by threerocks
格物 · 蜡笔状态图:一句话做一部会动的蜡笔状态图短片。3:4、2-3 分钟、四款合成旁白(可加自己的声音)、每章一张海报;支持 Codex、Claude Code、Grok 等,可批量出片。
# Add to your Claude Code skills
git clone https://github.com/threerocks/sweety-statechart-videoGuides for using ai agents skills like sweety-statechart-video.
See how sweety-statechart-video compares with popular alternatives.
sweety-statechart-video is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by threerocks. 格物 · 蜡笔状态图:一句话做一部会动的蜡笔状态图短片。3:4、2-3 分钟、四款合成旁白(可加自己的声音)、每章一张海报;支持 Codex、Claude Code、Grok 等,可批量出片。. It has 51 GitHub stars.
sweety-statechart-video's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.
Clone the repository with "git clone https://github.com/threerocks/sweety-statechart-video" and add it to your Claude Code skills directory (see the Installation section above).
sweety-statechart-video is primarily written in Python. It is open-source under threerocks on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh sweety-statechart-video against similar tools.
No comments yet. Be the first to share your thoughts!
Available after the catalog security scan passes.
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.
See comparison
一格一格,把事情讲明白。
跟你的 AI 助手说一句话,就能把一个流程、一门生意或一个系统,做成会动的蜡笔状态图短片:
"cover_intro": false 可关);灵感来自 Ann Nguyen 老师(@ann_nnng),我们做了风格提取,再加上:
scv.py add-voice。"aspect": "9:16" 之类。"duration": "1分钟" 之类。吸收 Kevin Ngo 的 statechart-art(MIT):
九种主题:蓝蜡笔(默认)、钢笔彩铅、夜读、牛皮纸、孔版、亚麻刺绣、四季,也可以由品牌色生成。
代码进,片子出:XState、Mermaid、SCXML、PlantUML,或 /statechart 技能的输出,都能 import 成片子的骨架;片子里的图也能 export 回去。
动起来更像手做:
插画更满:9 个场景件,人物有多种体型和表情,道具超过 130 件;draft 自动起草插画,lint 逐条报出问题和改法。
声音:
交付:

做法照着 Ann Nguyen 的 the making of nhang(一页往下长的蜡笔状态图),画法和播放器是我们自己写的:
[……],四周是彩色蜡笔插画。Skill 在 skills/sweety-statechart-video/,先读它的 SKILL.md。一部片子只需要两份文件:
film.json:章节、状态、箭头,以及每一步的字幕(字幕同时是旁白);scenes.js:每章的插画,用 130 多个会动的道具、9 个场景件和可以摆姿势的人物拼。版面全自动排。
cd skills/sweety-statechart-video
python3 scripts/scv.py new JOB --title 片名 # 起骨架
python3 scripts/scv.py import 状态机文件 JOB # 或者从 XState / Mermaid / SCXML / PlantUML / /statechart 输出起骨架
python3 scripts/scv.py check JOB # 结构、步骤、字幕,规则章找红线、验证修复
python3 scripts/scv.py layout JOB # 成品海报 + 网格 + 空地
python3 scripts/scv.py draft JOB # 按空地起草插画
python3 scripts/scv.py lint JOB # 插画的问题和改法
python3 scripts/scv.py preview JOB # 浏览器里带声音预览,改了自动刷新
python3 scripts/scv.py all JOB # 配音、排时间、渲染、海报、成片、交付、发布包
python3 scripts/scv.py batch JOB1 JOB2 JOB3 # 批量
python3 scripts/scv.py gallery # 道具和场景件图鉴
python3 scripts/scv.py voices # 列出声音
例子:
examples/intro/:《一句话,做一部会动的状态图》,5 章,2 分 10 秒,四个声音轮流出场;examples/takeout/:《一份外卖的一生》,4 章,1.5 分钟,蜡笔姐姐;examples/message/:《一条消息的旅程》,3 章,1 分钟,图纸哥;examples/boba/:《一杯奶茶》,4 章,1 分钟,钢笔彩铅主题、方形,四章分别用票据串红线、店面便签、按线着色的两条线、规则图例,对照 statechart-art 的四张海报。速度:在 M 系列 Mac 上,93 秒的片子渲染约 40 秒,36 句旁白约 3 分钟。
bash skills/sweety-statechart-video/scripts/setup.sh。它建渲染环境,没有 Chrome 时装 Playwright 的 Chromium,最后跑一遍冒烟测试。SCV_PYTHON 指定,默认用 setup.sh 建的 ~/.local/share/sweety-statechart-video/venv。python3 scripts/smoke_test.py 约 16 秒,不需要配音环境。STATECHART_MLX_PYTHON 指定;~/.local/share/voxcpm2-mlx/models/VoxCPM2-8bit,可用 STATECHART_VOXCPM_MODEL 指定;scripts/audio_doctor.py 检查以上各项。film.json 里写 "voice": "none",做无声版。节奏和参考视频一样,每步 1.2 秒。pencil 主题用了他的 Kevin Serif / Sans 字体(MIT)。吸收情况见 复盘;许可、字体和声音的来源见 THIRD_PARTY_NOTICES.md。合成旁白属于 AI 生成内容,发布时请标注。
MIT License.