The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Mentions the installation of well-known development tools and official addons from the Storybook ecosystem, specifically @storybook/addon-a11y and @storybook/test-runner. These are standard tools for accessibility testing in frontend development environments.
[COMMAND_EXECUTION]: Provides standard shell and PowerShell commands to facilitate the discovery of design token configuration files (e.g., tokens.json, tailwind.config.js) within a local project directory. The commands are scoped to exclude common dependency and build directories like node_modules or .next.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (Category 8) because it is designed to ingest and process external data from design token files.
Ingestion points: Files discovered via the provided find commands, such as tailwind.config.js, theme.ts, or tokens.json.
Boundary markers: None identified in the skill body.
Capability inventory: Execution of shell commands for file discovery and implied reading of the discovered files for auditing.
Sanitization: No explicit sanitization logic is provided for the content of the token files being audited. This exposure is typical for auditing tools and is inherent to the skill's primary purpose of validating external configuration data.

design-system