所有 Skills
找到 3865 个 Skills
Skills 列表
pixijs-ticker
Use this skill when running per-frame logic or controlling the PixiJS v8 render loop. Covers Ticker.add/addOnce/remove, deltaTime vs deltaMS vs elapsedMS, UPDATE_PRIORITY ordering, maxFPS/minFPS capping, speed scaling, Ticker.shared vs new instances, per-object onRender hook, manual rendering. Triggers on: Ticker, UPDATE_PRIORITY, deltaTime, deltaMS, elapsedMS, onRender, app.ticker, maxFPS, minFPS, Ticker.shared.
pixijspixijs-scene-text
Use this skill when rendering text in PixiJS v8. Covers Text for canvas-quality styled labels, BitmapText for cheap per-frame updates via glyph atlas, HTMLText for HTML/CSS markup via SVG, SplitText and SplitBitmapText for per-character animation, TextStyle, tagStyles, constructor options, TextOptions, HTMLTextOptions, BitmapText, SplitTextOptions, SplitBitmapTextOptions. Triggers on: Text, BitmapText, HTMLText, SplitText, SplitBitmapText, TextStyle, HTMLTextStyle, BitmapFont.install, tagStyles, fontFamily, wordWrap.
pixijspixijs-filters
Use this skill when applying visual effects to PixiJS v8 containers via the filter pipeline. Covers built-in filters (AlphaFilter, BlurFilter, ColorMatrixFilter, DisplacementFilter, NoiseFilter), custom Filter.from() with GLSL/WGSL, options (resolution, padding, antialias, blendRequired), filterArea optimization, pixi-filters community package. Triggers on: filters, BlurFilter, ColorMatrixFilter, DisplacementFilter, NoiseFilter, Filter.from, GLSL filter, pixi-filters, filterArea.
pixijspixijs-scene-particle-container
Use this skill when rendering thousands of lightweight sprites in PixiJS v8. Covers ParticleContainer with Particle instances, addParticle/removeParticle, particleChildren array, dynamicProperties (vertex, position, rotation, uvs, color), boundsArea, roundPixels, update. Triggers on: ParticleContainer, Particle, IParticle, addParticle, particleChildren, dynamicProperties, boundsArea, particle effects, constructor options, ParticleContainerOptions, ParticleOptions.
pixijspixijs-color
Use this skill when creating, converting, or manipulating colors in PixiJS v8. Covers Color class input formats (hex, CSS names, RGB/HSL objects, arrays, Uint8Array), conversion methods (toHex, toNumber, toArray, toRgba), component access, setAlpha/multiply/premultiply, Color.shared singleton. Triggers on: Color, ColorSource, hex, rgb, hsl, tint, premultiply, Color.shared, color conversion.
pixijspixijs-create
Use this skill when scaffolding a new PixiJS v8 project with the create-pixi CLI or adding PixiJS to an existing project. Covers npm/yarn/pnpm/bun create commands, interactive vs non-interactive flows, bundler vs creation template categories, available template presets (bundler-vite, bundler-webpack, bundler-esbuild, bundler-import-map, creation-web, framework-react, extension-default), Node version requirements, `npm install pixi.js` for existing projects, post-scaffold dev flow, and the Vite top-level-await production-build gotcha. Triggers on: create pixi.js, npm create, npm install pixi.js, scaffold, template, bundler-vite, bundler-webpack, creation-web, framework-react, new project, existing project, getting started, quick start.
pixijspixijs-custom-rendering
Use this skill when writing custom shaders, uniforms, filters, or batchers in PixiJS v8. Covers Shader.from({gl, gpu, resources}), GlProgram/GpuProgram, UniformGroup with typed uniforms (f32, vec2, mat4x4), UBO mode, textures as resources, custom Filter via Filter.from, GLSL ES 3.0 conventions (in/out, finalColor, texture()), uBackTexture sampling, pixi.js/unsafe-eval for strict CSP, custom Batcher via extensions. Triggers on: Shader, GlProgram, GpuProgram, UniformGroup, Batcher, Filter, Filter.from, GLSL, WGSL, UBO, uniform, custom shader, finalColor, uBackTexture, blendRequired, unsafe-eval.
pixijspixijs-scene-dom-container
当需要在 PixiJS v8 画布上叠加 HTML 元素时使用此技能。涵盖 DOMContainer 的 element、anchor 以及场景图驱动的 CSS 变换、pixi.js/dom 副作用导入、DOMPipe 注册、可见性同步、指针事件处理。触发词：DOMContainer、pixi.js/dom、DOMPipe、HTML 叠加、画布上的输入框、iframe 叠加、DOMContainerOptions、element、anchor、构造函数选项。
pixijspixijs-blend-modes
Use this skill when compositing display objects with blend modes in PixiJS v8. Covers standard modes (normal, add, multiply, screen, erase, min, max), advanced modes via pixi.js/advanced-blend-modes (color-burn, overlay, hard-light, etc.), batch-friendly ordering. Triggers on: blendMode, additive, multiply, screen, overlay, color-burn, color-dodge, advanced-blend-modes, glow, erase.
pixijspixijs-scene-mesh
Use this skill when rendering custom geometry in PixiJS v8. Covers Mesh with MeshGeometry (positions, uvs, indices, topology), MeshSimple for per-frame vertex animation, MeshPlane for subdivided deformation, MeshRope for path-following textures, PerspectiveMesh for 2.5D corners. Triggers on: Mesh, MeshGeometry, MeshSimple, MeshPlane, MeshRope, PerspectiveMesh, positions, uvs, indices, topology, setCorners, constructor options, MeshOptions, MeshPlaneOptions, MeshRopeOptions, SimpleMeshOptions, PerspectivePlaneOptions.
