AI Animation Skills is a collection of agent instructions and templates for generating single-file HTML animations, including presentations, diagrams, protocol visualizations, phone interfaces, and video-style scenes. People use the skills with AI coding agents to create animated web pages from descriptions or templates. The catalogue entries are the collection's individual generation workflows.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Unclecheng-li/AI_Animation --skill video-shot-demosgit clone --depth 1 https://github.com/Unclecheng-li/AI_AnimationWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/unclecheng-li/ai_animation/video-shot-demos)<a href="https://agentmods.dev/skills/unclecheng-li/ai_animation/video-shot-demos"><img src="https://agentmods.dev/badge/skills/unclecheng-li/ai_animation/video-shot-demos/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/unclecheng-li/ai_animation/video-shot-demos"><img src="https://agentmods.dev/badge/skills/unclecheng-li/ai_animation/video-shot-demos.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00166 | $0.01598 |
| Opus 5 | $0.00083 | $0.00799 |
| Sonnet 5 | $0.00033 | $0.00320 |
| Haiku 4.5 | $0.00017 | $0.00160 |
Grade A, and why
video-shot-demos scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
视频分镜演示动画(每镜头一个 HTML)
一个镜头 = 一个独立 HTML,统一播放器底盘 + 每页一种完全不同的视觉风格,全屏录屏即成片。内容开放(技术实测/产品发布/课程/叙事皆可),不变的是电影化机制、镜头语言与完成度标准。
创作哲学
- 风格轮换:连续镜头绝不同风格。问"这段内容若是一件实物/一个场所,它是什么"——复古报纸、POS 小票、审讯室、像素游戏……把抽象内容具象成一个世界观,页面就活了。
- 禁默认科技暗色:黑底+霓虹+玻璃拟态的"乌漆墨黑油光锃亮"两页即疲劳,除非内容本身是终端主题。
- 想象力优先:底盘之上放开写——会砸下的印章、会掉进存钱罐的硬币,用户要惊喜感。
- 完成度是纪律:元素有入有出(或定格)、无重叠遮挡、无孤儿元素、结尾有重播暗示、数据有出处角注。
- 音画同步:关键动作有音效、镜头移动配 whoosh;安静也是设计。
Token 纪律(硬性)
- 禁止通读
assets/template.html与assets/examples/下任何成片页(单个 20–50KB,读完耗尽预算)。 - 模板一律
cp复制后只读标记区域(第 1 步);成片页仅当写完仍卡壳时,grep 定位后按行号窗口读 ≤80 行。 - 机制与风格知识优先取自
references/三份浓缩文档,不要现场读源码反推。
工作流
第 0 步 · 输入与风格分配表:通读素材(大纲/口播稿/画面设计/口述),拿到分镜列表 + 口播时间戳(时间轴对齐基准)+ 角色素材。排表 镜头|时长|视觉风格|字体组合|主色:相邻不同风格、整辑不重复、同一实体全系列锁同一颜色(观众靠颜色跨页追踪)。表给用户确认后再动工。素材复制(勿读内容):
cp -r "assets/examples/<项目>/anan - emotion rename" <输出目录>/ # 安安 15 情绪立绘;图标同理
cp -r "assets/shery - emotion rename" <输出目录>/ # 橘雪莉 20 情绪(笨蛋吐槽役,重点页与安安同框)
第 1 步 · 逐页实现(cp 起步,只读标记区):
cp assets/template.html "<输出目录>/shot-x-x_名称.html"
grep -n "改这里\|DUR=" "<输出目录>/shot-x-x_名称.html" # 行号地图(7 处改这里 + DUR)
用 Read 的 offset/limit 只读标记行附近区域(字体 link+舞台底色 / 画面层 CSS / 画面 HTML / cue 表+DUR),逐一替换:① 字体与配色(Google Fonts 随风格);② 重画画面层;③ 按口播时间戳写 cue(注释引用口播句,如 // 5:20「正常充值」);④ DUR=规定时长±0.5s。底盘(引导脚本/音效引擎/时间轴/镜头调度/HUD)不动。
按需读参考(都很小):references/mechanics.md 播放器+镜头+音效机制 | references/style-cards.md 40 种风格卡片(字体/主色/材质/样板页号) | references/character-reactions.md 双角色吐槽体系(安安×橘雪莉情绪表、中段快闪切立绘、双人同框 cue、气泡强约束模板)。
第 2 步 · 质检:node scripts/shot.js 页面.html <毫秒> _t.png [fx fy scale] 多时间点无头截图,逐张查重叠遮挡/中间态穿帮/收尾定格,最后完整播一遍。
第 3 步 · index 总览:按章节分组的导航卡(编号/时长/标题/风格标签),自成一种风格。
翻新已有页面时:先盘点并列清单(用户点名保留的页面一字不动)→ 底盘统一注入 → 逐页重设计画面层 → 补角色/镜头/音效 cue → 质检。
交付标准
- 黑场「启动播放」起手,2s 渐变后开演;1920×1080 自适应;HUD 底部唤出;可暂停重播;DUR 准确
- 相邻镜头风格/字体/配色不同;无默认科技暗色;emoji→内联扁平 SVG
- 关键节拍有镜头运动(推/拉/跟/摇)+ whoosh;关键动作有音效;计数滚动有连击键音
- 角色出场每页 ≥2 次(中段 30–45% DUR 快闪 + 结尾 75–85% 定场,短页仅结尾):快闪=同一元素换台词换立绘、160ms 闪换重弹;重点页双角色(雪莉先吐槽→安安 1.2s 后接茬,同框退场);气泡必须用统一强约束模板(形态锁定,仅 4 配色可调,见 character-reactions.md)
