HyperFrames Motion Doctrine
heygen-com/hyperframes
Sets the motion rules for HyperFrames videos so scenes read as one continuous camera move, covering exit-to-entry vectors, seams, idle motion and sustained motion.
艺术与视频动画:拆解复刻动画;代码画35种艺术风格并让画活;9种解说动画语法,8种可按口播参数渲片段;含口播整片参考代码及框景检查;人用AI生帧;可选已有录音、系统声音与语音复刻,按需配置。
$ npx skills add alchaincyf/huashu-art-motion --skill huashu-art-motion -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install alchaincyf/huashu-art-motion huashu-art-motion --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "huashu-art-motion" agent skill from https://github.com/alchaincyf/huashu-art-motion/tree/main into .claude/skills/huashu-art-motion/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huashu-art-motion", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add alchaincyf/huashu-art-motion --skill huashu-art-motion -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install alchaincyf/huashu-art-motion huashu-art-motion --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "huashu-art-motion" agent skill from https://github.com/alchaincyf/huashu-art-motion/tree/main into .agents/skills/huashu-art-motion/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huashu-art-motion", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add alchaincyf/huashu-art-motion --skill huashu-art-motion -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install alchaincyf/huashu-art-motion huashu-art-motion --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "huashu-art-motion" agent skill from https://github.com/alchaincyf/huashu-art-motion/tree/main into .cursor/skills/huashu-art-motion/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huashu-art-motion", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add alchaincyf/huashu-art-motion --skill huashu-art-motion -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install alchaincyf/huashu-art-motion huashu-art-motion --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "huashu-art-motion" agent skill from https://github.com/alchaincyf/huashu-art-motion/tree/main into .gemini/skills/huashu-art-motion/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huashu-art-motion", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install alchaincyf/huashu-art-motion huashu-art-motionInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add alchaincyf/huashu-art-motion --skill huashu-art-motion -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "huashu-art-motion" agent skill from https://github.com/alchaincyf/huashu-art-motion/tree/main into .github/skills/huashu-art-motion/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huashu-art-motion", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add alchaincyf/huashu-art-motion --skill huashu-art-motion -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install alchaincyf/huashu-art-motion huashu-art-motion --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "huashu-art-motion" agent skill from https://github.com/alchaincyf/huashu-art-motion/tree/main into .opencode/skills/huashu-art-motion/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huashu-art-motion", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
huashu-art-motion艺术与视频动画:拆解复刻动画;代码画35种艺术风格并让画活;9种解说动画语法,8种可按口播参数渲片段;含口播整片参考代码及框景检查;人用AI生帧;可选已有录音、系统声音与语音复刻,按需配置。
Huashu Art Motion is an agent skill from alchaincyf/huashu-art-motion. 艺术与视频动画:拆解复刻动画;代码画35种艺术风格并让画活;9种解说动画语法,8种可按口播参数渲片段;含口播整片参考代码及框景检查;人用AI生帧;可选已有录音、系统声音与语音复刻,按需配置。
Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 493 other files, including scripts, reference files and assets (for example `.github/workflows/tests.yml`, `CHANGELOG.md` and `CONTRIBUTING.md`).
The repository describes itself as: 艺术动画skill:35种艺术风格、9种解说语法,用代码让画动起来。 The licence is MIT.
6 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 9ff5933. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 1 file in scripts/, which the agent can run.
Shell commands in SKILL.md call:
uvpython3ffmpegFrom the folder's file list and the shell code blocks in SKILL.md.
Links to these hosts (documentation or services it may open):
docs.astral.shFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Huashu Art Motion loads about 2k tokens when it runs, and up to ~117k if it reads all its reference files. Until then it costs about 28 tokens; SKILL.md has 442 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from alchaincyf/huashu-art-motion at commit 9ff5933, republished under its MIT licence (© alchaincyf). 442 words, ~1,962 tokens.
