The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes dynamic context injection in SKILL.md to run npx shadcn@latest info --json at load time. This allows the agent to automatically synchronize with the local project configuration, framework, and installed components.
[EXTERNAL_DOWNLOADS]: The skill facilitates downloading UI components and fetching documentation from external sources. It directs the agent to use npx shadcn@latest docs <component> to retrieve documentation and example URLs from official and community registries. The shadcn CLI is a well-known tool used for these operations.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. It instructs the agent to fetch and process external data from documentation and example URLs. This data, being untrusted external content, could potentially contain malicious instructions designed to influence the agent's actions during component creation or modification.
Ingestion points: External URLs fetched via npx shadcn@latest docs and npx shadcn@latest view (referenced in SKILL.md).
Boundary markers: None identified in the instructions for handling the ingested documentation content.
Capability inventory: The skill has access to shell commands via npx, file system modification (adding/updating components), and network operations for fetching documentation.
Sanitization: There are no instructions provided to sanitize or validate the content of the fetched documentation before processing.

shadcn