Communitygithub.com

Agentchengfeng/chengfeng-videocut-skills

Create Ian Xiaohei-style HTML/SVG motion illustrations for Chinese articles, scripts, storyboard scenes, workflow explanations, concept metaphors, and short video visual aids. Use when the user asks for 小黑 SVG、漫画感 HTML、分层 SVG 动效、把小黑生图做成 HTML/SVG、可编辑矢量动效、口播流程动画、手绘漫画动效、正文配图动画, or wants a Xiaohei illustration style adapted into controllable HTML/SVG/GSAP output instead of raster image generation.

chengfeng-videocut-skills 是什么?

chengfeng-videocut-skills is a Claude Code agent skill that create Ian Xiaohei-style HTML/SVG motion illustrations for Chinese articles, scripts, storyboard scenes, workflow explanations, concept metaphors, and short video visual aids. Use when the user asks for 小黑 SVG、漫画感 HTML、分层 SVG 动效、把小黑生图做成 HTML/SVG、可编辑矢量动效、口播流程动画、手绘漫画动效、正文配图动画, or wants a Xiaohei illustration style adapted into controllable HTML/SVG/GSAP output instead of raster image generation.

兼容平台✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/Agentchengfeng/chengfeng-videocut-skills/tree/HEAD/plugins/chengfeng-videocut/skills/chengfeng-visual/animation-styles/ian-xiaohei-svg-motion

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

Ian Xiaohei SVG Motion

把 Ian 小黑正文配图的原则,改造成可控的 HTML + SVG + GSAP timeline 动效。目标不是复刻生图像素,而是把文章里的一个认知动作重建成分层漫画舞台,方便录视频、按字幕 cue 对齐、后续改文案和元素。

Core Rule

Do not auto-vectorize a PNG and animate the resulting path soup. Use raster images only as composition references. Rebuild the scene as semantic SVG groups:

idea -> shot plan -> SVG layer plan -> HTML/SVG template -> GSAP timeline -> static + motion review

Workflow

  1. Extract one cognitive anchor from the article, script, screenshot, or storyboard scene.
  2. Choose one physical metaphor: sorting, carrying, bridging, leaking, catching, folding, weighing, opening, rerouting, or falling.
  3. Make Xiaohei perform the core action. If removing Xiaohei does not change the meaning, redesign.
  4. Design a 16:9 white canvas with one main scene, 35%+ whitespace, and 3-5 short handwritten annotations at most.
  5. Build semantic SVG groups for every moving object.
  6. Animate with GSAP timeline. Use x, y, rotation, scale, opacity, and SVG stroke drawing. Avoid layout animations.
  7. Save both a playable HTML page and a static review screenshot.
  8. If this is for a 口播成片 project, map timeline segments to subtitle/cue timing before final render.

Read When Needed

  • Read references/style-rules.md before designing a new scene or judging whether the result still feels like Ian Xiaohei.
  • Read references/svg-layering.md before writing or editing the SVG structure.
  • Read references/motion-rules.md before writing GSAP animation.

Output Contract

Default output folder:

output/<slug>-xiaohei-svg-motion/

Required files:

index.html
README.md
preview.png
vendor/gsap.min.js

Optional files:

source.png        # reference image, if provided by the user
cue-map.md        # when aligning to spoken script or subtitles

Reusable Assets

AI model and interface icons live in:

assets/icons/

Use assets/icons/index.json as the source of truth. Keep original SVG files in subfolders and inline their complete SVG content into scene SVGs during generation, so gradients, strokes, and brand colors are preserved.

Icon rules:

  • If index.json already has the exact model, provider, or semantic icon, use that icon. Do not replace ChatGPT, Claude, Flash lightning, Step, DeepSeek, Qwen, bug, table, chart, database, or web icons with generic boxes, stars, sparks, or abstract marks.
  • When the user provides a new SVG icon, save the raw SVG under assets/icons/<category>/, add an entry to index.json, and then reference it by id in the scene plan.
  • For comparison scenes, icon choice is part of the meaning. Keep model icons visually consistent in size and placement so the viewer can identify the actors before Xiaohei starts moving objects.

Template

Use assets/templates/xiaohei-comic-motion/ as the starter when the request resembles a hand-drawn comic scene with moving objects, arrows, annotations, or a Xiaohei action.

