Claude Skills by majiayu000

Capture task outcomes, score performance, and derive rules as token priors for continual learning without model weight changes. Use for post-task feedback, experience capture, pattern extraction, and learning from mistakes. Achieves continual learning for $18 per 100 samples vs $10k fine-tune cost. Triggers on "learn from experience", "capture patterns", "post-task analysis", "continual learning", "experience extraction".

Use when fine-tuning LLMs, training custom models, or optimizing model performance for specific tasks. Invoke for parameter-efficient methods, dataset preparation, or model adaptation.

Build AI applications using the Azure AI Projects Python SDK (azure-ai-projects). Use when working with Foundry project clients, creating versioned agents with PromptAgentDefinition, running evaluations, managing connections/deployments/datasets/indexes, or using OpenAI-compatible clients. This is the high-level Foundry SDK - for low-level agent operations, use azure-ai-agents-python skill.

Google Gemini API integration for building AI-powered applications. Use when working with Google's Gemini API, Python SDK (google-genai), TypeScript SDK (@google/genai), multimodal inputs (image, video, audio, PDF), thinking/reasoning features, streaming responses, structured outputs with JSON schemas, multi-turn chat, system instructions, image generation (Nano Banana), video generation (Veo), music generation (Lyria), embeddings, document/PDF processing, or any Gemini API integration task. ...

Comprehensive reference for Google's Gemini API. Use when building applications with: (1) Gemini models (Gemini 3 Pro, 2.5 Flash/Pro/Flash-Lite) for text and multimodal generation, (2) Image generation (Imagen, Nano Banana), video (Veo 3.1), music (Lyria), (3) Function calling, structured outputs, and agentic workflows, (4) Built-in tools: Google Search, Maps, Code Execution, URL Context, Computer Use, File Search, (5) Live API for real-time voice/video streaming, (6) Long context (1M+ tokens...

Comprehensive reference for Google's Gemini API. Use when building applications with: (1) Gemini models (Gemini 3 Pro, 2.5 Flash/Pro/Flash-Lite) for text and multimodal generation, (2) Image generation (Imagen, Nano Banana), video (Veo 3.1), music (Lyria), (3) Function calling, structured outputs, and agentic workflows, (4) Built-in tools: Google Search, Maps, Code Execution, URL Context, Computer Use, File Search, (5) Live API for real-time voice/video streaming, (6) Long context (1M+ tokens...

Use Gemini CLI's 1M token context to understand entire codebases in one pass. Full architecture mapping, pattern discovery, and onboarding documentation.

Generate text embeddings using Gemini Embedding API via scripts/. Use for creating vector representations of text, semantic search, similarity matching, clustering, and RAG applications. Triggers on "embeddings", "semantic search", "vector search", "text similarity", "RAG", "retrieval".

Create distinctive, production-grade frontend interfaces using Gemini 3 Pro for design ideation. Use this skill when you want Gemini's creative perspective on web components, pages, or applications. Generates bold, polished code that avoids generic AI aesthetics.

Guide for implementing Google Gemini API image generation - create high-quality images from text prompts using gemini-2.5-flash-image model. Use when generating images, creating visual content, or implementing text-to-image features. Supports text-to-image, image editing, multi-image composition, and iterative refinement.

Quick classifier training with automatic model selection, hyperparameter tuning, and comprehensive evaluation metrics.

This skill enables Claude to execute clustering algorithms on datasets. It is used when the user requests to perform clustering, identify groups within data, or analyze data structure. The skill supports algorithms like K-means, DBSCAN, and hierarchical clustering. Claude should use this skill when the user explicitly asks to "run clustering," "perform a cluster analysis," or "group data points" and provides a dataset or a way to access one. The skill also handles data validation, error handl...

Cluster data using K-Means, DBSCAN, hierarchical clustering. Use for customer segmentation, pattern discovery, or data grouping.

Finds differentially expressed genes (markers) for clusters of T/B cells using Seurat's FindMarkers function. Performs statistical testing between clusters, identifies cluster-defining genes, and automatically runs pathway enrichment analysis (via Enrichr) on significant markers. Generates publication-ready visualizations including volcano plots, dot plots, heatmaps, and enrichment plots.

Constraint-based metabolic modeling (COBRA). FBA, FVA, gene knockouts, flux sampling, SBML models, for systems biology and metabolic engineering analysis.

Constraint-based metabolic modeling (COBRA). FBA, FVA, gene knockouts, flux sampling, SBML models, for systems biology and metabolic engineering analysis.

Constraint-based metabolic modeling (COBRA). FBA, FVA, gene knockouts, flux sampling, SBML models, for systems biology and metabolic engineering analysis.

Constraint-based metabolic modeling (COBRA). FBA, FVA, gene knockouts, flux sampling, SBML models, for systems biology and metabolic engineering analysis.

Constraint-based metabolic modeling (COBRA). FBA, FVA, gene knockouts, flux sampling, SBML models, for systems biology and metabolic engineering analysis.

Constraint-based metabolic modeling (COBRA). FBA, FVA, gene knockouts, flux sampling, SBML models, for systems biology and metabolic engineering analysis.

