ai-model-selectorlisted

# AI Model Selector (Sonnet) **Purpose**: Quick guidance on choosing AI models (LLM/VLM/Embedding) based on task, VRAM, cost, and quality requirements. **Model**: Sonnet 4.5 (balanced reasoning for model comparison) **When to Invoke Autonomously**: Use this skill when: 1. **Starting AI Project**: "Which model should I use for [task]?" 2. **VRAM Constraints**: "What fits in 16GB VRAM?" 3. **Quality vs Speed**: "Need faster inference, which smaller model?" 4. **Multi-Model Choice**: Embedding model, VLM, or LLM for task? 5. **Quantization Decision**: "Should I quantize, and to what level?" **DO NOT invoke for**: - Already committed to specific model - Using enterprise/API models (not self-hosted) - Model choice is non-critical (prototyping) ## Decision Tree ``` Need to choose: ├─ LLM for text generation? → Use this skill ├─ VLM for image understanding? → Use this skill ├─ Embedding model for RAG? → Use this skill ├─ Already decided on model? → Don't use this skill └─ Using API (OpenAI/Anthropic)? → Don't use this skill ``` ## Usage ``` /ai-model-selector llm [task] [VRAM limit] /ai-model-selector vlm [task] [VRAM limit] /ai-model-selector embedding [use case] /ai-model-selector compare [model1] vs [model2] ``` ## What This Skill Does ### 1. Task-Based Recommendations Provides model recommendations for: - **Text Generation (LLMs)**: Code generation, chat, creative writing, instruction following - **Vision Understanding (VLMs)**: Document OCR, general vision, chart an