The Agent Skills Directory

[SAFE]: The skill follows security best practices for the Convex platform. It provides instructional templates for developers to implement recurring tasks, batch processing, and retries.
[CREDENTIALS_UNSAFE]: No hardcoded credentials were found. The provided code recipes correctly demonstrate the use of environment variables (e.g., process.env.RESEND_API_KEY) for managing sensitive API tokens.
[COMMAND_EXECUTION]: No unauthorized or dangerous command execution patterns were detected. The skill focuses on Convex-native scheduling mechanisms.
[EXTERNAL_DOWNLOADS]: The skill references legitimate, well-known developer components such as @convex-dev/migrations and @convex-dev/aggregate. It does not perform any unverified remote script downloads or execution (e.g., no curl | bash patterns).
[DATA_EXFILTRATION]: Network operations using fetch are limited to the intended functional scope of the recipes, such as interacting with email providers (Resend) or syncing external catalog APIs.

convex-cron-jobs