The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool to run local scripts which execute development commands including npx eslint, npm run lint, and npm run type-check for code validation purposes.
[PROMPT_INJECTION]: The skill processes user-controlled source code from the frontend/src directory, which establishes an indirect prompt injection surface.
Ingestion points: The scripts check-file-size.sh, check-naming.sh, and check-imports.sh use find and grep to read the contents of code files.
Boundary markers: There are no specific delimiters or system instructions used to separate the analyzed code content from the agent's instructions.
Capability inventory: The agent has access to Bash, Read, Grep, and Glob tools, and executes standard project commands via the shell.
Sanitization: Analyzed code content is read and processed without filtering or sanitization before being presented in the agent's context.

quality-reviewer