The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes dynamic context injection to execute npx shadcn@latest info --json when the skill is initialized. This provides the agent with necessary project metadata such as Tailwind version, framework, and import aliases. Additionally, shell command execution is strictly limited via allowed-tools configuration to the shadcn CLI through package runners.
[EXTERNAL_DOWNLOADS]: The skill enables downloading source code for UI components from external sources, including public GitHub repositories (owner/repo/item) and community registries. The skill follows security best practices by explicitly instructing the user to audit and verify all added files for correctness and potential malicious patterns before proceeding.
[SAFE]: The skill implements strong security controls by restricting tool access and providing clear guidance on auditing external code. The use of remote resources is confined to well-known domains and official registries.

shadcn