UXLens
v1.2.0Audit websites for UX, UI, and accessibility issues with 600+ checkpoints, offering detailed reports, full site crawls, and redesign comparisons.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Benign
medium confidencePurpose & Capability
The SKILL.md describes a UX/UI/a11y auditing API (POSTs to https://uxlens.io/api/audit, returns structured JSON and Core Web Vitals), which matches the skill name and description. However, the registry metadata at the top of the package claims no required env vars and no homepage/source while SKILL.md requires UXLENS_API_KEY and provides a homepage and GitHub source. This is an inconsistency in metadata (likely an omission) that should be clarified.
Instruction Scope
SKILL.md instructs setting a single API key and shows example POST requests to uxlens.io. It does not tell the agent to read arbitrary local files, other environment variables, or to exfiltrate data to unexpected endpoints. The claim that 'API keys are never stored by the skill' is an assertion only — there is no code to verify behavior.
Install Mechanism
This is an instruction-only skill with no install spec and no code files, so nothing is written to disk by an installer. That minimizes install-time risk.
Credentials
The only runtime secret declared in SKILL.md is UXLENS_API_KEY, which is proportionate for calling a third-party audit API. The registry metadata not listing this required env var is a mismatch and should be corrected so users know they must provide the key.
Persistence & Privilege
The skill has default privileges (not always: true), is user-invocable, and can be invoked autonomously (platform default). It does not request persistent system-level presence or access to other skills' configs.
Assessment
The skill appears to do what it claims (calls uxlens.io with a single API key). Before installing: (1) confirm the missing registry metadata — SKILL.md requires UXLENS_API_KEY but the package metadata lists none; ask the publisher to correct this, (2) verify the homepage (https://uxlens.io) and the GitHub source linked in SKILL.md to ensure the service and repo are legitimate, (3) only provide an API key with appropriate scope/limits and use a key you can revoke if needed, (4) test on non-sensitive sites first, and (5) remember that because this is instruction-only there is no code to audit in the package — review the external repo and service privacy/storage practices if you need stronger assurance.Like a lobster shell, security has layers — review code before you run it.
accessibilityauditcore-web-vitalslatestseouxweb
UXLens — UX Audit Skill for AI Agents
Audit any website for UX, UI, and accessibility issues in seconds. Get a structured report with specific issues, severity levels, and prioritized fixes — delivered as an agent_summary the agent can read and act on directly.
Install once. Use in every project.
What This Skill Does
- Runs 600+ UX, UI, and accessibility checkpoints against any URL
- Delivers structured JSON output with
agent_summary— a paragraph the agent can read and act on - Crawls entire sites automatically via sitemap discovery
- Compares before/after redesigns with diff mode
- Returns Core Web Vitals (LCP, CLS, FCP, INP) with pass/fail status
- Checks WCAG accessibility compliance with specific violation locations
Setup
- Get a free API key at https://uxlens.io/dashboard (no credit card required)
- Set
UXLENS_API_KEYenvironment variable with your key
export UXLENS_API_KEY=your_key_here
Pricing
| Tier | Price | What you get |
|---|---|---|
| Free | $0/mo | 5 audits/month |
| Developer | $9.99/mo | 500 audits/month |
| Pro | $29/mo | 3,000 audits/month |
API Examples
Single URL Audit
POST https://uxlens.io/api/audit
{ "url": "https://example.com" }
Full Site Crawl
POST https://uxlens.io/api/audit
{ "url": "https://example.com", "crawl_all": true }
Diff Mode (before/after redesign)
POST https://uxlens.io/api/audit
{ "url": "https://example.com", "compare_to": "uxl_a1b2c3d4" }
Response Fields
| Field | Description |
|---|---|
overall | 0-5 score with status label |
agent_summary | One-paragraph summary — safe to read aloud |
audit_id | Use with compare_to for diff mode |
uxIssues | Usability heuristic violations |
uiIssues | Spacing, typography, alignment issues |
a11yIssues | WCAG accessibility violations |
lighthouse | Performance, Accessibility, Best Practices, SEO (0-100) |
coreWebVitals | LCP, CLS, FCP, INP with pass/fail |
mobileResponsive | Viewport, touch targets, font sizes |
metaCompleteness | OG tags, Twitter cards, canonical, favicon |
Who Uses This
- Freelance developers auditing client sites before handoff
- Indie hackers checking landing pages before launch
- AI agents building websites and validating quality automatically
- Small agencies running quick UX audits
Security & Privacy
- API keys are never stored by the skill
- All audit data is processed transiently
- MIT-0 license
- Homepage: https://uxlens.io
Comments
Loading comments...
