skill-timeyour-agentskills-audit-collection-visual-qa · by Install
$ agentstack add skill-timeyour-agentskills-audit-collection-visual-qa ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-timeyour-agentskills-audit-collection-visual-qa) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Visual QA
Use this skill when the user wants to know whether a page feels designed, credible, consistent, and conversion-ready.
Do
- Identify product category and intended user scenario.
- Inspect first viewport, hierarchy, spacing, typography, color, imagery, components, and responsive behavior.
- Inventory visible media, document links, embeds, and product screenshots when they affect trust or layout.
- Flag AI slop: generic gradients, repeated icon cards, fake proof, vague copy, mismatched components, irrelevant imagery.
- Use measurable aesthetic heuristics for spacing, hierarchy, color roles, visual weight, component consistency, and Figma/code fidelity when evidence exists.
- Separate screenshot-backed findings from source-only findings.
- Compare against the right product pattern: local service, SaaS, portfolio, directory, dashboard, lifestyle commerce, etc.
- For product-pattern questions (scenario, outcome, next-step, inspiration vs. action), invoke
/ai-product-auditor use../ai-product-audit/references/product-pattern-rubric.md.
- Produce section-level issue cards and copyable design-fix prompts.
- Use
S0-S4severity and include regression checks for visual fixes. - For multi-section reviews, emit progress updates after each major page section or viewport group.
References
references/aesthetic-quality-audit.mdreferences/aesthetic-metrics.mdreferences/webpage-audit-rubric.md../audit/references/progressive-reporting.mdfor long visual audits../audit/references/web-surface-discovery.mdwhen media, documents, or embeds need inventory
Output
- Aesthetic audit summary.
- Visual score with evidence level.
- Pattern fit table.
- AI slop signals.
- S0-S4 severity.
- Issue cards.
- Copyable fix pack.
- Regression checks.
- Lessons.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: timeyour
- Source: timeyour/agentskills-audit-collection
- License: MIT
- Homepage: https://github.com/timeyour/agentskills-audit-collection
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.