Data & AI
Machine Learning, Data Science, and AI development skills
22656 skills in this category
Subcategories
allra-test-writing
Allra 백엔드 테스트 작성 표준. Use when writing test code, choosing test helpers, generating test data with Fixture Monkey, or verifying test coverage.
obsidian-moc-creator
Create and maintain Maps of Content (MOCs) for Obsidian vault navigation. Use when directories lack navigation structure, content needs organization, or index pages are missing. Generates MOCs based on directory structure and file analysis.
sql-query-optimization
A skill for optimizing SQL queries, focusing on PostgreSQL. It provides a checklist for query analysis, guidance on reading EXPLAIN plans, and patterns for common optimization problems like N+1 queries, JOINs, and pagination. Includes templates for benchmarking and recommending indexes. Use this skill when a user wants to improve the performance of a SQL query.
barqnet-client
Specialized agent for BarqNet client application development across Desktop (Electron/TypeScript), iOS (Swift), and Android (Kotlin). Handles UI/UX implementation, OpenVPN integration, platform-specific features, secure storage, and native API usage. Use when developing client-side features, fixing UI bugs, or implementing platform-specific functionality.
jupytext
This skill should be used when the user asks to "convert notebook to text", "use jupytext", "version control notebooks", "share data between kernels", "set up multi-kernel project", "pair notebooks with Python files", "sync ipynb and py files", or needs multi-kernel projects (Python/R/Stata/SAS) with version-control-friendly notebooks.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
java-ddd-hexagonal
Guide Claude to create domain modules following DDD principles and hexagonal architecture for Java + Spring Boot projects.Use when user requests:(1) "Create a new module" / "새 모듈 만들어줘" / "도메인 모듈 생성"(2) "Add {feature} module" (e.g., "Add order module", "Add product module")(3) "Build {domain} bounded context" / "{domain} 바운디드 컨텍스트 구현"(4) Any request to create a new domain module for Java + Spring Boot projects with DDD and hexagonal architecture.Applies Kent Beck's TDD workflow (Red → Green → Refactor).Adapts to any Java/Spring Boot project by reading CLAUDE.md at project root.Uses Java 17+ features including records, sealed classes, and pattern matching.
phoenix-advanced-forecasting
Architecture for the 'living model': graduation rates, multi-MOIC analysis, reserves ranking, scenarios, and Monte Carlo. Always sits on top of the deterministic core.
jsgui3-activation-debug
Debug jsgui3 client-side activation issues. Use when SSR renders but clicks don’t work, this.dom.el is null, or you see Missing context.map_Controls / activation failures.
skill-catalog
Categorize and display available skills. Use when listing or selecting skills.
starred-email
Retrieves the user's starred Gmail emails, summarizing each message with metadata, action notes, and direct links while honoring optional filters for timeframe, keywords, or participants.
htmx
Adds AJAX, CSS Transitions, WebSockets, and Server Sent Events to HTML using attributes. Use when building hypermedia-driven applications, adding interactivity without JavaScript frameworks, or when user mentions HTMX, hx-boost, or HTML-first development.
mcp-server-setup
MCP (Model Context Protocol) server selection and configuration skill usingDocker MCP Toolkit as the primary orchestration method. Guides dynamic serverdiscovery, installation via Docker gateway, and fallback to direct installation.Should be executed after /initialize-project to extend Claude Code's capabilities.
skill-writer
Guide users through creating Agent Skills for Claude Code. Use when the user wants to create, write, author, or design a new Skill, or needs help with SKILL.md files, frontmatter, or skill structure.
livekit-nextjs-frontend
Build and review production-grade web and mobile frontends using LiveKit with Next.js. Covers real-time video/audio/data communication, WebRTC connections, track management, and best practices for LiveKit React components.
multi-agent
Orchestrate autonomous agent teams to complete complex tasks. PM dynamically selects specialized agents based on task classification and enforces non-negotiable principles. Supports local and remote agents, persistent sessions, and continuous learning through skills.
database-technologies
Master database technologies including SQL, PostgreSQL, MongoDB, Redis, and data modeling. Use when designing databases, writing queries, or optimizing database performance.
get-last-frame
Extract the last frame of an MP4 file into an image using OpenCV. Use when the user needs the final frame of a generated video saved as a still image.
fastapi-patterns
Comprehensive FastAPI best practices, patterns, and conventions for building production-ready Python web APIs. Covers application structure, async patterns, Pydantic models, dependency injection, database integration, authentication, error handling, testing, OpenAPI documentation, performance optimization, and common anti-patterns. Essential reference for FastAPI code reviews and development.
pr-feedback-workflow
Process all PR feedback in one pass. Fetches review comments and CI failures together, creates a unified action plan, applies fixes, replies to reviewers, resolves threads, and posts a summary. Use when asked to address PR feedback, fix review comments, handle CI failures, or process PR reviews. Works on the current branch's open PR.