The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run various shell commands for project initialization and component management, including npx shadcn@latest init and npm install.
[DYNAMIC_EXECUTION]: The documentation directs the agent to execute specific Python scripts (scripts/shadcn_add.py and scripts/tailwind_config_gen.py) shipped with the skill. As these scripts' source code is not included in the provided analysis context, their behavior remains unverified.
[EXTERNAL_DOWNLOADS]: The install_command in the skill metadata uses curl to fetch the skill definition from the author's GitHub repository.
[INDIRECT_PROMPT_INJECTION]: The skill architecture relies on a series of reference documents (e.g., references/shadcn-components.md) that are used as instructions for the agent, creating a surface where malicious content could influence the agent's behavior.
Ingestion points: Multiple markdown files located in the references/ directory as specified in the SKILL.md file.
Boundary markers: None; the instructions are directly consumed as authoritative context.
Capability inventory: The skill provides the ability to execute both shell commands and Python scripts.
Sanitization: No content validation or sanitization process for the referenced files is mentioned.

shadcn-tailwind