Claude Skills by majiayu000

N-dimensional array computing library providing array types, vectorized operations, linear algebra, FFT, random sampling, and testing utilities.

python library

Local vision-language model for image analysis using SmolVLM-2B

Automatically extract abstract finite-state models in SMV/NuSMV format from source code (C/C++, Java, Python) for formal model checking. Use when users need to: (1) Generate SMV models from program code for verification, (2) Extract state-transition models from protocol implementations, (3) Analyze control flow and data flow to construct formal models, (4) Create models for checking safety and liveness properties, (5) Convert imperative code to declarative state machines. Particularly effecti...

Topological soliton detection and agency bridge with anyonic fusion algebra for concept composition

spaCy NLP library with pipelines. Use for text processing.

SpatialAgent focuses on the biological interpretation of spatial transcriptomics

---name: spatial-epigenomics-agent

Give your agent the ability to speak to you real-time. Talk to your Claude! Local TTS, text-to-speech, voice synthesis, audio generation with voice cloning on Apple Silicon. Use for reading articles aloud, audiobook narration, or voice responses. Runs entirely on-device via MLX - private, no API keys.

Vocalize Claude's last response using local Qwen3-TTS. Default voice is the Oracle (deep, resonant Dune narrator). Use --preset for emotion-controlled preset speakers.

Advanced speaker diarization using pyannote-audio. Identify who speaks when, detect multiple speakers, handle overlapping speech, and create speaker-specific segments. Use when you need accurate speaker identification, multi-speaker content analysis, or speaker-specific clip extraction. More accurate than Gemini's built-in diarization for complex scenarios.

Explains specialized Synapse action classes for specific workflows. Use when the user mentions "BaseTrainAction", "BaseExportAction", "BaseUploadAction", "BaseInferenceAction", "BaseDeploymentAction", "AddTaskDataAction", "train action", "export action", "upload action", "inference action", "deployment action", "pre-annotation", "add_task_data", "autolog", "get_dataset", "create_model", or needs workflow-specific action development help.

'Skills for computing spectroscopic observables from first principles:

Expert speech-language pathologist specializing in AI-powered speech therapy, phoneme analysis, articulation visualization, voice disorders, fluency intervention, and assistive communication technology. Activate on 'speech therapy', 'articulation', 'phoneme analysis', 'voice disorder', 'fluency', 'stuttering', 'AAC', 'pronunciation', 'speech recognition', 'mellifluo.us'. NOT for general audio processing, music production, or voice acting coaching without clinical context.

Expert skill for implementing speech-to-text with Faster Whisper. Covers audio processing, transcription optimization, privacy protection, and secure handling of voice data for JARVIS voice assistant.

Split datasets into training, validation, and test partitions with the right stratification and temporal rules. Use as a narrow preprocessing helper once the broader ML workflow is already chosen, not as the main route owner for an end-to-end ML task.

Qualitative behavior of solutions near equilibria

Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick prototyping, and well-documented algorithm implementations. Best for single-agent RL with Gymnasium environments. For high-performance parallel training, multi-agent systems, or custom vectorized environments, use pufferlib instead.

Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick prototyping, and well-documented algorithm implementations. Best for single-agent RL with Gymnasium environments. For high-performance parallel training, multi-agent systems, or custom vectorized environments, use pufferlib instead.

Manifold of points converging to equilibrium

Stellogen Skill

Stellogen Skill

StructuredDecompositions.jl sheaves on tree decompositions for FPT algorithms with bidirectional navigation

Summarize text using extractive, abstractive, hierarchical, and multi-document techniques, producing concise outputs at configurable detail levels. Use when the user requests summarization or provides relevant inputs for this workflow.

Build production-ready classification and regression models with hyperparameter tuning

This skill group covers the calculation of surface energies and the prediction

Use when you need exact symbolic math in Python — algebra, calculus, equation solving, symbolic linear algebra, or code generation via lambdify/LaTeX. Prefer NumPy or SciPy when floating-point approximations are sufficient.

LLM-generated training data, augmentation strategies, distillation datasets, self-instruct and Evol-Instruct patterns, quality filtering pipelines.

