Claude Skills by majiayu000

Analyze videos using Google's Gemini API - describe content, answer questions, transcribe audio with visual descriptions, reference timestamps, clip videos, and process YouTube URLs. Supports 9 video formats, multiple models (Gemini 2.5/2.0), and context windows up to 2M tokens (6 hours of video).

Generate AI videos with Hailuo (MiniMax) via AceDataCloud API. Use when creating videos from text descriptions or animating images into video. Supports text-to-video and image-to-video with director mode for precise control.

Generate AI videos with Hailuo (MiniMax) via AceDataCloud API. Use when creating videos from text descriptions or animating images into video. Supports text-to-video and image-to-video with director mode for precise control.

Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval. Works with the model-index metadata format.

Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.

Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.

AI model inference and serving. Activate when: (1) Setting up LocalAI or vLLM, (2) Configuring model serving, (3) Working with GGUF/GGML models, (4) Implementing inference pipelines, or (5) Optimizing model performance.

Spectral similarity and compound identification for metabolomics. Use for comparing mass spectra, computing similarity scores (cosine, modified cosine), and identifying unknown compounds from spectral libraries. Best for metabolite identification, spectral matching, library searching. For full LC-MS/MS proteomics pipelines use pyopenms.

Manage mixed precision trainer operations. Auto-activating skill for ML Training. Triggers on: mixed precision trainer, mixed precision trainer Part of the ML Training skill category. Use when working with mixed precision trainer functionality. Trigger with phrases like "mixed precision trainer", "mixed trainer", "mixed".

Plan reproducible ML experiment runs with explicit parameters, metrics, and artifacts. Use before model training to standardize tracking-ready experiment definitions.

Implement machine learning solutions including model architectures, training pipelines, optimization strategies, and performance improvements. This skill spawns a specialist ML implementation agent...

Explain ML model predictions using SHAP values, feature importance, and decision paths with visualizations.

Build end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment. Use when creating ML pipelines, implementing MLOps practices, or automating model training and deployment workflows.

Build end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment. Use when creating ML pipelines, implementing MLOps practices, or automating model training and deployment workflows.

Build end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment. Use when creating ML pipelines, implementing MLOps practices, or automating model training and deployment workflows.

Build end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment. Use when creating ML pipelines, implementing MLOps practices, or automating model training and deployment workflows.

Build end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment. Use when creating ML pipelines, implementing MLOps practices, or automating mod...

Use when building ML pipelines, orchestrating training workflows, automating model lifecycle, implementing feature stores, or managing experiment tracking systems.

MLflow is an open-source platform for managing the machine learning lifecycle, including tracking, packaging, and deploy

Expertise in operating and maintaining production AI/ML systems, including deployment pipelines, monitoring, incident response, capacity management, and continuous improvement for local LLM infrastructure.

Production-grade data science specialist with TensorFlow 2.20.0, PyTorch 2.9.0, Scikit-learn 1.7.2 expertise. Master data processing, ML pipeline development, model deployment, and statistical analysis. Build end-to-end data science solutions with comprehensive experimentation and visualization.

Enterprise Machine Learning specialist with TensorFlow 2.20.0, PyTorch 2.9.0, Scikit-learn 1.7.2 expertise. Master AutoML, neural architecture search, MLOps automation, and production ML deployment. Build scalable ML pipelines with comprehensive monitoring and experiment tracking.

Enterprise Machine Learning specialist with TensorFlow 2.20.0, PyTorch 2.9.0, Scikit-learn 1.7.2 expertise. Master AutoML, neural architecture search, MLOps automation, and production ML deployment. Build scalable ML pipelines with comprehensive monitoring and experiment tracking.

Monitor model performance, detect data drift, concept drift, and anomalies in production using Prometheus, Grafana, and MLflow

Manage model registry manager operations. Auto-activating skill for ML Deployment. Triggers on: model registry manager, model registry manager Part of the ML Deployment skill category. Use when working with model registry manager functionality. Trigger with phrases like "model registry manager", "model manager", "model".

