The Agent Skills Directory

[SAFE]: The skill operates entirely within the local repository environment to perform UI refactoring. It does not attempt to download external scripts or execute code from untrusted remote sources.
[PROMPT_INJECTION]: The skill is designed to process external data in the form of codebase files and documentation, which constitutes an indirect prompt injection surface.
Ingestion points: Local source code, style guides, and design documentation files identified through grep searches.
Boundary markers: There are no explicit delimiters or instructions provided to ignore potential malicious prompts embedded within the files being audited.
Capability inventory: The skill allows the agent to read project files, perform code refactoring (write), and execute local development tools such as linters and type-checkers.
Sanitization: The instructions do not include specific sanitization steps for the content extracted from the files before the agent analyzes them.
[COMMAND_EXECUTION]: The skill references the use of standard development tools (grep, lint, type-check) for codebase analysis and quality assurance. These commands are typical for the stated purpose of UI normalization and do not represent unauthorized privilege escalation.

normalize