How to create and run agent actions. Actions are the single source of truth for app operations — the agent calls them as tools and frontend code calls them through client hooks. Use when creating a new action, adding an API integration, or wiring up frontend data fetching.
81%
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 canonical home for this skill is actions in BuilderIO/agent-native
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 is agent-driven: the agent actively fetches public web pages via `web-search`, `web-request`, and `run-code` with `webRead()`/`webFetch()`, which are arbitrary outsider-authored content it must select, so exposure is low.
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.