Explorar skills

Extract uncaptured knowledge from the current conversation before it's lost to compaction. Use after completing a task, before switching context, before large exploratory work (multi-file reads, codebase scans), or when the user signals session end. Trigger: '/extract', 'extract knowledge', 'capture session knowledge'. Also prompt mid-session: 'Task complete — want me to run /extract?' and 'Switch

Structured retrospective on a shipped commit range, release, PR, commit, or session: per-fix validation, evidence-sourcing pass, re-diagnosis, action verdicts, growing failure-mode library. Triggers — "/aria-cowork:retrospect", "retrospect this". (Cowork variant — namespaced-only.)

Quicknode blockchain infrastructure: endpoint access for 80+ chains over RPC/WebSocket/gRPC/REST, Streams, Webhooks, SQL Explorer, IPFS, Solana DAS API, Yellowstone and Hypercore gRPC, Key-Value Store, Admin API, x402 and MPP pay-per-request RPC, and Agent Subscriptions. Use for any Quicknode product, qn_ methods, blockchain data access on Ethereum, Solana, Hyperliquid and other supported chains,

Video analysis and inspection using FFprobe and FFmpeg. Reads metadata, codec info, resolution, bitrate, duration, HDR status, keyframe structure, audio loudness, scene boundaries, and quality metrics (VMAF, SSIM, PSNR). Use when user says "analyze", "inspect", "info", "metadata", "quality", "VMAF", "SSIM", "PSNR", "scene detect", "keyframes", "HDR", "bitrate", "ffprobe", or "what codec".

Generate database migrations with up/down scripts — Alembic, Flyway, Liquibase, and framework-native migrations.

Create GitLab CI/CD pipelines — stages, jobs, caching, artifacts, environments, and Auto DevOps customization.

Longform-to-shortform video pipeline that automatically extracts viral-ready short clips from long videos. V3 pipeline with VLM-powered visual analysis (Gemini 2.5 Flash), auto-detects screen recordings vs talking-head, uses "Framed" layout for screen content (padded top/bottom with centered captions), face-tracked crop for talking-head. Transcribes with WhisperX, scores by visual interest + trans

Edita textos em russo seguindo o infostyle de Ilyakhov, removendo palavras-chave, clichês e afirmações infundadas, substituindo-os por fatos, números e benefícios. Adapta a rigidez ao contexto e é ativado quando usuários pedem para editar, melhorar ou revisar textos em russo.

Programmatic video creation using Remotion (React-based). Generates title cards, data visualizations, motion graphics, branded intros/outros, animated text, and template-based videos from data. Claude writes React components, Remotion renders them headlessly to video. Use when user says "create video", "title card", "intro", "outro", "motion graphics", "animated text", "data visualization video",

Fix a bug with structured diagnostic workflow. Uses interview to clarify details and Bug Council for complex issues.

Identifica palavras-chave que concorrentes posicionam, mas o domínio alvo não, usando dados do Ahrefs, revelando oportunidades de conteúdo e lacunas de tópicos.

Load this skill whenever the project contains interactive UI elements that users touch, tap, click, drag, swipe, or gesture with — buttons, links, drag-and-drop interfaces, sliders, carousels, or custom touch interactions. Under no circumstances create touch targets smaller than 44×44 CSS pixels. Absolutely always provide pointer cancellation, single-pointer alternatives to gestures, and load alon