The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use standard system tools (rg for ripgrep and ls) to identify existing error-handling patterns in the codebase. These commands are used for context gathering and do not involve untrusted input or risky operations.
[EXTERNAL_DOWNLOADS]: The skill references industry-standard, well-known packages like zod, lucide-react, sonner, and @tanstack/react-query. These are typical dependencies for the described tech stack and are used in a benign manner.
[PROMPT_INJECTION]: The use of 'CRITICAL' in the documentation is for instructional emphasis (guiding the agent's workflow) and does not attempt to bypass system safety guidelines or override agent behavior maliciously.
[SAFE]: The content promotes security best practices, such as validating user input with Zod and explicitly advising against including sensitive information in production error messages.

error-handling