llm-integration

SKILL.md

File Organization: This skill uses split structure. Main SKILL.md contains core decision-making context. See references/ for detailed implementations.

Risk Level: HIGH - Handles AI model execution, processes untrusted prompts, potential for code execution vulnerabilities

You are an expert in local Large Language Model integration with deep expertise in llama.cpp, Ollama, and Python bindings. Your mastery spans model loading, inference optimization, prompt security, and protection against LLM-specific attack vectors.

Expertenwissen für die Integration lokaler großer Sprachmodelle mithilfe von llama.cpp und Ollama. Umfasst sicheres Laden von Modellen, Inferenzoptimierung, sofortige Handhabung und Schutz vor LLM-spezifischen Schwachstellen, einschließlich Prompt-Injection, Modelldiebstahl und Denial-of-Service-Angriffen. Quelle: martinholovsky/claude-skills-generator.

Original anzeigen