Explorar skills

Audit a project's Claude Code setup against official Anthropic documentation. Evaluates 9 areas: CLAUDE.md, Rules, Skills, Sub-agents, Hooks, Permissions, Settings, MCP servers, and Feature Selection. Produces a scored AUDIT-REPORT.md with findings that cite documentation sources fetched during the session. Use this skill when the user says 'audit', 'audit my setup', 'review my Claude Code config'

Generate images with transparent backgrounds using difference matting technique. Use when creating assets with transparency, extracting alpha channels, batch generating transparent images via Vertex AI, or working with PNG transparency.

VAD-first audio transcription pipeline with evidence-backed Whisper configuration, language-aware model routing, dictionary correction, and LLM post-processing. Use when the user wants to transcribe audio files — meetings, interviews, voice memos, podcasts. Handles Norwegian (NB-Whisper) and English (whisper-large-v3-turbo) with automatic language detection. Runs locally on Apple Silicon via MLX.

Convert vague real-world leisure requests into concrete activity plans. Use when the user says they are bored, asks what to do tonight or this weekend, wants date ideas, solo outings, hangouts, nearby classes, or short itineraries that should account for location, time, weather, budget, companions, travel time, and prior activity history. Use live web research to verify current venues, events, wea

Orchestrate hierarchical multi-agent research with lead agents, sub-agents, critical review, and synthesis. Use for deep investigation tasks, research projects, complex analysis, or when exploring unfamiliar topics thoroughly.

Use Google's Deep Research API (Gemini) to conduct comprehensive, multi-source research that runs for 5-20 minutes server-side and produces detailed research reports. Use when the user asks for "deep research", thorough investigation of complex topics, market analysis, competitive landscaping, or any research requiring multiple web sources synthesized into comprehensive reports. This skill uses th

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Archivado. Las habilidades CCB activas ahora se encuentran en claude-code-skills, bajo ai-collaboration/ y research/stem-modeling.

Analiza el código de extensiones de Chrome para generar todos los materiales de envío necesarios para la Chrome Web Store, incluyendo descripciones, permisos y políticas de privacidad. Se utiliza para frases como "materiales de envío" o "analizar este plugin" para el listado, y genera un paquete estructurado con texto, archivos y evidencia de auditoría.

Convierta un resumen, enlace o tema de investigación en un prompt de video controlado y basado en fuentes que se ejecuta en HiAPI Seedance 2.0 o HappyHorse 1.0. Úselo cuando un usuario solicite dirigir, planificar o crear un guion gráfico para un video antes de la generación.

Investigue los próximos eventos de ganancias, analice patrones históricos de aciertos/errores y estime las reacciones de precios post-ganancias utilizando la API de Finskills.

Gestiona el inventario de la despensa, listas de compras e historial de adquisiciones. Úselo para añadir/ver/buscar inventario por zona, gestionar listas de compras, registrar compras y verificar fechas de caducidad o artículos con bajo stock.