发现 Skills

Fetch SEC Form 4 insider trading data (Directors, CEOs, Officers) from OpenInsider. Use this to track corporate insider buying/selling signals.

Enable agents and skills to challenge users for fresh two-factor authentication proof (TOTP or YubiKey) before executing sensitive actions. Use this for identity verification in approval workflows - deploy commands, financial operations, data access, admin operations, and change control.

Given an arXiv ID or URL, fetch the paper, spawn sub-agents to read its key citations, and write an executive summary under.

Generate SEO-optimized product descriptions for e-commerce platforms (Amazon, Shopify, eBay, Etsy). Create compelling, conversion-focused copy with keywords, features, benefits, and calls-to-action. Use when creating product listings, optimizing existing descriptions, or generating bulk product copy.

World-class psychology expertise for human mind optimization. Masters learning science (age-appropriate skill acquisition for languages, coding, etc.), cognitive psychology, behavioral economics, and ethical marketing/conversion psychology. Use when designing learning programs, understanding human motivation, optimizing user experiences, creating persuasive messaging, improving conversion rates, or analyzing human behavior patterns. Covers developmental psychology, memory systems, habit formation, decision-making biases, and customer psychology.

Generate images and videos via Runware API. Access to FLUX, Stable Diffusion, Kling AI, and other top models. Supports text-to-image, image-to-image, upscaling, text-to-video, and image-to-video. Use when generating images, creating videos from prompts or images, upscaling images, or doing AI image transformation.

Create AI-First Website with GEO (Generative Engine Optimization) and marketing rules to convert visitors into leads

Google search via Serper API with full page content extraction. Fast API lookup + concurrent page scraping (3s timeout). One well-crafted query returns rich results — avoid multiple calls. Two modes, explicit locale control. API key via .env.

Get snow conditions, forecasts, and ski reports for any mountain resort worldwide. Use when asked about snow, powder, ski conditions, or mountain weather. Supports 1000+ resorts via OpenSnow. Users can set favorite mountains for quick access. Supports SnowTick 4-letter codes (JHMR, TARG, MMTH) for quick lookups.

Generate promo video plan with 30-45s script, shot-by-shot storyboard, and optional Remotion/Montage-tool config. Use when user says "create video", "promo video", "video script", "storyboard", "demo video", or "product video plan". Do NOT use for social media text posts (use /content-gen) or landing page copy (use /landing-gen).

Get Portland transit information including arrivals, trip planning, and alerts. Use when user asks about buses, MAX, trains, or transit in Portland.

Control Alexa devices via VoiceMonkey API v2 - make announcements, trigger routines, start flows, and display media.

Real-time WhatsApp voice message processing. Transcribe voice notes to text via Whisper, detect intent, execute handlers, and send responses. Use when building conversational voice interfaces for WhatsApp. Supports English and Hindi, customizable intents (weather, status, commands), automatic language detection, and streaming responses via TTS.

Meta-skill for internal codebase exploration at varying depths (quick/deep/architecture)

Provides comprehensive guidance for DALL-E AI image generation including prompt creation, image generation, variations, and editing. Use when the user asks about DALL-E, needs to generate AI images, create image variations, or work with DALL-E API.

Provides comprehensive guidance for PostgreSQL database including SQL syntax, advanced features, JSON support, full-text search, and performance tuning. Use when the user asks about PostgreSQL, needs to work with PostgreSQL features, write complex queries, or optimize PostgreSQL databases.

Provides comprehensive guidance for Vant Vue 3 mobile component library including mobile components, themes, and best practices. Use when the user asks about Vant, needs to build mobile applications with Vue 3, or implement mobile UI components.

NautilusTrader algorithmic trading platform. Use for building trading strategies, backtesting, live trading, data handling, and quantitative finance applications.

Create 3D scenes in Blender using Python scripts. Renders images from procedurally generated scenes.

Checks for all types of code review issues found by the Qualimetry HITL code reviewer on a source file, including coding standards violations, design and best practice issues, general coding principle violations, secure coding principle violations, and policy violations. Retrieves a compliant code example showing how to resolve the issues. Invoked as the review-check skill, optionally with a file path argument, to check a previously reviewed file.

Detects, analyzes, and suggests changes to the Opencode CLI configuration file (config.json). Use this when the user complains about Opencode performance, asks to change the default model, or wants to modify CLI behavior.

Creates professional Mermaid diagrams with semantic styling and visual hierarchy. Use when creating flowcharts, sequence diagrams, state machines, class diagrams, or architecture visualizations.

Professional video prompt generator and optimizer for multi-platform AI video generation. Supports: - Text-to-video (文生视频) - Image-to-video (图生视频) - First/last frame generation (首尾帧) - Reference image guided generation (参考图) - Intelligent multi-frame generation (智能多帧/分镜) - Universal reference (图片、视频、音频) - Multi-platform support (可灵, Vidu, 即梦, Sora, Google, Runway, Pika, etc.) Use when: - User wants AI video generation prompts - User provides images/videos/audio for reference - User specifies platform (Kling, Vidu, Jimeng, Sora, Google, Runway, Pika) - User wants storyboard or multi-frame video - User wants first/last frame control - User wants to optimize existing video prompts

Write documents in a natural, human style. Use when writing essays, papers, documentation, reports, articles, or any prose content. Avoids common AI writing patterns.