.claude/skills/huashu-art-motion/SKILL.md (or your agent's skills folder). This skill also uses 489 other files; get the full folder from GitHub.scripts/deliver.py,红灯不交付。开工前也建议先写一张镜头表(references/镜头表模板.md),lint 可跑可不跑。references/镜头表模板.md 写 <项目>/镜头表.md。表前先锁画风,三行:画风(一句话,全片只用这一种)、色板(references/色板.md 里的一套或 3–6 个色值,不落蓝紫)、角色(无/只出手和背影/帧库 <路径>,先读 references/角色精细度.md)。表里每行一镜:时间段|画面里的物(名词)|它在做什么(动词)|镜头(停/快推/横移/砸入/切)|屏上字(≤8 字,可空)|做法。开头 3 秒是一个具体的小场景(一双手或一个物在做一件和题目有关的事),不是标题;全片用一个具体例子贯穿;一镜 2–6 秒;文字主导的镜头 ≤30%;相邻两镜换构图,不换画风。uv run <skill>/scripts/storyboard_lint.py <项目>/镜头表.md(有口播稿加 --script <项目>/文稿.txt,查屏上数字和口播是不是同一个数)。有红灯就改镜头表、重跑,红灯没清不许开始写代码。cp -R <skill>/scripts/engine <项目>/代码工程,每一镜出一个 镜NN.mp4,所有镜同宽高、同 fps(默认 1920×1080@30)。references/09-视频动画语法.md 第二节选型表和用到的 references/动画语法/<语法>.md「起手必查」,从 examples/<语法>.json 抄结构不抄内容,屏上字照镜头表那一格,uv run --with playwright python <项目>/代码工程/render.py --spec 镜NN.json --out 镜NN.mp4。单个参数化片段最多撑 8 秒,超了拆成几镜。references/风格配方/INDEX.md 和一张风格卡,写 scenes/<id>.js 并登记进 eras.js,render.py --solo <id> --from 0 --to <秒> --fps 30 --no-counter --out 镜NN.mp4。"theme"(镜头表色板那一行,写法见 references/色板.md),最多 2 种片段语法;scenes 也只用这套色板。每镜加 --stills 0.5,2 --out 静帧/镜NN 抽帧,排成一排对着镜头表看:哪一镜像从别的片子里拿来的,就按画风重做。镜NN.mp4 的目录里:for f in 镜*.mp4; do printf "file '%s'\n" "$f"; done > 镜头列表.txt
ffmpeg -y -f concat -safe 0 -i 镜头列表.txt -r 30 -c:v libx264 -crf 16 -pix_fmt yuv420p -an 成片.mp4ffmpeg -i 成片.mp4 -i 口播.wav -map 0:v -map 1:a -c:v copy -c:a aac -shortest 成片_口播.mp4。要转场就全用 scenes,把各镜按顺序写进 eras.js 段落表(段写 dur 秒、transition),整片模式 render.py --out 成片.mp4 一次出片。uv run <skill>/scripts/qa.py --spec 镜NN.json --out <项目>/qa/镜NN;有 scenes 再跑 qa.py --project <项目>/代码工程 --ids <id,…> --out <项目>/qa/scenes。再拿抽帧逐条对下面「六种做坏方式」。uv run <skill>/scripts/deliver.py 成片.mp4 --root <项目> --qa <项目>/qa/<跳变最多的那一镜> --out output/。红灯不交付:脚本不复制成片,照它打印的修法改完重渲、重跑。绿灯、黄灯它复制成片并写 output/交付说明.md,时长、门禁、qa、有没有审片由脚本写;你只在「制作说明」段补用了哪些语法和做法、其余各镜的 qa 结论(每镜一行)、黄灯项逐条理由、六种做坏方式自查,事实段不许改。派了独立审片的,先让审片人把结论写进 <项目>/审片/*.md 再跑。你同时是这支片子的导演、分镜师、原画师、动画师和剪辑师,画画用的是代码。你对成片的标准:观众看得懂每一镜在讲什么,愿意看下去;用艺术风格时一眼认得出是谁的画,画是活的,不是图片在切换。
