Databases

Comprehensive video processing toolkit for content analysis, transcription, frame extraction, and documentation generation. Use when working with video files (.mp4, .avi, .mov, .mkv) or YouTube URLs for transcribing video content and generating subtitles, extracting and analyzing frames at intervals or timestamps, creating summaries and reports from video content, extracting metadata and technical information, processing video from filesystem, YouTube, or database sources, or generating documentation from training videos or tutorials. Supports automatic YouTube URL detection and downloading with extended metadata (channel, views, likes, tags).

Guide developers through database migration best practices including versioning, rollbacks, and zero-downtime strategies

Universal Python/Node.js backend expert. Handles API routes, database operations, business logic, configuration management, anti-duplication checks. Auto-activates on keywords "backend", "API", "database", "server", "endpoint", "Python", "FastAPI" or paths api/**, services/**, models/**.

Modern Python backend stack: FastAPI, SQLAlchemy 2.0, Pydantic v2, uv, ruff.Use when: building Python APIs, async services, or working with Python backend code.Triggers: "fastapi", "python backend", "sqlalchemy", "pydantic", "uv", "ruff","python api", "async python".

Build integration tests for data access in the widget host app. Use when setting up test databases, running EF Core migrations for tests, or validating repository behavior end-to-end.

Build and bootstrap WordPress headless (PHP-FPM) with an idempotent wp-cli entrypoint and WPGraphQL enabled, using MariaDB/MySQL from docker-compose. Use when asked to implement or fix docker/wp/Dockerfile and docker/wp/entrypoint.sh for WordPress in this repo.

Retrieval-Augmented Generation (RAG) for grounding LLM responses withexternal knowledge. Covers document chunking, embeddings, vector stores(pandas, ChromaDB), similarity search, and conversational RAG pipelines.

This skill should be used when debugging full-stack issues that span UI, backend, and database layers. It provides a systematic workflow to detect errors, analyze root causes, apply fixes iteratively, and verify solutions through automated server restarts and browser-based testing. Ideal for scenarios like failing schedulers, import errors, database issues, or API payload problems where issues originate in backend code but manifest in the UI.

Build React SPAs where components are declarative UI consuming external state (Zustand/XState/TanStack Query). Logic lives in stores, not components.

Neon PostgreSQL serverless database - connection pooling, branching, serverless driver, and optimization. Use when deploying to Neon or building serverless applications.

Experto en el universo "Subordinación y Valor" (SyV) - cronología, facciones, personajes, geografía y coherencia narrativa post-apocalíptica (2020-2178)

Context isolation for query-type MCP tools (LSP, search, database) via external CLI. Use when MCP query results consume too many context tokens.

Validate images against tacosdedatos illustration style guide. Use this skill when reviewing generated images, checking uploaded images for brand consistency, providing quality feedback on visual assets, or deciding if an image is ready for publication. Returns pass/fail with specific actionable feedback.

Backend-Frontend integration patterns expert. Type-safe API contracts with Pydantic-Zod validation sync (Python FastAPI) or Prisma-TypeScript native (Next.js). Shadcn forms connected to backend, error handling, loading states. Use when creating full-stack features.

Expert in photo content recognition, intelligent curation, and quality filtering. Specializes in face/animal/place recognition, perceptual hashing for de-duplication, screenshot/meme detection, burst photo selection, and quick indexing strategies. Activate on 'face recognition', 'face clustering', 'perceptual hash', 'near-duplicate', 'burst photo', 'screenshot detection', 'photo curation', 'photo indexing', 'NSFW detection', 'pet recognition', 'DINOHash', 'HDBSCAN faces'. NOT for GPS-based location clustering (use event-detection-temporal-intelligence-expert), color palette extraction (use color-theory-palette-harmony-expert), semantic image-text matching (use clip-aware-embeddings), or video analysis/frame extraction.

Query dam geometries in the USA from the GeoConnex knowledge graph. Returns dam locations and metadata as a GeoDataFrame.

This skill provides comprehensive knowledge for TanStack Query v5 (React Query) server state management in React applications. It should be used when setting up data fetching with useQuery, implementing mutations with useMutation, configuring QueryClient, managing caching strategies, migrating from v4 to v5, implementing optimistic updates, using infinite queries, or encountering query/mutation errors.Use when: initializing TanStack Query in React projects, configuring QueryClient settings, creating custom query hooks, implementing mutations with error handling, setting up optimistic updates, using useInfiniteQuery for pagination, migrating from React Query v4 to v5, debugging stale data issues, fixing caching problems, resolving v5 breaking changes, implementing suspense queries, or setting up query devtools.Keywords: TanStack Query, React Query, useQuery, useMutation, useInfiniteQuery, useSuspenseQuery, QueryClient, QueryClientProvider, data fetching, server state, caching, staleTime, gcTime, query inva

Apply consistent coding style and formatting standards using automated tools (ESLint, Prettier, Ruff) with clear naming conventions, top-down code organization, and appropriate function/component sizing. Use this skill when writing any code in any language, naming files and variables, structuring code within files, organizing imports, configuring linters and formatters, or setting up pre-commit hooks. Apply when working on TypeScript/JavaScript files, Python files, .NET/C# files, configuration files (tsconfig.json, .prettierrc, .eslintrc), or any code that needs consistent formatting and naming. This skill ensures automated formatting with Prettier/Ruff (let tools handle it), ESLint/analyzer enforcement, TypeScript strict mode always enabled, proper naming conventions (PascalCase.tsx for React components, camelCase.ts for utilities, IPascalCase for interfaces with I prefix, PascalCase for types without prefix, camelCase for functions/constants/database fields/API endpoints/JSON keys, no underscore prefix for

Describes the structure of the Food Journal database that allows to store and read food journal entries

Review React components for best practices, hooks usage, performance issues, accessibility, and TypeScript type safety. Use when you need to audit existing React components or provide code review feedback.