The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The scripts/fetch-idls.js script fetches Web IDL definitions from the official webmachinelearning organization on GitHub. These downloads target established technical standards repositories and are used to provide the agent with accurate technical signatures.
[COMMAND_EXECUTION]: The package utilizes an npm postinstall script to run scripts/install.js. This script synchronizes documentation templates to the user's project root, which is the primary intended function of this package.
[SAFE]: The skill instructions explicitly direct the AI agent to advocate for security best practices, such as using DOMPurify to sanitize untrusted LLM outputs before rendering them in a web interface.
[SAFE]: No obfuscation, data exfiltration patterns, or unauthorized privilege escalation attempts were detected. All external resource references are to well-known and trusted technology organizations.

built-in-ai