The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides Python automation scripts (frontend_scaffolder.py, component_generator.py, bundle_analyzer.py) intended for project scaffolding and analysis. These tools are designed to run within the user's workspace to facilitate development workflows.
[DYNAMIC_EXECUTION]: The skill generates React components and project configuration files from hardcoded templates. The generation logic is localized and does not incorporate untrusted external input into executable code.
[INDIRECT_PROMPT_INJECTION]: The skill includes a bundle analyzer that processes local project files.
Ingestion points: The bundle_analyzer.py script reads package.json and source code files within the specified project directory.
Boundary markers: None explicitly used in data reading, but the script results are processed by the agent.
Capability inventory: The skill possesses file-write capabilities (via scaffolding/generation scripts) and file-read capabilities (via analysis scripts).
Sanitization: Robust path sanitization is implemented via a safe_user_path function that prevents directory traversal by ensuring all file operations are relative to the current working directory.
[SAFE]: No obfuscation, hardcoded credentials, persistence mechanisms, or network exfiltration patterns were identified. All external resource references target well-known and trusted package registries.

senior-frontend