Claude Skills by luokai0

Systematically add test coverage for all local code changes using specialized review and development agents. Add tests for uncommitted changes (including untracked files), or if everything is commited, then will cover latest commit.

Expert-level Domain-Driven Design (DDD). Use when applying DDD principles, identifying bounded contexts, aggregates, entities, value objects, domain events, repositories, application services, or ubiquitous language. Also use when the user mentions 'bounded context', 'aggregate', 'value object', 'domain event', 'ubiquitous language', 'context map', 'DDD', 'domain model', or 'aggregate root'.

Expert-level API design and developer experience. Use when designing REST APIs, versioning, backward compatibility, SDK design, error handling conventions, API documentation, or API governance. Also use when the user mentions 'API design', 'versioning', 'backward compatible', 'OpenAPI', 'SDK design', 'error format', 'pagination', 'rate limiting', 'API governance', or 'REST conventions'.

Expert-level system design and software architecture. Use when designing large-scale systems, discussing scalability, availability, consistency, load balancing, caching, message queues, databases, or drawing architecture diagrams. Also use when the user mentions 'design a system', 'how would you scale', 'architecture review', 'trade-offs', 'CAP theorem', 'bottleneck', 'high availability', or 'distributed system'.

Expert-level developer experience. Use when improving workflows, ESLint, Prettier, pre-commit hooks, monorepo tooling, Turborepo, Nx, or developer docs.

Expert-level Clean Architecture and SOLID principles. Use when structuring codebases with clean architecture, applying SOLID principles, dependency inversion, use cases, ports and adapters, hexagonal architecture, or onion architecture. Also use when the user mentions 'Clean Architecture', 'SOLID', 'dependency inversion', 'hexagonal', 'use case', 'ports and adapters', 'domain layer', 'application layer', or 'Uncle Bob'.

Expert-level software design patterns. Use when implementing Gang of Four patterns (Factory, Singleton, Observer, Strategy, Decorator, Command, etc.), architectural patterns, or recognizing when and how patterns apply. Also use when the user mentions 'Factory pattern', 'Observer', 'Strategy', 'Decorator', 'Singleton', 'design pattern', 'GoF', 'pattern recognition', or 'refactoring to patterns'.

Expert-level microservices architecture. Use when designing microservices, service boundaries, inter-service communication, saga pattern, CQRS, event sourcing, service mesh, API gateways, or managing distributed systems complexity. Also use when the user mentions 'microservices', 'service boundary', 'saga pattern', 'service mesh', 'CQRS', 'event sourcing', 'API gateway', 'distributed transaction', or 'service decomposition'.

Expert-level open source. Use when setting up OSS projects, README, CONTRIBUTING, changelogs, semantic versioning, GitHub Actions releases, or community building.

Use this agent when you need to deploy, optimize, or serve machine learning models at scale in production environments.

Expert-level machine learning engineering. Use when building ML models, feature engineering, model training/evaluation, scikit-learn, XGBoost, hyperparameter tuning, cross-validation, or deploying ML models to production. Also use when the user mentions 'ML model', 'feature engineering', 'scikit-learn', 'overfitting', 'cross-validation', 'classification', 'regression', 'clustering', 'training data', or 'model accuracy'.

Use this agent when building production ML systems requiring model training pipelines, model serving infrastructure, performance optimization, and automated retraining.

Expert-level deep learning with PyTorch and TensorFlow. Use when building neural networks, CNNs, RNNs, transformers, training loops, loss functions, backpropagation, GPU optimization, or fine-tuning pretrained models. Also use when the user mentions 'neural network', 'PyTorch', 'transformer', 'fine-tuning', 'backpropagation', 'GPU training', 'loss function', 'overfitting', 'batch normalization', or 'transfer learning'.

Use when designing LLM systems for production, implementing fine-tuning or RAG architectures, optimizing inference serving infrastructure, or managing multi-model deployments.

Expert-level LLM application engineering. Use when building LLM-powered apps, prompt engineering, RAG systems, embeddings, vector databases, function calling, agents, or evaluating LLM outputs. Also use when the user mentions 'RAG', 'LangChain', 'embedding', 'vector store', 'prompt engineering', 'AI agent', 'function calling', 'hallucination', or 'context window'.

AI-first application patterns, LLM testing, prompt management

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

Build production-grade Retrieval Augmented Generation systems. Covers chunking, embedding, vector search, reranking, evaluation, and RAG pipelines.

