Video & Animation

End-to-end agentic playbook for fixing a Jira bug (WEBUI-<id>, or an ELEMENTS-<id>/other ticket whose fix lands in nuxeo-web-ui) in the nuxeo-web-ui repo: runs fully autonomously end-to-end (YOLO mode, no confirmation gates), analyse the ticket + all comments, reproduce and capture evidence (images AND videos) to ~/Desktop/jira-evidence/<TICKET-ID>/fix/ first, then branch from both lts-2025 and maintenance-3.1.x, fix without inducing regressions, run the PR gating checks, create signed-commit PRs on both bases, watch CI and fix/rerun failures, then evaluate the Ready-for-QA checklist. Use when asked to fix a WEBUI-/Jira bug, "commit and raise PR", or take a nuxeo-web-ui ticket to Ready for QA.

Turn an object or character reference image into a quality-gated, animation-ready procedural Three.js model built in code. Use for image-to-3D reconstruction, detail-accurate object rebuilds, stylized/likeness-maximized human characters, sculpt specs, and staged code generation.

Three-stage Discover, Define, Deliver workflow for getting distinctive, studio-grade UI design out of an AI coding agent instead of the default "AI template" look. Use whenever the user asks to design or redesign a landing page, marketing page, app screen, onboarding flow, dashboard, poster-like web page, or game UI and wants it to look original, bold, premium, or "not like AI made it", including phrases like "make it unique", "it looks generic", "too much AI vibe", "AI 味太重", "千篇一律", "设计得独特一点", "榨出创造力", "design critic", "critique loop", "seed string", "double diamond", or "why does my AI design always look the same". Also use when iterating on an existing page whose layout is the stock hero-left/illustration-right template, or when the user wants image or video generation woven into a UI. Covers seed-string randomness, ambitious briefs, a screenshot-only design-critic subagent loop, image/video-driven motion, and the final subtraction pass.

Turn a music track (an audio file, a video to pull audio from, or a track generated from a mood brief) into a beat-synced video — lyric video, slideshow, or kinetic promo. The music drives all pacing; any user-supplied images/videos are cut onto the same beat grid, and a complete video needs zero assets. Narrated pieces → the input-matched workflow (see /hyperframes). Unclear → /hyperframes.

Use Ghostget to give a bring-your-own coding agent bounded, local-first web capabilities: capture or scrape public and signed-in web pages into Markdown; archive authorized audio, video, and transcripts with verification; query encrypted cached email, contacts, inbox, and messaging views; resolve a live conversation, read fresh context, preview ordered message bubbles, and execute an exactly authorized turn through one provider route; publish and reconcile text, image, and video posts through observed installed social capabilities; inspect or develop bounded provider contracts for X, LinkedIn, Bluesky, Substack Notes, Threads, TikTok, Instagram, and YouTube Shorts; save private native article drafts; operate reviewed Beeper messaging actions across the pinned official CLI and fixed Desktop loopback operations; and build or run typed provider plugins from recorded browser-session APIs or versioned provider CLIs. Trigger for web capture, URL clipping, authenticated sites, social media posting or cross-posting,

Use this skill when loading 3D models into melonJS — glTF and GLB scenes, OBJ/MTL models, materials, imported lights, node animation, ground shadows and GPU instancing. Covers level.load options including the async flag, the rightHanded conversion, and exactly what the loader does and does not support. Triggers on: glTF, gltf, glb, OBJ, MTL, 3D model, getGLTF, getOBJ, getMTL, GLTFModel, GLTFScene, level.load glb, rightHanded, lightIntensityScale, castGroundShadow, shadowGroundY, EXT_mesh_gpu_instancing, KHR_lights_punctual, skinning, Blender export, 3D asset.

Use this skill for loading and managing game assets in melonJS — the resource descriptor format, the full asset type list, preload versus load, retrieving loaded assets, base URLs and cross-origin settings, and the loading screen. Triggers on: loader, loader.preload, loader.load, resources, getImage, getJSON, getTMX, getGLTF, getVideo, getFont, setBaseURL, setOptions, crossOrigin, withCredentials, credentials, cookies, authenticated assets, CORS, asset, preload, LOADER_COMPLETE, loading screen, unload.

Animate a portrait, character, artwork or scene with Magic Hour, editing and inspecting the start frame when needed before motion. Use for image-to-video, transformations, reveals and character animation when Magic Hour is requested or is the project's chosen media provider.

Elevate any existing website or webpage to world-class software standards. Combines Apple design foundations, Emil Kowalski's tactile physics and animation principles, mobile-native touch defect eradication, optical typography, calibrated dark/light contrast, liquid glass depth, Command+K action palette, and anti-AI copy standards. Transforms ordinary, clunky, or AI-generated pages into high-craft, beautiful software with noticeable feature and visual upgrades.

Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading), reduced-motion, or the design foundations (feedback, spatial consistency, restraint) behind Apple-style interfaces.

Evaluate generated Chatterbox voice files as voice-quality artifacts: affect match, arousal/valence proxies, pause placement, intelligibility inputs, clipping, loudness, and discontinuity flags. Use when reviewing Chatterbox emotional tags, pauses, Turbo/base affect delivery, Persona Dream utterance renders, or whether generated speech matches an intended product-facing affect.

Reverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact term ("the bouncy thing when a popover opens" → Pop in; "the iOS rubber-band scroll" → Rubber-banding). Use when the user asks "what's it called when…", or describes a motion effect without knowing its name and wants the right word to prompt an AI or designer with. For naming an effect, not designing or building one.

Router and orchestrator for AI UGC video production. Use for broad outcome requests like making a UGC video or running a campaign; it routes step-specific requests to the right sub-skill and can drive the full pipeline from persona research through virality-scored video.

Turn a locked character image (from portrait-clone) into a UGC-style 9:16 talking-head video: pick a voice-reference clip, size the script to the duration, write the Seedance 2.5 prompt, generate through treg (reAPI or PiAPI), then burn a static emoji header and phrase captions with code. Use after portrait-clone when the user wants the character to speak a script on camera.

Turns Claude into a hyper-realistic AI UGC influencer studio. Use whenever the user wants to create, manage, or scale a synthetic/AI influencer: building a consistent character, writing image or video prompts, producing TikTok/Reels/Shorts-style content, or locking a recurring synthetic person with a JSON identity card + 6-layer prompt assembler.

Create short videos for any genre or placement, then independently review the actual exports.

Export a promoted fine-tuned model in the right deployment format — merged safetensors, LoRA-only, GGUF with imatrix, or FP8. Use after a checkpoint passes promotion, when choosing a quantization format for a target device, or when an exported model fails its smoke test.

Convert files between formats — PDF to Word, HEIC to JPG, MP4 to MP3, CSV to JSON, EPUB to MOBI, and 999 total routes across images, video, audio, documents, data, fonts, ebooks, and archives. Free via changethisfile.com, no API key or signup. Use when the user needs a file converted to a different format.

Create and extend complete visual brand systems through the Higgsfield CLI and bundled deterministic local tooling: palettes, SVG logo marks, typography, mockups, social graphics, packaging, signage, merchandise, posters, presentation decks, and editable PPTX/PDF brandbooks. Preserves official supplied assets, persists approvals locally, and regenerates only dependent outputs. Use when: "create a brand kit", "make a visual identity", "design a logo and brandbook", "apply this logo to branded assets", "make packaging or signage", or "extend our existing branding". Chain with higgsfield-generate for general image production and Marketing Studio brand-kits when importing website metadata for ads. NOT for unbranded image generation (use higgsfield-generate), product catalog photography (use higgsfield-product-photoshoot), website implementation (use higgsfield-websites), or native Figma/Canva/PSD/AI delivery.

Build, edit, and deploy full-stack websites, apps and games via the Higgsfield CLI (`higgsfield website …`). Each is a React 19 + TanStack Start SSR app in one Cloudflare Worker (D1/R2/KV/DO/Containers). THREE product types, picked via `--type` on create: `website` (standalone, no Higgsfield integration — references/website-flow.md), `app` (Sign in with Higgsfield + fnf SDK, Quanta — references/app-flow.md), `game` (realtime multiplayer rooms — references/game-flow.md). Routes to the right flow; each carries its own rules and deploy/publish gates. Use when: "build me a website", "make a landing page", "create a web app", "build a SaaS dashboard / portfolio", "make me a game", "deploy this site", "publish". Also owns GAME ART: "make a spritesheet", "tileable texture", "animate a 3D character", game music/SFX — see the game-* references. NOT for: single image/video/audio generation (higgsfield-generate), product photos (higgsfield-product-photoshoot), marketplace cards (higgsfield-marketplace-cards).

Build a complete non-photoreal narrated explainer or story video from ordered 10-second blocks: one narrator, one universal style key, one Seed Audio take and one Gemini Omni clip per block, then server-side assembly with explainer_video. Use when: "make an explainer video", "explain this in a video", "turn this topic or document into a narrated video", "tell this story as an animated video", "make a faceless narrated video", or "show me explainer styles". Supports live CMS presets, custom style references, mascot/faceless modes, two aspects, and optional burned subtitles. NOT for: photoreal films, ads/UGC, talking heads, podcasts, motion typography reels, one-off clips without narration, or editing a finished video.

Plans and scripts short-form and long-form video, and designs the packaging — titles, thumbnails, and openings — that determines whether it gets watched. Use this to script a video, plan a series, fix retention or click-through problems, design thumbnail and title concepts, or turn written content into video. For a YouTube channel specifically — idea selection, retention teardowns, and channel-level strategy — use `youtube-producer`.

Create high-click-through YouTube thumbnails and vertical video covers through the Higgsfield CLI. Builds a truthful information-gap concept, preserves up to three referenced identities, supports logos and controlled variants, renders the main image with Nano Banana Pro, and applies focused Seedream edits. Use when: "make a YouTube thumbnail", "thumbnail for this video", "MrBeast-style cover", "Shorts cover", or "Instagram video cover". Chain after any video workflow once its truthful topic and visual direction are known. NOT for producing the video itself (use higgsfield-generate), product catalog photos (use higgsfield-product-photoshoot), or marketplace cards (use higgsfield-marketplace-cards).

Generate, extend, or audit design tokens in DTCG format with the 3-tier architecture (primitive → semantic → component). Use when the user wants a color palette, type scale, spacing/shadow/radius/motion tokens, multi-brand theming, or wants to validate token files. Covers colors, typography, spacing, shadows, borders, breakpoints, motion, gradients, opacity, blur, sizing, states, theming.