Video & Animation

Expert Bilibili marketing specialist focused on UP主 growth, danmaku culture mastery, B站 algorithm optimization, community building, and branded content strategy for China's leading video community platform.

Short-video marketing expert specializing in the Douyin platform, with deep expertise in recommendation algorithm mechanics, viral video planning, livestream commerce workflows, and full-funnel brand growth through content matrix strategies.

Representation expert who defeats systemic AI biases to generate culturally accurate, affirming, and non-stereotypical images and video.

Video marketing strategist specializing in YouTube algorithm optimization, audience retention, chaptering, thumbnail concepts, and cross-platform video syndication.

Use when a store needs to collect more reviews — designing or fixing how and when it asks customers, choosing the trigger and the delay, deciding which products to prioritise, adding or removing a follow-up, or working out why submissions are low despite requests going out. Covers photo and video asks as well as text.

Use when reviews and UGC exist but are not working — deciding where proof should appear on the site, which proof belongs on which page, whether to add badges, carousels or galleries, and whether existing photo and video can be reused in email, ads or social. Also use when a placement was added and nothing changed.

Sci-fi-styled image segmentation, re-skinning, and annotation for thermal-imaging-style video. Use for local Yautja video effects, false-color footage, or warm silhouettes with alien glyphs and an audio-reactive HUD. For entertainment only; colors are algorithmically generated with some randomness, not measured temperatures.

Use when a user wants to parse or collect Bilibili video data through HotBee from a bilibili.com or b23.tv URL.

Use when a user wants audio or video converted to text through HotBee speechToText, including file URL transcription, video URL transcription, or transcript extraction from parsed social videos.

EasyIndie 内容自动化统一技能（多领域扩展）：YouTube 搬运/内容创作（当前），后续按领域扩展 audio/video/ai-music 等。

快手数据助手、快手热榜、快手内容研究、作品研究、作品详情、评论分析、评论回复分析、达人数据和达人作品。覆盖 Kuaishou / Kwai short-video research，来自 GuaiKei 社媒数据助手。

Use this skill when a feature works on one machine and not another, when choosing or pinning a renderer, or when writing code that must degrade gracefully. Covers the WebGPU to WebGL 2 to Canvas fallback ladder, what each backend supports, capability detection, and the subsystems that warn once and then stop working on Canvas. Triggers on: video.AUTO, video.WEBGPU, video.WEBGL, video.CANVAS, renderer.type, supportsDepthBuffer, shaderLanguage, WebGPU, WebGL2, Canvas fallback, context loss, backen

Use when a user wants to parse or collect verified Douyin video, comment, creator, fan portrait, or hashtag data through HotBee APIs using Chinese natural-language instructions and Douyin links.

Review, script and edit video with the bundled Creative Studio toolkit — footage inventory (duration/resolution/fps/audio), frame extraction and contact sheets, copywriting and storyboard structure, timeline cutting, transition joins, on-screen text, burned-in subtitles, music mixing with fades, smart cover-frame selection, and platform-spec exports (9:16 / 16:9 / 1:1 / 4:5). Use proactively for any task involving 视频/短视频/素材整理/剪辑/分镜/脚本/字幕/配乐/封面/转码, product videos, TikTok/Reels/Shorts/YouTube deli

下载抖音（Douyin）视频与图集。当用户给出抖音分享链接（v.douyin.com/xxx、www.douyin.com/video/<id>、www.douyin.com/note/<id>）并要求保存、下载、备份视频，或抱怨抖音下载器解析失败、画质只有标清、需要登录才能看高清时使用。通过真实 Chrome + DevTools Protocol 读取播放器真实直链，绕过抖音对无 Cookie 请求的 JS-VMP 反爬与验证码中间页。

Agent skill 'find-animation-opportunities' from emilkowalski/skills. Use when the task matches this skill's domain.

Agent skill 'review-animations' from emilkowalski/skills. Use when the task matches this skill's domain.

Agent skill 'improve-animations' from emilkowalski/skills. Use when the task matches this skill's domain.

Agent skill 'animation-vocabulary' from emilkowalski/skills. Use when the task matches this skill's domain.

Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools.

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.

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 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.

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.