The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands to search the project directory and inspect file contents.
Evidence: Uses rg (ripgrep) to search for animation patterns in .css, .tsx, .jsx, .vue, and .svelte files.
Evidence: Uses cat package.json to identify installed dependencies.
Evidence: Utilizes playwright-cli for browser-based verification, including navigation and screenshot capture.
[EXTERNAL_DOWNLOADS]: The skill evaluates and recommends the addition of external animation libraries.
Evidence: References well-known packages such as motion (formerly Framer Motion), gsap, and @formkit/auto-animate as potential additions to the project.
Evidence: Directs the agent to research current library APIs using external search protocols.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted local data to inform its code generation tasks.
Ingestion points: Reads configuration and source code from package.json, CSS files, and framework-specific component files (*.tsx, *.jsx, *.vue, *.svelte).
Boundary markers: No explicit delimiters or instructions to ignore embedded content are provided when reading files.
Capability inventory: The skill has the ability to execute shell commands (rg, cat), modify project source code (applying motion passes), and automate browser sessions (playwright-cli).
Sanitization: No sanitization or validation logic is defined for the content extracted from local files before it is processed by the agent.

enhance-motion