Standardizes visual audits, multi-viewport ergonomics, composited contrast, and behavioral testing for web apps. Use to verify web UI changes, responsive design across viewports, zoom reflow, or conduct comparative audits; separates automated smoke from human visual acceptance.
84%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow drives a browser against the web app under test and reads its DOM snapshots, console, and network output, so any outsider-authored content rendered by that app (for example, user comments) enters the agent's context only after the agent navigates to pages it chose to test.
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.