
Web Video Presentation
Turns written articles or narration scripts into click-driven 16:9 web presentations that look and feel like videos. You get a React app where each click advances one beat of the script, with fullscreen transitions designed on the fly using a content-first methodology instead of templated animations. The workflow is disciplined: it generates both the narration script and a chapter outline in one pass, forces you to align on five things (script, outline, theme, assets, dev mode) before any coding starts, then builds chapter one as a complete reference before touching the rest. Ships with a theme system, optional audio synthesis via MiniMax CLI, and explicit anti-AI-slop design principles baked into the chapter implementation guide. Best for recording screen demos that need cinematic pacing without looking like PowerPoint.
- skills.sh installs
- 6.3K
- GitHub stars
- 14.8K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add conardli/garden-skills --skill web-video-presentation --agent claude-codeInstalls into .claude/skills of the current project.
Files
Web Video Presentation
把一篇文章或口播稿,一步步做成可录屏的"伪装成视频的网页",可选合成 口播音频。产出物 = Vite + React + TS 项目 + 按章节切分的音频。
适用场景
- "我有口播稿 / 一篇文章,帮我做成视频" —— 口播驱动的内容
- 想做 "动态 PPT"
- 16:9 横屏录屏,大字、留白、每屏都要有动效
- 教学 / 产品演示 / keynote 想要电影感
- B 站 / YouTube /抖音视频内容
本 Skill 以方法论 + 协作流程为核心。脚手架模板提供 token 和原语, 但每个美学决策(配色、字型、动效气质)都应该针对你的主题重新设计 —— 不要照搬。
工作流总览
Phase 1 内容编写
1.1 识别用户输入
1.2 一次产出 script.md + outline.md
(口播稿 + 开发计划)
▼
[Checkpoint Plan] ← 必须停。一次对齐 5 件事:
稿子 / outline / 主题 / 素材 / 开发模式
▼
Phase 2 网页开发
2.1 脚手架(按选定主题)
2.2 第 1 章 = 主线程 + 完整版本(强制 anchor)
▼
[硬节点] 用户验收第 1 章 ← 不可跳过
▼
2.3 第 2~N 章(按选定模式:A 逐章 / B 顺序 / C 并行)
▼
[Checkpoint Audio] ← 必须停。是否合成音频
▼
Phase 3 音频合成(可选)
▼
Phase 4 录屏 + 后期
工作目录约定(agent 在用户当前目录下创建 / 编辑):
Sponsors
Details
- Repository
- github.com/conardli/garden-skills
- Categories
- Backend & APIs, Documentation, AI & Agent Building, Sales & Marketing, Cloud & Infrastructure, CLI & Terminal, Office & Documents, Generative Media
- First seen
- May 16, 2026