theme)。storyboard_lint 查物列是不是空镜、纯色、黑场;film_gate(deliver.py 先跑它)查成片中段连续 0.3 秒以上的空画面,红灯不出片。references/色板.md),所有片段写同一个 theme;角色要么 AI 生帧过交付线,要么只出手和背影(references/角色精细度.md)。storyboard_lint 查画风锁、色板色值和角色行;deliver.py 量蓝紫底,蓝紫帧占全片 30% 以上红灯,不出片。干净统一但略像幻灯片的片子,胜过花哨的拼贴。| 用户说的 | 做什么 | 读 |
|---|---|---|
| 「复刻这个动画」「拆一下这段」 | 拆解 → 机制 → 代码复刻 | 01 → 02 → 04 |
| 「做个 XX 风格的动画」「梵高/莫奈/包豪斯那种」 | 先为题材定构图 → 一帧先行 → 渲染器 → 让它活 | 03 → 04 → 风格配方/INDEX.md 找最近的材料当起点 |
| 「用我的口播做一段艺术动画」 | 镜头表 → 定风格 → 世界画布+镜头 → 画面轨 | 06(草案)+ 04;口播的转录与时间轴交给你的视频管线 |
| 「配个乐」「卡节奏」 | BPM 网格、动机换乐器、结尾音效序列 | 05 |
| 画面里要出现人(用户本人、真人、拟人角色、吉祥物) | AI 生帧+代码合成(B/C 两法),过交付线;没有生图能力就只出手和背影 | 10 + 角色精细度.md |
| 派 agent 画某个风格 / 自己写新风格 | 接口、两种起点、硬要求、自检交付 | 08 + 风格配方/INDEX.md |
| 「一个人穿过一幅幅名画」「一路走过几个世界」 | 长卷骨架:每个世界一个段文件,主角从左走到右,跨边界换画风 | 11 + scripts/engine/demos/long_scroll/ |
| 「做解说/科技/财经视频的动画」「Kurzgesagt/Vox/3b1b/白板/发布会/财经图表那种」、口播管线要一段动画 | 按口播选语法 → 过语法卡「起手必查」→ 管线用 render.py --spec 出时长精确的片段 | 09 + 动画语法/<语法>.md |
口播整片先读references/12-口播整片与经验回流.md;讲解员风格再读references/动画语法/y6_presenter_explainer.md。艺术史速通、穿越这类「同一场景换风格」的片子,机制见 02 号(五层机制),只用于这类片子。
任务需要新配音时,先读语音能力指南,运行scripts/capabilities.py status --explain。已有录音直接沿用;无声动画不启动配置。未选择时只询问当前需要的声音方式,可本次跳过或长期手动启用;用户已明确选择时直接应用。私人音色、参数和凭证引用保存在安装目录外,公共默认不绑定作者声音。
scripts/koubo.py say/train/voices保留旧调用,使用同一套配置。仅音频任务不启动画面设计或成片审片。
需要图片时读图片能力指南。已有图片直接导入;生成图片按当前会话实际工具和用户许可选择,脚本输出调用计划,Agent执行工具后验收并复制到项目。无图片任务跳过配置;禁止生成时不换供应商绕过。语音和图片分别配置,新增能力不会自动获准。
CAM.track(镜头动作表)、MO.slam(砸入)。艺术风格画面仍要「画一直是活的」:每幕一个主动作+2 个母题循环,自检量帧差(避开转场后 0.35s 的镜头冲击)。MD.cover 满幅+焦点推近、MD.print 冲印件、MD.label 黑底撕边标签;缺图直接报错)。「场景与风格用代码画」只适用于艺术风格画面。人用 AI 生帧、代码合成,见references/10-角色.md;代码不画人脸、不画机器人,也不给物加脸(references/角色精细度.md)。theme,scenes 也只用这几个色。不用蓝紫渐变、深紫星空、霓虹青紫(作者原话:「这种非常ai slop」);用户点名要蓝紫才例外,交付时 --allow-blue-purple "理由"。<项目>/审片/*.md(deliver.py 只认这里)。风格配方/ 里 35 张卡(总表 风格配方/INDEX.md,分「材料层」和「时代标本」两张表)是实做的参数和坑,不是唯一画法。35 张样片和 assets/全风格总览.jpg 用的是同一个房间构图,那是艺术史速通片的机制,不是这些风格的构图;做新题材要为题材重新构图。表里标了每种的当前质量和短板,下一次做到它时先超越短板。你有更好的渲染器就去写,做出来和原作或参考并排给人看。新风格做完,把配方卡补进来。
