Model optimization and quantization. Includes Flash Attention (2-4x speedup), bitsandbytes (8/4-bit quantization), GPTQ (4-bit post-training), AWQ (activation-aware), GGUF (llama.cpp format), and HQQ (calibration-free). Use when reducing memory, accelerating inference, or quantizing models.
/plugin marketplace add zechenzhangAGI/AI-research-SKILLs/plugin install optimization@ai-research-skillsComprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Interactive learning mode that requests meaningful code contributions at decision points (mimics the unshipped Learning output style)
Automated code review for pull requests using multiple specialized agents with confidence-based scoring
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification