The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Fetches automated refactoring scripts from the official React GitHub repository (reactjs/react-codemod) to perform transformations like renaming lifecycle methods and updating imports.
[REMOTE_CODE_EXECUTION]: Executes JavaScript transformation logic fetched from remote URLs using the npx jscodeshift command.
[COMMAND_EXECUTION]: Invokes shell commands through npx to run jscodeshift and codemod tools for codebase transformations.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided source code which could potentially contain malicious instructions intended to influence the agent's behavior during the refactoring process.
Ingestion points: The skill ingests and processes React source code files located in the src/ directory (e.g., SKILL.md).
Boundary markers: No specific boundary markers or instructions to ignore embedded content within the source code are defined.
Capability inventory: The skill uses npx for shell execution and has the ability to write/modify files on the local file system via codemod scripts.
Sanitization: There is no evidence of sanitization or validation of the source code content before it is processed by the transformation tools.

react-modernization