scripts/engine/ 是可复制的完整工程(引擎、转场库、绘画库、角色骨架、35 个风格场景、渲染器;YouTube 解说语法的 8 个库、8 支示范 demos/、参数化片段 clip.html+clips/,见 09;长卷穿越片示范 demos/long_scroll/,见 11;口播整片参考代码reference_films/spacex/需自备角色和音频,见目录README)。开新片:复制到项目的 代码工程/,改 eras.js 段落表,写 scenes/<id>.js。
E=<项目>/代码工程
uv run --with playwright python $E/render.py --solo <id> --stills 0,0.3,0.6 --out 渲染/<id> # 单段静帧
uv run --with playwright python $E/render.py --out 成片.mp4 --audio 配乐.wav # 整片
uv run --with playwright python $E/render.py --spec 片段.json --out 片段.mp4 # 参数化片段
python3 $E/compare.py --a 参考.mp4 --b 成片.mp4 --times 1.5,2.0 --out 对比.jpg # 并排
uv run scripts/analyze/breakdown.py --video 参考.mp4 --out 拆解/ # 拆解地图字体在 scripts/engine/lib/fonts/(woff,各字体许可见同目录 LICENSES.md)。依赖:uv、ffmpeg(出片与拆解)、Playwright Chromium(首次要 uv run --with playwright playwright install chromium)。
交付前三样,按顺序:①uv run scripts/qa.py --project <工程>(参数化片段用 --spec;稳定/效率/动感/流畅及文字框景线索;短于 0.35 秒的单调快推、横移记作镜头事件,不算跳变);②派独立 agent 只看成片审片,结论写进 <项目>/审片/;③uv run scripts/deliver.py 成片.mp4 --project <工程>(或 --spec)--out output/。deliver.py 先过门禁 film_gate.py:快速运动帧占比 < 0.035 红灯,不复制成片、非零退出;< 0.06 黄灯。过了才复制成片、写交付说明,时长、门禁各项、最差 30 秒窗口、qa 结果、有没有审片记录都由脚本写,没审片就写「没派审片」;事实段带指纹,deliver.py --verify 查得出改动。门禁另外两条:成片中段连续 0.3 秒以上近乎纯色、整帧几乎没有边缘的空画面,红灯并给时间码;蓝紫底画面占全片 30% 以上红灯(题材本身要蓝紫时 --allow-blue-purple "理由" 降黄,理由写进交付说明)。门禁只拦这三样,页框、米底小图、前紧后松、每镜换画风的拼贴拦不住,所以抽帧还要对一遍「六种做坏方式」;静止多不是病,脉冲节奏的片子本来就有大段停住,静止类数字别拿来判。浅底无字幕成片再用uv run --with numpy python scripts/subzone_gate.py 成片.mp4检查图形进入字幕区;纹理底不适用。经验先看 07-正面经验.md。
每做完一支:新风格写进 风格配方/ 并更新 INDEX,做对了的事写进 07-正面经验.md(做法+证据+为什么+何时用),新坑写进对应 reference 的「踩过的坑」,CHANGELOG.md 记一行。实际与这里不符时以实际为准,然后把这里改对。
这份 skill 起于一次真实复刻(2026-10-04,X 用户 Tak @cherry_mx_reds 的 15 秒「Art History Speedrun」,16 个艺术时代),后来扩展到解说动画语法和口播整片。
© alchaincyf, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 489 other files (scripts, references, assets) in the repository root of alchaincyf/huashu-art-motion.
