The Agent Skills Directory

[SAFE]: The skill serves as a reference for architectural patterns such as Prompt Chaining, Orchestrator-Workers, and Evaluator-Optimizer loops. All code snippets are instructional and follow standard development practices.
[SAFE]: Dependencies used in the examples are standard, well-known libraries including @trigger.dev/sdk, zod, and the Vercel AI SDK (ai).
[SAFE]: No evidence of prompt injection, data exfiltration, or unauthorized system access was detected. The patterns described (e.g., Human-in-the-Loop) actually promote safer agent behavior by incorporating manual approval gates.

trigger-agents