The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes shell scripts (init-artifact.sh, bundle-artifact.sh) and Node.js utilities (sloplint.mjs) to manage the project lifecycle, including scaffolding React projects, bundling artifacts, and performing static design audits. These are standard operations for a professional frontend development toolkit.
[EXTERNAL_DOWNLOADS]: The skill automates the installation of standard industry dependencies (such as React 19, Vite, Tailwind CSS v4, and Lucide React) from the npm registry. It also leverages well-known services like Unsplash, Picsum, and Simple Icons for project assets, and integrates with the vendor's own CLI tool (ima2) for image generation. These sources are considered trusted or well-known and do not present a security risk.
[DYNAMIC_EXECUTION]: The initialization scripts dynamically generate project configuration files (e.g., vite.config.ts, tsconfig.json) and boilerplate source code based on user-specified project names. This behavior is expected and required for the skill's primary function of scaffolding new applications.
[INDIRECT_PROMPT_INJECTION]:
Ingestion points: The skill processes user-provided design briefs and brand references to determine the visual direction and technical requirements for the frontend build.
Boundary markers: The skill does not explicitly implement boundary markers or delimiters for user-provided data within its shell or Node.js scripts.
Capability inventory: The skill possesses capabilities to write to the local file system and execute shell commands through its provided utility scripts.
Sanitization: The skill relies on the agent's internal reasoning and its own design guidelines rather than technical sanitization within the scripts to handle user instructions.

noslop-frontend