Home / amliuyong / html-to-explainer-video · GitHub

html-to-explainer-video SKILL.md skillA

html-to-explainer-video from amliuyong/html-to-explainer-video is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add amliuyong/html-to-explainer-video/html-to-explainer-video@v2.3.0

Pins v2.3.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
amliuyong/html-to-explainer-video
Path
SKILL.md
Versions recorded
5
Latest version
v2.3.0, committed Nov 3, 2026
First version recorded
Oct 23, 2026
Size
62,788 bytes
Repository stars
5
License
MIT

把任意主题做成讲解/科普视频并渲染成 MP4（HTML/CSS/GSAP 画面 + 确定性逐帧渲染 + 配音（默认阿里云百炼，可切 edge-tts / 火山）+ 词级硬字幕）。触发场景：要做科普/讲解/教学/知识/产品类视频、「讲一下 X 做成视频」、要挑某种视觉风格（极简/数据/赛博/电影感/品牌）出片、要出抖音封面/竖版封面/9:16 封面、要用 html-video 那种模板化画面但更稳的音画同步、anything2explainer 换 HTML 渲染，或提到 html-to-explainer-video / HTML 讲解视频 / explainer video / MG 视频。内置 23 个模板风格（8 类）与 40+ 动作词汇的动效库，主题驱动模板编排；支持 4K60、快门运动模糊、多进程提速、断点续渲；流程含六个用户确认点（渲染通道是硬闸门）。独立可移植，不依赖 html-video / anything2explainer。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# html-to-explainer-video

> **定位**：主题 → 解说词 → 配音 → 词级字幕 → HTML/GSAP 画面 → 确定性逐帧渲染 → QC → 封面的完整流水线，
> 画面节拍锚在吐字时刻上。MIT 许可；第三方组件与署名见 `THIRD_PARTY_NOTICES.md`。
>
> **零外部依赖**：不需要 Remotion/npm 工程，不需要任何外部模板仓库/Studio/pnpm/agent 后端。
> 技能自带：GSAP（离线）、playwright-core、渲染器、TTS/字幕/时间轴/主题/QC/封面全套脚本。
> 风格库是**随包附带的设计规范文本**（`references/style-catalog.md`，转写自 `html-video` 的模板规范，Apache-2.0），
> 运行时不读任何外部项目的文件。

**v2.0 新增能力（全部可选、向下兼容；不用就是 v1.4 行为）**

| 能力 | 入口 | 文档 |
|---|---|---|
| **动效库**（40+ 动作词汇） | `assets/motion.js` → `window.HXM` | `references/motion-library.md` |
| **主题驱动模板编排**（挑风格 / 混用 / 动态开头） | `scripts/style_director.py` | `references/style-director.md` |
| **画质帧率档位 + 快门运动模糊 + 提速** | `scripts/render_video.mjs --profile/--quality/--fps/--shutter-only/--motion-hold` | `references/render-profiles.md` |
| **渲染基准测试**（优化前后对比） | `scripts/bench_render.py` | `references/render-profiles.md` |
| **宣传片范式**（去模板化：模板只吸纳配色/字体/时序三层） | 设计方法 | `references/showcase-mode.md` |
| **库全量演示编排**（统一舞台 + 节拍网格 + 标签常驻） | 设计方法 | `references/library-showcase.md` |
| **确认闸门**（六个确认点由用户拍板才放行） | `scripts/gate_check.py` | `SKILL.md` 流程第 3 步 |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add amliuyong/html-to-explainer-video/html-to-explainer-video@sha256:08ab2ebdef4bdb66

The line at the top of this page pins the label v2.3.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_gh7wpjtp5taoviqq.svg)](https://markdownregistry.com/a/art_gh7wpjtp5taoviqq)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Oct 23, 2026 and Nov 3, 2026, about one every 3 days.

versioncommittedcommitsizeaudit
v2.3.0 latest2026-11-03 6f2ef56 62,788 BA view · diff
v2.2.62026-10-25 3aec428 61,272 BA view · diff
v2.2.52026-10-25 fe80961 60,005 BA view · diff
v2.2.42026-10-24 77dcdf9 60,005 BA view · diff
v2.2.32026-10-23 d631f7b 59,417 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (62788 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

amliuyong/html-to-explainer-video · 5 stars · license MIT · pushed 2026-11-03 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_gh7wpjtp5taoviqq
GET https://markdownregistry.com/api/v1/resolve?ref=amliuyong/html-to-explainer-video/html-to-explainer-video
GET https://markdownregistry.com/api/v1/blob/08ab2ebdef4bdb6676c08bbd8c5147e6bdbd67e80ca249b54286a7140cc6690a

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

Browse by kind, by grade A, or by owner.