LLM and ML model deployment for inference. Use when serving models in production, building AI APIs, or optimizing inference. Covers vLLM (LLM serving), TensorRT-LLM (GPU optimization), Ollama (local), BentoML (ML deployment), Triton (multi-model), LangChain (orchestration), LlamaIndex (RAG), and streaming patterns.

This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked f...

Algorithm/model development and fine-tuning skill. Use for tasks like dataset design/cleaning, supervised fine-tuning (SFT), preference optimization (DPO/RLHF concepts), LoRA/QLoRA, training configs, evaluation (offline/online), safety checks, deployment packaging, and cost/performance trade-offs.

Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML.

End-to-end multiome workflow for joint scRNA-seq + scATAC-seq analysis. Covers data loading, separate modality processing, and WNN integration with Seurat/Signac. Use when analyzing joint scRNA+scATAC data.

Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).

Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).

Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K/2K/4K; use --input-image.

Generate and edit images using Google Gemini 3 Pro Image (Nano Banana Pro). Supports text-to-image, image editing, various aspect ratios, and high-resolution output (2K/4K).

Neuropixels neural recording analysis. Load SpikeGLX/OpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen/IBL curation, AI-assisted visual analysis, for Neuropixels 1.0/2.0 extracellular electrophysiology. Use when working with neural recordings, spike sorting, extracellular electrophysiology, or when the user mentions Neuropixels, SpikeGLX, Open Ephys, Kilosort, quality metrics, or unit curation.

Neuropixels neural recording analysis. Load SpikeGLX/OpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen/IBL curation, AI-assisted visual analysis, for Neuropixels 1.0/2.0 extracellular electrophysiology. Use when working with neural recordings, spike sorting, extracellular electrophysiology, or when the user mentions Neuropixels, SpikeGLX, Open Ephys, Kilosort, quality metrics, or unit curation.

Neuropixels neural recording analysis. Load SpikeGLX/OpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen/IBL curation, AI-assisted visual analysis, for Neuropixels 1.0/2.0 extracellular electrophysiology. Use when working with neural recordings, spike sorting, extracellular electrophysiology, or when the user mentions Neuropixels, SpikeGLX, Open Ephys, Kilosort, quality metrics, or unit curation.

Performs rigorous time series cross-validation using expanding and sliding windows. Use when needing to evaluate the performance of time series models on unseen data. Trigger with cross validate time series, evaluate forecasting model, time series backtesting.

Automatically selects the best forecasting model between StatsForecast and TimeGPT based on time series data characteristics. Use when unsure which model performs best. Trigger with 'auto-select model', 'choose best model', 'model selection'.

Provides expert Nixtla forecasting using TimeGPT, StatsForecast, and MLForecast. Generates time series forecasts, analyzes trends, compares models, performs cross-validation, and recommends best practices. Activates when user needs forecasting, time series analysis, sales prediction, demand planning, revenue forecasting, or M4 benchmarking.

Advanced indexing techniques including slicing, fancy indexing, and boolean masks, along with memory implications of views vs. copies. Triggers: indexing, slicing, fancy indexing, boolean mask, np.where, np.ix_.

Protocols for cross-library data exchange including DLPack, buffer interfaces, and __array_ufunc__ for overriding NumPy functions. Triggers: DLPack, interoperability, __array_interface__, __array_ufunc__, buffer protocol.

Local speech-to-text with the Whisper CLI (no API key).

Local speech-to-text with the Whisper CLI (no API key).

Local speech-to-text with the Whisper CLI (no API key).

Local speech-to-text with the Whisper CLI (no API key).

Local speech-to-text with the Whisper CLI (no API key).

Local speech-to-text with the Whisper CLI (no API key).

Local speech-to-text with the Whisper CLI (no API key).

Local speech-to-text with the Whisper CLI (no API key).