Use this agent when you need to design and implement ML infrastructure, set up CI/CD for machine learning models, establish model versioning systems, or optimize ML platforms for reliability and au...

Expert-level MLOps and ML infrastructure. Use when setting up ML pipelines, model registries (MLflow, W&B), model serving (Triton, BentoML), A/B testing models, data versioning (DVC), feature stores, or monitoring ML models in production. Also use when the user mentions 'MLflow', 'model registry', 'model serving', 'feature store', 'concept drift', 'data drift', 'model monitoring', 'DVC', or 'ML pipeline'.

Expert-level data engineering. Use when building data pipelines, ETL/ELT processes, working with Apache Spark, Airflow, dbt, data warehouses (Snowflake, BigQuery, Redshift), data lakes, or streaming pipelines. Also use when the user mentions 'data pipeline', 'ETL', 'ELT', 'dbt', 'Airflow', 'Spark', 'data warehouse', 'data lake', 'streaming', 'partitioning', or 'data quality'.

Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing repositories, models, datasets, and Spaces on the Hugging Face Hub. Replaces now deprecated `huggingface-cli` command.

Use Hugging Face Hub via MCP server tools. Search models, datasets, Spaces, papers. Get repo details, fetch documentation, run compute jobs, and use Gradio Spaces as AI tools. Available when connected to the HF MCP server.

Use this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, download parquet URLs, and read size or statistics.

Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, streaming row updates, and SQL-based dataset querying/transformation. Designed to work alongside HF MCP server for comprehensive dataset workflows.

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.

This skill should be used when users want to run any workload on Hugging Face Jobs infrastructure. Covers UV scripts, Docker-based jobs, hardware selection, cost estimation, authentication with tokens, secrets management, timeout configuration, and result persistence. Designed for general-purpose compute workloads including data processing, inference, experiments, batch jobs, and any Python-based tasks. Should be invoked for tasks involving cloud compute, GPU workloads, or when users mention ...

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...

Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/datasets/spaces, Github repo and project page. Use when the user shares a Hugging Face paper page URL, an arXiv URL or ID, or asks to summarize, explain, or analyze an AI research paper.

Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.

Use this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help. This is especially useful when chaining or combining API calls or the task will be repeated/automated. This Skill creates a reusable script to fetch, enrich or process data.

Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API), firing alerts for training diagnostics, or retrieving/analyzing logged metrics (CLI). Supports real-time dashboard visualization, alerts with webhooks, HF Space syncing, and JSON output for automation.

Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation,...

Build Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or chatbots.

Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detection), audio (speech recognition, audio classification), and multimodal tasks. Works in Node.js and browsers (with WebGPU/WASM) using pre-trained models from Hugging Face Hub.

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.

Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experi...

Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely novel research directions by leveraging combinatorial creativity, analogical reasoning, constraint manipulation, and other empirically grounded creative strategies.

Generate comprehensive market research reports (50+ pages) in the style of top consulting firms (McKinsey, BCG, Gartner). Features professional LaTeX formatting, extensive visual generation with scientific-schematics and generate-image, deep integration with research-lookup for data gathering, and multi-framework strategic analysis including Porter Five Forces, PESTLE, SWOT, TAM/SAM/SOM, and BCG Matrix.

Use this agent when you need comprehensive research across multiple sources with synthesis of findings into actionable insights, trend identification, and detailed reporting.

Write competitive research proposals for NSF, NIH, DOE, DARPA, and Taiwan NSTC. Agency-specific formatting, review criteria, budget preparation, broader impacts, significance statements, innovation narratives, and compliance with submission requirements.

Look up current research information using the Parallel Chat API (primary) or Perplexity sonar-pro-search (academic paper searches). Automatically routes queries to the best backend. Use for finding papers, gathering research data, and verifying scientific information.

Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.

Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias), or teaching critical analysis. Best for understanding evidence quality, identifying flaws. For formal peer review writing use peer-review.

Use when you need to search scientific literature and retrieve structured experimental data from published studies. Invoke this agent when the task requires evidence-grounded answers from full-text...

Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.1 Pro Preview for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and complex scientific visualizations.

Build slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and LaTeX Beamer.

Meta-skill for publication-ready figures. Use when creating journal submission figures requiring multi-panel layouts, significance annotations, error bars, colorblind-safe palettes, and specific journal formatting (Nature, Science, Cell). Orchestrates matplotlib/seaborn/plotly with publication styles. For quick exploration use seaborn or plotly directly.

Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA), for research papers and journal submissions.