productivity▌

Enable reliable interaction with Anki through the AnkiConnect local HTTP API. Use this skill to translate user requests into AnkiConnect actions, craft JSON requests, run them via curl/jq (or equivalent tools), and interpret results safely.

Real-time GLSL fragment shader development for procedural graphics and visual effects. \n \n Provides complete Shadertoy API reference including built-in inputs (iResolution, iTime, iMouse, iChannel0-3) and the mainImage entry point structure \n Covers essential patterns: ray marching with distance fields, procedural color palettes, hash functions, 2D/3D rotations, domain repetition, and post-processing techniques \n Includes multi-pass rendering workflows for temporal feedback and buffer compos

Rive is a state machine-based animation platform that enables designers to create interactive vector animations with complex logic and runtime interactivity. Unlike timeline-only animation tools (like Lottie), Rive supports state machines, input handling, and two-way data binding between application code and animations.

Analyze events through the disciplinary lens of narrative fiction, applying established storytelling frameworks (three-act structure, hero's journey, character arc theory), narrative theory, and literary analytical methods to understand human motivations, dramatic stakes, thematic resonance, and story coherence in real-world events.

Build touch-optimized, performant mobile experiences with proper viewport handling and responsive patterns.

Status: Production Ready Last Updated: 2026-01-25 Dependencies: None Latest Versions: jquery@4.0.0, jquery-migrate@4.0.2

Complete iOS/macOS/watchOS/tvOS development with SwiftUI, async/await, protocol-oriented design, and actor-based concurrency. \n \n Covers SwiftUI state management with @Observable, async/await patterns, protocol-oriented architecture with associated types, and actor isolation for thread safety \n Includes validation checkpoints at each workflow stage: compilation verification, strict warning checks for actor isolation, and async test confirmation \n Provides reference guides for SwiftUI pattern

Comprehensive trading plan framework with risk management, position sizing, entry/exit rules, and performance tracking. \n \n Covers five trading styles (day, swing, position, options, investing) with specific rules and best practices for each \n Includes mandatory risk management components: 1% rule, 2R minimum reward-to-risk, position sizing formulas, and daily loss limits to prevent account blowup \n Provides detailed entry and exit strategies using technical patterns, support/resistance, ATR

Convert documents, spreadsheets, presentations, images, audio, and web content to Markdown for LLM processing. \n \n Supports 15+ formats including PDF, Word, PowerPoint, Excel, HTML, CSV, JSON, XML, images with OCR, audio with transcription, ZIP archives, YouTube URLs, and EPub \n Preserves document structure including headings, tables, lists, and links in the converted Markdown output \n Optional Azure Document Intelligence integration ( -d flag) for improved extraction on complex or scanned P

Best Minds \n \n \"Don't think of LLMs as entities but as simulators.\"\n— Andrej Karpathy \n \n 核心 \n 不要问 AI \"你怎么看\"。 \n 要问： 这个问题，世界上谁最懂？TA 会怎么说？ \n 然后模拟那个人。 \n 原则 \n \n 问题决定人数 — 一个人够就一个，需要碰撞才多个 \n 找真正最懂的 — 不是找\"合适的\"，是找\"最强的\" \n 基于真实 — 模拟要基于 TA 公开的思想、著作、言论 \n 引用原话 — 尽可能用 TA 说过的话 \n \n vs ai-coaches \n \n \n \n ai-coaches \n best-minds \n \n \n \n \n 从 13 个预设智者选 \n 从全世界找 \n \n \n 基于关键词匹配 \n 基于问题本质 \n \n \n