System 2 attention mechanisms for deliberate, slow reasoning in transformer

Predict miRNA target genes using sequence-based algorithms and database lookups. Use when identifying potential mRNA targets of differentially expressed or functionally important miRNAs.

Predict miRNA target genes using sequence-based algorithms and database lookups. Use when identifying potential mRNA targets of differentially expressed or functionally important miRNAs.

---name: tcr-pmhc-prediction-agent

---name: tcr-repertoire-analysis-agent

Guides technology selection and implementation of AI and ML features in .NET 8+ applications using ML.NET, Microsoft.Extensions.AI (MEAI), Microsoft Agent Framework (MAF), GitHub Copilot SDK, ONNX Runtime, and OllamaSharp. Covers the full spectrum from classic ML through modern LLM orchestration to local inference. Use when adding classification, regression, clustering, anomaly detection, recommendation, LLM integration (text generation, summarization, reasoning), RAG pipelines with vector se...

Hot dog or not? Classify food photos and battle Nemotron. Use when a user sends a food photo, asks if something is a hot dog, or says 'hotdog', '/hotdog', or 'hot dog battle'.

Create efficient data pipelines with tf.data

3-MATCH gadgets and non-backtracking geodesics for 3-SAT via colored subgraph isomorphism.

---name: time-resolved-cryoem-agent

Zero-shot time series forecasting with Google's TimesFM foundation model. Use this skill when forecasting ANY univariate time series — sales, sensor readings, stock prices, energy demand, patient vitals, weather, or scientific measurements — without training a custom model. Automatically checks system RAM/GPU before loading the model, supports CSV/DataFrame/array inputs, and returns point forecasts with calibrated prediction intervals. Includes a preflight system checker script that MUST be r...

Zero-shot time series forecasting with Google's TimesFM foundation model. Use for any univariate time series (sales, sensors, energy, vitals, weather) without training a custom model. Supports CSV/DataFrame/array inputs with point forecasts and prediction intervals. Includes a preflight system checker script to verify RAM/GPU before first use.

Deep learning framework development with tinygrad - a minimal tensor library with autograd, JIT compilation, and multi-device support. Use when writing neural networks, training models, implementing tensor operations, working with UOps/PatternMatcher for graph transformations, or contributing to tinygrad internals. Triggers on tinygrad imports, Tensor operations, nn modules, optimizer usage, schedule/codegen work, or device backends.

---name: tme-immune-profiling-agent

BPE, WordPiece, SentencePiece, and Unigram tokenizer training, vocabulary optimization, domain extension, and multilingual design.

Identifies and visualizes the top expressing genes per cluster in T/B cells, followed by pathway enrichment analysis. Provides quick cluster characterization by highlighting the most highly expressed genes and their biological functions.

Use torch.compile to JIT-compile PyTorch code into optimized kernels,

PyTorch Geometric (PyG) for graph neural networks — node/link/graph classification, message passing (GCN, GAT, GraphSAGE, GIN), heterogeneous graphs, neighbor sampling, and custom datasets. Use when working with torch_geometric, not for general NetworkX analytics or non-graph PyTorch models.

PyTorch-native graph neural networks for molecules and proteins. Use when building custom GNN architectures for drug discovery, protein modeling, or knowledge graph reasoning. Best for custom model development, protein property prediction, retrosynthesis. For pre-trained models and diverse featurizers use deepchem; for benchmark datasets use pytdc.

PyTorch-native graph neural networks for molecules and proteins. Use when building custom GNN architectures for drug discovery, protein modeling, or knowledge graph reasoning. Best for custom model development, protein property prediction, retrosynthesis. For pre-trained models and diverse featurizers use deepchem; for benchmark datasets use pytdc.

Model serving engine for PyTorch. Focuses on MAR packaging, custom handlers for preprocessing/inference, and management of multi-GPU worker scaling. (torchserve, mar-file, handler, basehandler, model-archiver, inference-api)

Natural Language Processing utilities for PyTorch (Legacy). Includes tokenizers, vocabulary building, and DataPipe-based dataset handling for text processing pipelines. (torchtext, tokenizer, vocab, datapipe, regextokenizer, nlp-pipeline)