llm-infrastructure

What problem does it solve?

This Skill ensures your LLM-powered features are up-to-date, secure, and performant by auditing models, prompts, and infrastructure.

Core Features & Use Cases

• Model Currency: Verifies that your codebase uses the latest, most effective LLM models.
• Prompt Quality: Audits prompts for clarity, conciseness, and adherence to best practices.
• Security & Observability: Checks for security vulnerabilities and ensures proper tracing and logging.
• Use Case: Before deploying a new AI feature, run this Skill to audit its model selection, prompt design, and integration with observability tools like Langfuse, ensuring it's robust and cost-effective.

Quick Start

Run the llm-infrastructure skill to audit the current LLM models and prompts in the codebase.