Home / haojing8312 / easegen-video-talkcraft · GitHub

easegen-video-talkcraft SKILL.md skillA

easegen-video-talkcraft from haojing8312/easegen-video-talkcraft is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add haojing8312/easegen-video-talkcraft/easegen-video-talkcraft@git:20260918.f54e634

Pins git:20260918.f54e634 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
haojing8312/easegen-video-talkcraft
Path
SKILL.md
Versions recorded
5
Latest version
git:20260918.f54e634, committed Sep 18, 2026
First version recorded
Sep 15, 2026
Size
57,740 bytes
Repository stars
17
License
a license file GitHub does not identify

本地优先的数字人口播视频 Skill：中文口播稿和成品配音，或可选 IndexTTS2 本地配音与独立数字人运行时，经 CPU 字级时间戳、SHOTBOOK、108 张动效卡、Remotion 合成横屏或竖屏成片；也支持可选 Fish Audio。用于数字人口播、解说、科普和配音驱动画面任务；不包含第三方模型权重或云端 GPU 服务。.

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

# easegen-video-talkcraft — 本地数字人口播视频 Skill

三大来源合体：**管线**（配音→字级时间戳→Remotion）+ **词汇**（108 张动效配方卡，全配可播 demo + 自包含 tsx）+ **镜头**（七层模型反 PPT 系统）+ **视觉语言**（Apple 范式默认版）。

核心范式：解说词驱动画面，每句都要有**活的画面响应**（相机极缓推拉/已有元素的变化），
但**新元素只在语义拍边界进场，禁止机械的"一句一个新元素"**（一句一元素是堆积型凌乱的制度根源；
分镜按语义段落切，排版预算见 cinematography.md §4.5）；
**一个节拍只有一个主角，说完就让位**；字幕句边界 = 全片时间锚点。

## 流程

```
① 文案 → ② 成品配音或可选 IndexTTS2/Fish Audio → ②½ 人物素材或本地数字人 → CPU 时间戳 → ③ 其他素材
                                → ④ SHOTBOOK 层矩阵 → ⑤ 实现(全局系统 → 首镜先做先确认 → 其余镜头)
                                → ⑥ 渲染 → ⑦ 三重验收（机器闸全过 + 1 轮审片修 P0/P1）→ ⑧ 交付（可选续审 ≤3 轮）
```

## Plus 流程：IndexTTS2 + 本地数字人

首次安装、缺依赖或询问“素材放哪里/数字人怎么下载”时，先读
[`references/beginner-windows.md`](references/beginner-windows.md)。按实际路径配置独立环境；
IndexTTS2 使用官方 v2 CLI，不要求修改上游模型源码；独立数字人包的引擎路径是 `engine` 子目录。
运行包没有私人示例音色或人物视频，缺少时要求用户提供授权素材，不从其他项目擅自挑选。

当用户只有口播稿、授权音色参考和单人人物母片，希望 Skill 同时生成配音与人物口型时，读取
[`references/plus-pipeline.md`](references/plus-pipeline.md)，使用 `scripts/plus_pipeline.py` 初始化、预检并运行。

- 所有本地 Plus 推理在用户自己的电脑上运行，不接入远程 GPU 租赁或自动云端回退。Fish Audio 是可选云端服务，须经用户选择。
- IndexTTS2 可选择 CPU、CUDA 等上游支持的设备；CPU 是兼容路径，不承诺实时速度。
- Windows 使用 `heygem-win-onnx`：外部 Windows ONNX 整合包 + 自带 Python 3.10，
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add haojing8312/easegen-video-talkcraft/easegen-video-talkcraft@sha256:508087e8eccb8e83

The line at the top of this page pins the label git:20260918.f54e634, 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_7ti3y6ksm2zjyt54.svg)](https://markdownregistry.com/a/art_7ti3y6ksm2zjyt54)

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

Versions

The registry has recorded 5 versions of this file, between Sep 15, 2026 and Sep 18, 2026, more than one a day.

versioncommittedcommitsizeaudit
git:20260918.f54e634 latest2026-09-18 f54e634 57,740 BA view · diff
git:20260917.de2bc7f2026-09-17 de2bc7f 55,430 BA view · diff
git:20260916.6f2524e2026-09-16 6f2524e 51,219 BA view · diff
git:20260916.e1ef6092026-09-16 e1ef609 50,343 BA view · diff
git:20260915.687c8602026-09-15 687c860 54,017 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 (57740 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

haojing8312/easegen-video-talkcraft · 17 stars · license a license file GitHub does not identify · pushed 2026-09-18 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_7ti3y6ksm2zjyt54
GET https://markdownregistry.com/api/v1/resolve?ref=haojing8312/easegen-video-talkcraft/easegen-video-talkcraft
GET https://markdownregistry.com/api/v1/blob/508087e8eccb8e83e2f36f65521aa962897386005ae7338bbab3807e4d65e3d8

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.