20 skills · sorted by relevance
Build HyperFrames animations from small motion recipes, scene templates, and transitions. The skill guides runtime selection, including GSAP, Lottie, and Three.js, and provides an audit script to examine timing and choreography while following HyperFrames requirements for reproducible rendering.
Guides development of apps for viewing USD, a 3D scene format. Selects browser streaming or local implementation references, covering rendering, camera controls, selection, interface layout, and validation while keeping users’ scene files unchanged.
Build charts and interactive diagrams in TypeScript with explicit data types and clear component boundaries. Guides library selection, data validation, interaction design, and shareable view settings to support maintainable visualization code.
Refactor large macOS SwiftUI views into focused files and components. Clarify window state, selection, commands, and AppKit integration while preserving existing behavior and keeping the main layout stable as users change selections.
How to read and change anything in the Unity Editor with RQL (rql-query / rql-mutate / rql-schema): the query language, operators, sources (scene objects, assets, scenes, prefabs, console logs, Editor state), Editor operations (create, add components, scenes, prefabs, assets, selection, Play Mode) and what installed extensions add.
The English summary is being prepared. Showing the original description.
Create Viking web projects, start and verify a local preview, or deploy a generated project to Volcengine IGA Pages when explicitly requested. Includes agent-guided feature, eligible application, dataset, scene, and authentication choices. Use only after confirming the installed CLI exposes `vs project`; otherwise stop without taking action.
The English summary is being prepared. Showing the original description.
Find topic-specific API guidance and implementation patterns for Three.js projects. Ten references cover scene setup, geometry, materials, lighting, textures, animation, loading models, custom visual effects, postprocessing, and mouse or touch interaction.
Add mouse, touch, and keyboard interaction to Three.js scenes. Implement object picking, camera navigation, dragging, and transform handles, with examples for selection feedback, coordinate conversion, and limiting the cost of interaction checks.
Create game assets through fal.ai, including sprites, textures, 3D models, sound effects, music, voices, and video clips. Guides consistent visual variations, file conversion, model selection, and generation records so assets can be traced and regenerated.
Build custom browser charts with D3, including precise labels, annotations, zooming, and range selection. Create SVG graphics that adapt to mobile screens, use meaningful contextual backgrounds, and support export when needed.
Use for AI-assisted Unity work that needs live repo discovery, project-derived routing, runtime-owner proof, runtime-visible output hard stops, runtime numeric proof for repeated visible-output failures, state-step guards, multi-agent scope ownership, modular C#/asmdef safety, UI/scene/visual asset gates, data-first content changes, validation, cleanup proof, or durable workflow rules. Best when agents must prove the actual folder/module/scene/prefab/runtime owner before editing, especially runtime UI, generated assets, code graphs, tutorial/state flows, guided selection/action flows, overlay/dim source-bound mistakes, coordinate conversions, focus/highlight/marker/HUD alignment, predictive lead aiming, ballistic trajectories, spatial IoU verification, or repeated "fix still not visible" failures.
The English summary is being prepared. Showing the original description.
Generate AI images using Gemini or GPT APIs directly. Covers model selection (Gemini for scenes; GPT Image 2 for text rendering, batch variations, multi-reference compositing; GPT Image 1.5 for transparent icons), the 5-part prompting framework, API calling patterns, multi-turn editing, and quality assurance. Produces photorealistic scenes, icons, illustrations, OG images, posters, infographics, and product shots. Use when building websites that need images, creating marketing assets, or generating visual content. Triggers: 'generate image', 'ai image', 'create hero image', 'make an icon', 'generate illustration', 'create og image', 'poster', 'infographic', 'image variations', 'gpt-image-2', 'ai art', 'image generation'.
The English summary is being prepared. Showing the original description.
Generate cinematic clips with Seedance 2.0 using camera directions, multiple shots, and synchronized speech, sound effects, and ambience. Reference images help maintain character appearance, while the skill guides prompt structure, provider selection, previews, and checks of the finished clips.
Build prompts for FLUX image generation and editing, with guidance on model selection, lighting, composition, text, and precise colors. It also covers structured scene descriptions using JSON and editing with multiple reference images.
Generate images and videos through Atlas Cloud by checking each model’s input requirements before submission. Guides the agent through sending a request, checking progress within a time limit, and downloading and validating the resulting media.
Build image-based conversations with LLaVA, an AI model that combines image understanding with language. Covers setup, model selection, image descriptions, follow-up questions, and memory-saving options for running models on a GPU.
Premise, theme, controlling idea, subject selection and logline for scripts (前提/主题/立意/选材/戏核) — merged from Lajos Egri's premise-as-tyrant and dialectic, Robert McKee's controlling idea (value + cause) and idea/counter-idea, Neill Hicks' five premise questions, Lisa Cron's "third rail" (desire vs misbelief, origin scene, what-if), Julian Hoxter's logline and theme-attitude rule, Blake Snyder's logline/genre/title tests, and Lu Jun's Chinese craft chapters on 选材要严/开掘要深/视角要新/戏核要好/情节要奇. Use when turning a vague idea into a premise, finding what a story is really about, choosing a subject and angle, testing a logline, deciding the ending from the theme, or diagnosing a script that "has events but no story".
The English summary is being prepared. Showing the original description.
Use when designing a new Godot feature or system — guides scene tree planning, node type selection, and architectural decisions
The English summary is being prepared. Showing the original description.
Produce presenter-led AI avatar videos with Synthesia Studio and Synthesia API. Use for Synthesia-specific avatar video planning, avatar/voice/language selection, scripted scenes, template personalization, API job lifecycle, localization/dubbing, brand/training/product workflows, consent/rights/safety checks, artifact custody, troubleshooting, and final QA.
The English summary is being prepared. Showing the original description.
Produce HeyGen avatar videos with Direct Video, Video Agent, Digital Twin, Avatar Realtime, and related avatar/voice/asset APIs. Use for provider routing, avatar and voice selection, script-to-video workflows, lip-sync from audio, backgrounds/scenes, callbacks and polling, consent and rights checks, localization handoffs, artifact custody, QA, and troubleshooting HeyGen avatar-video productions.
The English summary is being prepared. Showing the original description.