- 无底部字幕条(口播只以 cue 注释对齐,不上屏);截图验证无重叠遮挡;数据角注出处;index 可逐页打开
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/examples/doubao-paper-detective/anan - emotion rename/01_淡漠凝睇_无口忧郁.png 1456 KB
- assets/examples/doubao-paper-detective/anan - emotion rename/02_抱书怀羊_恬静温柔.png 1503 KB
- assets/examples/doubao-paper-detective/anan - emotion rename/03_掩袖半垂_慵懒羞怯.png 1491 KB
- assets/examples/doubao-paper-detective/anan - emotion rename/04_闭目莞尔_温柔娇羞.png 1489 KB
- assets/examples/doubao-paper-detective/anan - emotion rename/05_阖眸轻语_雀跃腼腆.png 1498 KB
- assets/examples/doubao-paper-detective/anan - emotion rename/06_蹙眉闭唇_窘迫羞恼.png 1499 KB
- assets/examples/doubao-paper-detective/anan - emotion rename/07_睁眸微张_愕然疑惑.png 1501 KB
- assets/examples/doubao-paper-detective/anan - emotion rename/08_倦眼半阖_慵懒无力.png 1498 KB
- assets/examples/doubao-paper-detective/anan - emotion rename/09_垂眸出神_淡然凝思.png 1566 KB
- assets/examples/doubao-paper-detective/anan - emotion rename/10_闭目含笑_恬静满足.png 1569 KB
- assets/examples/doubao-paper-detective/anan - emotion rename/11_懵然半睁_茫然迟疑.png 1566 KB
- assets/examples/doubao-paper-detective/anan - emotion rename/12_粉颊捧笺_娇羞雀跃.png 1578 KB
- assets/examples/doubao-paper-detective/anan - emotion rename/13_掩袖低眸_羞怯暗思.png 1590 KB
- assets/examples/doubao-paper-detective/anan - emotion rename/14_红腮含颦_腼腆欣喜.png 1585 KB
- assets/examples/doubao-paper-detective/anan - emotion rename/15_平举素纸_认真以待.png 1557 KB
- assets/examples/doubao-paper-detective/doctor_ava.jpg 25 KB
- assets/examples/doubao-paper-detective/doubaoicon.png 81 KB
- assets/examples/doubao-paper-detective/index.html 14 KB
- assets/examples/doubao-paper-detective/papers/p1_evidence.jpg 233 KB
- assets/examples/doubao-paper-detective/papers/p1_full.jpg 267 KB
- assets/examples/doubao-paper-detective/papers/p1_read.jpg 275 KB
- assets/examples/doubao-paper-detective/papers/thumb_p1.jpg 55 KB
- assets/examples/doubao-paper-detective/papers/thumb_p2.jpg 88 KB
- assets/examples/doubao-paper-detective/papers/thumb_p3.jpg 99 KB
- assets/examples/doubao-paper-detective/shot-0-1_导师的论文砸下来.html 25 KB
- assets/examples/doubao-paper-detective/shot-0-2_下马威38页术语轰炸.html 24 KB
- assets/examples/doubao-paper-detective/shot-0-3_反转预告.html 22 KB
- assets/examples/doubao-paper-detective/shot-0-4_标题卡论文侦探.html 32 KB
- assets/examples/doubao-paper-detective/shot-1-1_读两遍的习惯.html 27 KB
- assets/examples/doubao-paper-detective/shot-1-1b_横向对比.html 31 KB
- assets/examples/doubao-paper-detective/shot-2-4_疑点95条攻击零迁移.html 27 KB
- assets/examples/doubao-paper-detective/shot-4-5_卡片墙越攒越好用.html 40 KB
- assets/examples/doubao-paper-detective/shot-4-6_沉淀成工具.html 34 KB
- assets/examples/doubao-paper-detective/shot-5-1_三篇一条线与双结论.html 32 KB
- assets/examples/doubao-paper-detective/shot-5-2_指定句与三连.html 35 KB
- assets/examples/glm-5.3-range-test/anan - emotion rename/01_淡漠凝睇_无口忧郁.png 1456 KB
- assets/examples/glm-5.3-range-test/anan - emotion rename/02_抱书怀羊_恬静温柔.png 1503 KB
- assets/examples/glm-5.3-range-test/anan - emotion rename/03_掩袖半垂_慵懒羞怯.png 1491 KB
- assets/examples/glm-5.3-range-test/anan - emotion rename/04_闭目莞尔_温柔娇羞.png 1489 KB
- assets/examples/glm-5.3-range-test/anan - emotion rename/05_阖眸轻语_雀跃腼腆.png 1498 KB