SOTA Computer Vision Expert (2026). Specialized in YOLO26, Segment Anything 3 (SAM 3), Vision Language Models, and real-time spatial analysis.

This skill provides guidance for counting tokens in datasets using specific tokenizers. It should be used when tasks involve tokenizing dataset content, filtering data by domain or category, and aggregating token counts. Common triggers include requests to count tokens in HuggingFace datasets, filter datasets by specific fields, or use particular tokenizers (e.g., Qwen, DeepSeek, GPT).

Process data normalization tool operations. Auto-activating skill for ML Training. Triggers on: data normalization tool, data normalization tool Part of the ML Training skill category. Use when working with data normalization tool functionality. Trigger with phrases like "data normalization tool", "data tool", "data".

Process data normalization tool operations. Auto-activating skill for ML Training. Triggers on: data normalization tool, data normalization tool Part of the ML Training skill category. Use when working with data normalization tool functionality. Trigger with phrases like "data normalization tool", "data tool", "data".

Expert in statistical analysis, predictive modeling, machine learning, and data storytelling to drive business insights.

Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first PyTorch workflows use torchdrug; for benchmark datasets use pytdc.

Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first PyTorch workflows use torchdrug; for benchmark datasets use pytdc.

Diffusion-based molecular docking. Predict protein-ligand binding poses from PDB/SMILES, confidence scores, virtual screening, for structure-based drug design. Not for affinity prediction.

Build a rigorous world model with state, dynamics, uncertainty, and provenance. Use when creating digital twins, constructing system representations, building simulation foundations, or establishing baseline world state.

Synchronize construction digital twins with real-time data. Connect BIM models with IoT sensors, progress updates, and field data for live project visualization and monitoring.

Build and maintain digital twins - virtual representations of physical systems that synchronize with real-world counterparts for monitoring, prediction, and optimization. Use when "digital twin, virtual model, real-time synchronization, physical-virtual coupling, predictive maintenance, asset modeling, system replica, live simulation, " mentioned.

Build transformer fine-tuning run plans with task settings, hyperparameters, and model-card outputs. Use for repeatable Hugging Face or PyTorch finetuning workflows.

Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.

Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.

Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.

Evaluation framework patterns for RAG and LLMs, including faithfulness metrics, synthetic dataset generation, and LLM-as-a-judge patterns. Triggers: ragas, deepeval, llm-eval, faithfulness, hallucination-check, synthetic-data.

Evaluation framework patterns for RAG and LLMs, including faithfulness metrics, synthetic dataset generation, and LLM-as-a-judge patterns. Triggers: ragas, deepeval, llm-eval, faithfulness, hallucination-check, synthetic-data.

Measure model performance on test datasets. Use when assessing accuracy, precision, recall, and other metrics.

Manages ML experiment tracking with MLflow, Weights & Biases, or SpecWeave's built-in tracking. Activates for "track experiments", "MLflow", "wandb", "experiment logging", "compare experiments", "hyperparameter tracking". Automatically configures tracking tools to log to SpecWeave increment folders, ensuring all experiments are documented and reproducible. Integrates with SpecWeave's living docs for persistent experiment knowledge.

All-in-one read preprocessing with fastp including adapter trimming, quality filtering, deduplication, base correction, and HTML report generation. Use when preprocessing Illumina data and wanting a single fast tool instead of separate Cutadapt, Trimmomatic, and FastQC steps.

All-in-one read preprocessing with fastp including adapter trimming, quality filtering, deduplication, base correction, and HTML report generation. Use when preprocessing Illumina data and wanting a single fast tool instead of separate Cutadapt, Trimmomatic, and FastQC steps.

Work with FASTQ quality scores using Biopython. Use when analyzing read quality, filtering by quality, trimming low-quality bases, or generating quality reports.

Auto-generate features with encodings, scaling, polynomial features, and interaction terms for ML pipelines.

Create and transform features using encoding, scaling, polynomial features, and domain-specific transformations for improved model performance and interpretability

Execute feature store connector operations. Auto-activating skill for ML Deployment. Triggers on: feature store connector, feature store connector Part of the ML Deployment skill category. Use when working with feature store connector functionality. Trigger with phrases like "feature store connector", "feature connector", "feature".

Framework for computational fluid dynamics simulations using Python. Use when running fluid dynamics simulations including Navier-Stokes equations (2D/3D), shallow water equations, stratified flows, or when analyzing turbulence, vortex dynamics, or geophysical flows. Provides pseudospectral methods with FFT, HPC support, and comprehensive output analysis.

Transcribe audio files using Google's Gemini API or Vertex AI

Invoke Google Gemini for video understanding and analysis using the Python google-genai SDK. Supports gemini-3-pro-preview and gemini-2.5-flash for video analysis, transcription, and content extraction.

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).

Guide for implementing Google Gemini API image understanding - analyze images with captioning, classification, visual QA, object detection, segmentation, and multi-image comparison. Use when analyzing images, answering visual questions, detecting objects, or processing documents with vision.