Open the folder on GitHubat commit 9ff5933
Huashu Art Motion next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Huashu Art Motion this skillalchaincyf/huashu-art-motion | 3.3k | — | ~2k | Automated safety check: Pass | MIT | |
| HyperFrames Motion Doctrineheygen-com/hyperframes | 60k | 1 repos | ~3k | Automated safety check: Pass | Apache-2.0 | |
| Emilkowalski Motionnexu-io/open-design | 100k | — | ~644 | Automated safety check: Pass | Apache-2.0 | |
| Algorithmic Artnexu-io/open-design | 100k | — | ~351 | Automated safety check: Pass | Apache-2.0 | |
| Motion Foundationsaffaan-m/ECC | 277k | 1 repos | ~2.4k | Automated safety check: Pass | MIT | |
| Algorithmic Art with p5.jsanthropics/skills | 180k | 38 repos | ~4.9k | Automated safety check: Pass | Apache-2.0 |
heygen-com/hyperframes
Sets the motion rules for HyperFrames videos so scenes read as one continuous camera move, covering exit-to-entry vectors, seams, idle motion and sustained motion.
nexu-io/open-design
Motion-design follow-up skill inspired by Emil Kowalski's animation guidance.
nexu-io/open-design
Create generative art using p5.js with seeded randomness so every render is reproducible.
affaan-m/ECC
Motion tokens, spring presets, performance rules, device adaptation, accessibility enforcement, and SSR safety for React / Next.js using motion/react.
anthropics/skills
Creates original generative art in two steps: a written algorithmic philosophy, then a p5.js sketch with seeded randomness and an interactive viewer for exploring parameters.
heygen-com/hyperframes
Builds short, unnarrated motion graphics such as kinetic type, stat count-ups, logo stings, lower thirds, animated maps and tweets, rendered to MP4 or a transparent overlay.
艺术与视频动画:拆解复刻动画;代码画35种艺术风格并让画活;9种解说动画语法,8种可按口播参数渲片段;含口播整片参考代码及框景检查;人用AI生帧;可选已有录音、系统声音与语音复刻,按需配置。. Huashu Art Motion is an agent skill from alchaincyf/huashu-art-motion.
Run `npx skills add alchaincyf/huashu-art-motion --skill huashu-art-motion -a claude-code`. Or copy the skill folder (the alchaincyf/huashu-art-motion repository) into .claude/skills/huashu-art-motion in your project. Claude Code loads it when a task matches its description.
Run `npx skills add alchaincyf/huashu-art-motion --skill huashu-art-motion -a codex`. Or copy the skill folder (the alchaincyf/huashu-art-motion repository) into .agents/skills/huashu-art-motion in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add alchaincyf/huashu-art-motion --skill huashu-art-motion -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/huashu-art-motion, .gemini/skills/huashu-art-motion, .github/skills/huashu-art-motion and .opencode/skills/huashu-art-motion in your project.
Going by SKILL.md and its folder, Huashu Art Motion needs the command-line tools its instructions call (uv, python3 and ffmpeg). Our summary lists: Python 3.
SKILL.md names 1 domain. As links in the text: docs.astral.sh. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Huashu Art Motion is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
About 2k tokens (SKILL.md is roughly 7.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 115k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Huashu Art Motion: HyperFrames Motion Doctrine (heygen-com/hyperframes, 60k stars), Emilkowalski Motion (nexu-io/open-design, 100k stars), Algorithmic Art (nexu-io/open-design, 100k stars) and Motion Foundations (affaan-m/ECC, 277k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
alchaincyf (a GitHub user) maintains it in alchaincyf/huashu-art-motion, which has 3,277 GitHub stars. The repository was last updated on October 10, 2026.
Source: alchaincyf/huashu-art-motion on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.