Loading...
Loading...
Found 27 Skills
Switch AI providers or models without breaking things. Use when you want to switch from OpenAI to Anthropic, try a cheaper model, stop depending on one vendor, compare models side-by-side, a model update broke your outputs, you need vendor diversification, or you want to migrate to a local model. Covers DSPy model portability — provider config, re-optimization, model comparison, and multi-model pipelines.
Building and training neural networks with PyTorch. Use when implementing deep learning models, training loops, data pipelines, model optimization with torch.compile, distributed training, or deploying PyTorch models.
Practical guidance for training MoE VLMs in Megatron Bridge. Compares FSDP and 3D-parallel approaches, using rounded lessons from Qwen3-VL, Qwen3-Next, and other multimodal experiments.
Hyperparameter Tuner - Auto-activating skill for ML Training. Triggers on: hyperparameter tuner, hyperparameter tuner Part of the ML Training skill category.
Ollama local LLM deployment and management. Use for running LLMs locally.
Direct high-fidelity cinematic video with AI — translates creative intent into technical cinematographic directives for Veo3, Kling, and Luma video models via muapi.ai
Use when the workflow works but needs to handle more complex cases or produce higher-quality output through better tools, context, prompts, or models.
Use when an SGLang, vLLM, or TensorRT-LLM serving/model optimization task needs prior model-family PR evidence. Query and read the PR-driven history docs under model-pr-optimization-history before choosing source paths, fast paths, kernel/fusion ideas, regression risks, or validation lanes.
Build and run LLM-as-judge evaluation pipelines using Amazon Bedrock Evaluation Jobs with pre-computed inference datasets. Use when setting up automated model evaluation, designing test scenarios, collecting pre-computed responses, configuring custom metrics, creating AWS infrastructure, running evaluation jobs, parsing results, and iterating on findings.
Programmatic GLB/glTF 3D model compression library with a multi-phase pipeline, skinned-model awareness, and custom glTF-Transform transforms. Use when integrating compression into application code, building custom pipelines, or using individual transforms.
Optimize Claude Code prompts for Opus 4.6, Sonnet 4.5, and Haiku 4.5 with model-aware reasoning settings, context control, safe tool use, and concise output shaping.
Choose the right MoE token dispatcher (`alltoall`, DeepEP, or HybridEP) for the hardware, EP degree, and optimization stage. Summarizes patterns from DSV3, Qwen3, Qwen3-Next, and VLM bring-up work.