The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown documentation and reference files. It does not include any executable scripts, binaries, or configuration files that could autonomously run code.\n- [COMMAND_EXECUTION]: The documentation references the usage of the shadcn CLI through standard package runners like npx, pnpm dlx, and bunx. These are provided as examples for the user's manual development workflow and do not represent a security threat.\n- [EXTERNAL_DOWNLOADS]: The skill contains URLs pointing to ui.shadcn.com and related subdomains for documentation, component previews, and registry references. These are well-known and trusted sources within the modern web development ecosystem.\n- [PROMPT_INJECTION]: The content uses instructional imperatives such as "ALWAYS" and "NEVER" to enforce technical standards and best practices for UI development. These instructions are focused on software architecture and ownership models and do not attempt to bypass agent safety filters or override system constraints.

shadcn-core-blocks