The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill automates the setup of new projects by downloading dependencies from the npm registry. Specifically, init-nextjs-shadcn.sh installs packages such as class-variance-authority, clsx, tailwind-merge, lucide-react, next-themes, and tailwindcss-animate. It also uses npx to run create-next-app and shadcn initialization commands. These operations target well-known technology services and trusted organizations.
[COMMAND_EXECUTION]: Several scripts perform command-line operations to facilitate project management. analyze-codebase.py and detect-hardcoded-values.sh use system tools to scan directory structures and file contents. init-nextjs-shadcn.sh executes shell commands to initialize project directories, manage packages, and generate configuration files using heredocs.
[INDIRECT_PROMPT_INJECTION]: As a tool designed to analyze and process existing frontend codebases, the skill possesses an ingestion surface for untrusted data.
Ingestion points: The analyze-codebase.py and detect-hardcoded-values.sh scripts read the content of all files within a user-specified directory.
Boundary markers: The scripts do not use explicit boundary markers or 'ignore' instructions for the content they process; they rely on regular expressions and grep patterns.
Capability inventory: The skill has the capability to write files, install npm packages, and execute shell commands via the agent.
Sanitization: Content is processed via regex for pattern detection (e.g., framework versions, hardcoded colors) without extensive sanitization before being summarized into reports for the agent.

nextjs-shadcn-builder