pixijspixijs-environments
Use this skill when running PixiJS v8 outside a standard browser: Web Workers, OffscreenCanvas, Node/SSR, or CSP-restricted contexts. Covers DOMAdapter.set, BrowserAdapter, WebWorkerAdapter, custom Adapter interface, pixi.js/unsafe-eval for strict CSP. Triggers on: DOMAdapter, BrowserAdapter, WebWorkerAdapter, Web Worker, OffscreenCanvas, Node, headless, SSR, CSP, unsafe-eval, Adapter.
pixijspixijs-scene-gif
Use this skill when displaying animated GIFs in PixiJS v8. Covers the pixi.js/gif side-effect import, Assets.load returning a GifSource, GifSprite playback (play/stop/currentFrame/animationSpeed), autoPlay/loop options, onComplete/onLoop/onFrameChange callbacks, GifSource sharing, clone, destroy. Triggers on: GifSprite, GifSource, pixi.js/gif, animationSpeed, currentFrame, autoPlay, onComplete, onFrameChange, constructor options, GifSpriteOptions.
pixijspixijs-accessibility
Use this skill when adding screen reader and keyboard navigation to PixiJS v8 apps. Covers AccessibilitySystem options (enabledByDefault, debug, activateOnTab, deactivateOnMouseMove), per-container accessibility properties, shadow DOM overlay, mobile touch-hook activation. Triggers on: accessibility, a11y, screen reader, ARIA, keyboard navigation, tab order, AccessibilitySystem, accessibleTitle, accessibleHint, tabIndex, accessibleChildren.
pixijspixijs-migration-v8
Use this skill when upgrading to PixiJS v8 from v7 or diagnosing broken v7 code after an upgrade. Covers async app.init, single pixi.js package (deprecated @pixi/* sub-packages), Graphics shape-then-fill, BaseTexture → TextureSource, shader/uniform rework, ParticleContainer+Particle, constructor options objects, DisplayObject removal, settings/utils removal, Ticker signature, events rewrite. Triggers on: migrate v7, v8 breaking changes, @pixi/ import, DisplayObject, beginFill, endFill, cacheAsBitmap, BaseTexture, deprecated.
pixijs
core-data-expert
Expert Core Data guidance (iOS/macOS): stack setup, fetch requests & NSFetchedResultsController, saving/merge conflicts, threading & Swift Concurrency, batch operations & persistent history, migrations, performance, and NSPersistentCloudKitContainer/CloudKit sync.
avdlee
html-slides
使用 reveal.js 创建惊艳的 HTML 演示文稿。
claude-office-skillsppt-visual
设计演示文稿视觉和幻灯片布局。创建视觉概念，推荐图形，并为有影响力的PowerPoint幻灯片提供设计规范。
claude-office-skills
cross-border-ecommerce
Cross-border e-commerce expansion advisor. Scores target markets on 8 weighted dimensions (market size, ecommerce penetration, competition, regulatory complexity, logistics infrastructure, payment ecosystem, cultural distance, IP protection), compares 5 fulfillment models with cost and transit data, provides country-by-country tax/duty compliance guides (EU VAT/IOSS, UK VAT, US sales tax, CA GST, AU GST, JP consumption tax), maps local payment preferences by market, and builds a phased expansion roadmap. No API key required.
nexscope-aiexcel-automation
>
claude-office-skills
computer-automation
Vision-driven desktop automation using Midscene. Control your local desktop (macOS, Windows, Linux) or a remote Windows desktop over RDP with natural language commands. Operates entirely from screenshots — no DOM or accessibility labels required. Can interact with all visible elements on screen regardless of technology stack. ⚠️ In local mode this takes over the user's real mouse and keyboard. For web apps, prefer "Browser Automation" instead. Only use this for desktop-native apps (Electron, Qt, native macOS/Windows/Linux) that cannot run in a browser, or for driving a remote Windows host via RDP. Triggers: open app, press key, desktop, computer, click on screen, type text, screenshot desktop, launch application, switch window, desktop automation, control computer, mouse click, keyboard shortcut, screen capture, find on screen, read screen, verify window, close app, test Electron app, rdp, remote desktop, windows server, connect via rdp Powered by Midscene.js (https://midscenejs.com)
web-infra-dev
andrej-karpathy-perspective
Andrej Karpathy的思维框架与表达方式。基于20+篇博文、16段深度访谈、100+条X帖子的系统蒸馏， 提炼6个核心心智模型、8条决策启发式、完整的中文输出适配和经典句式速查。 用途：作为思维顾问，用Karpathy的视角分析AI技术可靠性、学习方法、行业趋势、产品设计。 当用户提到「用Karpathy的视角」「Karpathy会怎么看」「卡帕西」「karpathy模式」时使用。 也适用于：Software 2.0/3.0讨论、vibe coding话题、神经网络训练、AI炒作判断、LLM能力边界。 即使用户只是说「从工程现实主义角度」「march of nines」「构建即理解」「锯齿状智能」也可触发。 不在用户只是普通问AI相关问题时触发——只在明确想要Karpathy式思维框架时激活。
alchaincyf
context7
通过 Context7 API 获取软件库、框架和组件的最新文档。当需要查询任何编程库或框架的文档、查找特定 API 或功能的代码示例、验证库函数的正确用法，或获取训练后可能已更改的库 API 的最新信息时，应使用此技能。
intellectronicayoutube-transcript
从YouTube视频中提取转录文本。当用户要求获取YouTube视频的转录、字幕或隐藏式字幕，并提供YouTube网址（youtube.com/watch?v=、youtu.be/等格式）时使用。支持带或不带时间戳的输出。
intellectronicanano-banana-pro
Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.
intellectronica