @eN — description of issue
- [INFO] @eN — description of issue
**Screenshots:** path/to/screenshot.png
**Recommendation:** actionable fixSeverity levels:
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.