Use assets/templates/xiaohei-series-reference/ when the request asks for multiple variants, a reusable series, or a broader reference set for 口播 explanation scenes.

Copy the template into the project output folder, then edit:

  • SVG group names.
  • Handwritten labels.
  • Object positions.
  • Timeline labels and durations.
  • README notes for the scene-specific metaphor.

Quality Gate

Before final response:

  • Open the HTML in a local server.
  • Check console for errors.
  • Capture a static screenshot with ?static=1.
  • Capture at least one playback mid-frame when the scene has multiple beats. If available, use ?frame=mid for a deterministic review frame.
  • Visually inspect that text, arrows, Xiaohei, props, belts, pits, cards, and final impact points do not overlap.
  • Confirm the animation has visible progression: context first, action second, problem/result third, summary last.
  • Confirm annotations appear only after the object/action they explain.
  • Remove decorative or semi-transparent guide arrows if the object motion already shows direction.
  • Confirm Xiaohei is part of the action.
  • Confirm the page is not just a PNG in an <img> tag unless the user explicitly asked for PNG-only camera moves.

Individual skills in this repo

This repo contains 7 individual skills — each has its own dedicated page.

Agentchengfeng/chengfeng-videocut-skills

剪辑环境的唯一管理者:就绪检查(skills 是否最新 → Runtime 是否配套)、Skills 更新激活、Runtime 安装与体检。用户说检查更新、安装剪辑环境、装播放器、检查剪辑环境、剪辑环境就绪了吗、配置转录凭证时使用;业务 Skill(剪口播/字幕/画面/导出)第 0 步也引用本 Skill 的就绪检查。不用于剪辑、字幕、画面、导出本身或项目数据迁移。

Agentchengfeng/chengfeng-videocut-skills

剪辑中文口播原素材:逐词转录、词典修字出修字表、五轮扫描找口误与重复、汇总表与重复句子表、打开 Studio 让用户复核、复盘沉淀用户偏好与词典。只产出一份已复核的删词账本,不切媒体、不做字幕、不做分镜动画。用户说剪口播、处理口误、生成口播基础素材、继续剪口播,或确认卡回传 action=return_cut_review 时使用。不要用于执行物理剪切、导出剪后视频、单独安装、单独打开工作台或口播分镜成片。

Agentchengfeng/chengfeng-videocut-skills

把剪好的口播烧成一个成片文件:账本切片段、推近、字幕、HTML 画面层,一次全部烧进 mp4。用户说导出、出成片、烧字幕、渲染、导出视频、生成最终文件时使用。不要用于生成删词候选、写字幕、做画面动画。

Agentchengfeng/chengfeng-videocut-skills

整理、脱敏并上报 chengfeng-videocut 的 GitHub Bug。用户说上报 Bug、反馈剪口播问题、提交 GitHub Issue、这个问题告诉开发者,或要求继续提交已预览的 Bug 草稿时使用。不要用于功能建议、普通排错、代码提交或未获用户确认的自动上报。

Agentchengfeng/chengfeng-videocut-skills

给剪好的口播做字幕:直接用已有的逐词稿加账本算出剪后时间(不必导出、不必重新转录)、用词典和作者文稿改写听错的专名、按句子分屏、在 Studio 里逐屏复核。用户说做字幕、加字幕、改字幕、重新分屏、字幕不对时使用。不要用于删词剪辑、物理剪切、分镜动画或成片渲染。

Agentchengfeng/chengfeng-videocut-skills

操作 chengfeng-videocut 剪辑工作台的已有工程,通过 Runtime CLI 查工程与词句位置、添加或替换画面覆盖层、移除画面、删除明确指定的词句或片段、拆分裁剪移动已有片段、调整画布比例并回读核验。用户说插入片段、删掉这句、移除动画、换个画面、调整顺序或管理时间线时使用;先区分画面覆盖与主轨顺延插入,不负责自动判断口误、创作动画、制作字幕、导出或排查安装故障。

Agentchengfeng/chengfeng-videocut-skills

给剪好的口播配画面:在录屏上盖 HTML 层(圈重点标注 / 小黑整屏动画 / 推近),层绑字幕屏、由播放器逐帧驱动、直接在预览里看。用户说做分镜、配画面、加动画、圈重点、B-roll、做 storyboard 时使用。不要用于删词剪辑、字幕、物理剪切或成片渲染。

相关技能