Reviews layout density, theme adherence, typography, spacing, search-chrome placement, accessibility modes, and visual consistency. Use during visual layout or CSS adjustments.
85%
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 skill's required workflow includes reviewing pull requests and posting a Review record comment on the PR after a completed review (line 15), which means ingesting GitHub PR text that external contributors can author, while the rest of the workflow reads only first-party repo docs and local browser output.
BigSimmo/PsychSift
fada614
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.