- assets/examples/glm-5.3-range-test/anan - emotion rename/06_蹙眉闭唇_窘迫羞恼.png 1499 KB
- assets/examples/glm-5.3-range-test/anan - emotion rename/07_睁眸微张_愕然疑惑.png 1501 KB
- assets/examples/glm-5.3-range-test/anan - emotion rename/08_倦眼半阖_慵懒无力.png 1498 KB
- assets/examples/glm-5.3-range-test/anan - emotion rename/09_垂眸出神_淡然凝思.png 1566 KB
- assets/examples/glm-5.3-range-test/anan - emotion rename/10_闭目含笑_恬静满足.png 1569 KB
- assets/examples/glm-5.3-range-test/anan - emotion rename/11_懵然半睁_茫然迟疑.png 1566 KB
- assets/examples/glm-5.3-range-test/anan - emotion rename/12_粉颊捧笺_娇羞雀跃.png 1578 KB
- assets/examples/glm-5.3-range-test/anan - emotion rename/13_掩袖低眸_羞怯暗思.png 1590 KB
- assets/examples/glm-5.3-range-test/anan - emotion rename/14_红腮含颦_腼腆欣喜.png 1585 KB
- assets/examples/glm-5.3-range-test/anan - emotion rename/15_平举素纸_认真以待.png 1557 KB
- assets/examples/glm-5.3-range-test/icons/GLMicon.png 6.1 KB
- assets/examples/glm-5.3-range-test/icons/GPTicon.png 31 KB
- assets/examples/glm-5.3-range-test/index.html 17 KB
- assets/examples/glm-5.3-range-test/reference/0-1-typewriter.html 11 KB
- assets/examples/glm-5.3-range-test/shot-0-1_两周2436个漏洞.html 22 KB
- assets/examples/glm-5.3-range-test/shot-0-2_CyberGym是什么.html 25 KB
- assets/examples/glm-5.3-range-test/shot-0-3_力压两位闭源标杆.html 22 KB
- assets/examples/glm-5.3-range-test/shot-0-4_实测悬念27vs23.html 23 KB
- assets/examples/glm-5.3-range-test/shot-0-5_标题卡.html 18 KB
- assets/examples/glm-5.3-range-test/shot-1-1_约束更严格的编程能力.html 17 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 57 lines · 166 tokens per session scan A cd086ff24724
video-shot-demos is a skill published in the GitHub repository Unclecheng-li/AI_Animation (1,265 stars, last pushed 12d ago), licensed MIT. It adds 166 tokens to every session and 1,598 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
preline-mcp
Add, integrate, or build Preline UI components and blocks into HTML files via the Preline MCP server. Use when the user mentions "preline", says "/preline", asks to add a UI component, or requests a Preline block (a ready-made page section) using Preline UI.
preline-theme-generator
Generate, preview, save, or validate Preline theme CSS using the bundled local generator in this skill. Use when the user asks to create a new Preline theme, match a brand color, translate a mood into a theme, generate light and dark theme CSS, preview theme output without writing files, or review and fix generated…
animejs-animation-v2
Anime.js Animation Skill workflow skill. Use this skill when the user needs Advanced JavaScript animation library skill for creating complex, high-performance web animations and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
web-image
A way to create PNG images by describing their layout with HTML and CSS and rendering it in a browser.
animejs-animation
Anime.js Animation Skill workflow skill. Use this skill when the user needs Advanced JavaScript animation library skill for creating complex, high-performance web animations and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
dark-mode-master
Professional Dark Mode Master skill. Build accessible, performance-tuned, responsive UI components with clean design standards.