Rebuild website effects in your repo or Design with exact behavior and original code. Use when asked to remix, borrow, port, recreate, explain an effect, or /remix source into ours.
87%
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 has the agent drive a user-specified source website in a browser and read its rendered DOM, CSS, and JavaScript, which is arbitrary outsider-authored web content the agent must actively fetch rather than a feed outsiders can push into.
BuilderIO/agent-native
cf9ff10
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.