The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes several shell commands to manage the recording workflow, including starting a development server, running a dynamically generated Node.js script, and using FFmpeg for video processing and thumbnail extraction. It also uses chmod +x to ensure internal scripts are executable.
[EXTERNAL_DOWNLOADS]: The skill checks for and installs the @playwright/test package and the Chromium browser via npm and npx if they are not already present. These are industry-standard tools from a well-known source.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface (Category 8) because its core functionality depends on reading and analyzing project source code to generate automation logic. 1. Ingestion points: The agent reads files such as GameScene.js, EventBus.js, and Constants.js. 2. Boundary markers: No delimiters or warnings are used when reading these files. 3. Capability inventory: The skill has the ability to execute shell commands, install software packages, and write files to the local disk. 4. Sanitization: No validation or sanitization of the source code content is performed before it is used to influence the generated script logic.

record-promo