Video Talkcraft

终极口播视频 skill：中文口播稿 + 成品配音 → CPU 字级时间戳 → SHOTBOOK 层矩阵分镜 → Remotion 电影感成片（横屏默认/竖屏）。当用户要"做口播视频"、"解说/科普视频"、"把文案变成视频"、"给配音配画面动效"时使用。默认使用成品配音，可选 Fish Audio 从稿子合成配音与时间戳；数字人生成技术不在本 skill 内（人物素材是输入）。含统一视觉语言（Apple 范式）、108 张动效配方卡、镜头三面分层工作单、七层镜头反PPT系统（极缓推拉相机/让位，运动做减法）、六式运动承接转场（每式一卡）、长镜头世界画布、anime.js+three.js 桥、自动静止检测 + 独立 subagent 评估循环。

1,974 stars 203 forksImages, Video & Audio

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add Vincentwei1021/video-talkcraft --skill video-talkcraft

Manual install

git clone --depth 1 https://github.com/Vincentwei1021/video-talkcraft.git /tmp/video-talkcraft
mkdir -p ~/.claude/skills
cp -r /tmp/video-talkcraft/. ~/.claude/skills/video-talkcraft

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# video-talkcraft — 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 配音输入+时间戳(本机CPU) → ③ 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）
```

## ⓪ 开工体检：统一依赖 + 画幅与视觉语言
**依赖只有一份**：所有口播工程的 `remotion/node_modules` 与 `workbench/node_modules` 都是指向 `<skill根>/runtime/node_modules` 的软链，版本只在
`runtime/package.json` 里钉（`@remotion/*` 全家同号）。**新片开工第一件事**（用户 2026-09-15 定版：每次新做视频都要检查更新）：
```bash
bash <skill根>/runtime/check-runtime.sh --upgrade   # 装好共享依赖 + 共享无头浏览器 + 链好 workbench；Remotion 有新版就全家升级并冒烟渲 1 帧，不过自动回滚
```
末行 `[runtime] OK` 才往下走；升了级要把 `runtime/package.json` / `package-lock.json` 的改动提交。**制作中途不升级**（母版段缓存不认依赖版本，混版本渲出的段不一致）。
工程目录里**永远不跑 `npm install`**（会写进共享目录）；要加包 → 加进 `runtime/package.json`，`npm ci`，再提交。

### 画幅与视觉语言（开工先定，全流程引用）
- **画幅默认横屏 1920×1080**（用户偏好）；明确要发抖音/竖屏渠道才用 1080×1920
- 视觉语言：**用户明确点了风格就按用户的来**（整套 token 替换）；没点时**先从口播稿判定领域、派生本片风格档**
  （`references/design-language.md` §0：读全稿答"讲什么 / 对谁讲 / 什么口吻"→ 领域 → 风格档表给底色策略 / accent / 字体气质 / 材质与卡造型 / 图表语言 / 素材气质 / 能量档，
  写进 SHOTBOOK §0 `G0 风格档`），骨架仍是 Apple 范式（一个强调色/一个投影/底色交替分幕/两档字重/

Read the full skill on GitHub

Details

Skill name: video-talkcraft
Repository: Vincentwei1021/video-talkcraft
Repo updated: 12 October 2026

FAQ

What does the Video Talkcraft skill do?

How do I install the Video Talkcraft skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add Vincentwei1021/video-talkcraft --skill video-talkcraft. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Video Talkcraft popular?

It lives in Vincentwei1021/video-talkcraft, which has 1,974 GitHub stars and 203 forks.

Related skills

Aso Appstore Screenshots

1.8k

adamlyttleapps/claude-skill-aso-appstore-screenshots

Generate high-converting App Store screenshots by analyzing your app's codebase, discovering core benefits, and creating ASO-optimized screenshot images using Nano Banana Pro.

Images, Video & Audio277

Holo Card Studio

EverettFish/holo-card-studio

Create collectible holographic foil cards and two-image lenticular flip cards with AI-generated full-color ukiyo-e and colored sumi-e anime artwork, layered Blender scenes, renders, GLB export, and a flat white web viewer. Use for 镭射卡、闪卡、全息卡、光栅卡、一念神魔、双形态卡、角色收藏卡，或需要保持角色高度一致的 A/B 状态切换。

Images, Video & Audio262

Capcut Edit

1.1k

renezander030/capcut-cli

Edit CapCut / JianYing video projects — read and write subtitles, timing, speed, volume, templates, animations (fade/ken-burns), and cut long-form to shorts. Use when the user mentions capcut, jianying, subtitles, video editing, draft_content.json, draft_info.json, or cutting videos — in English or Chinese (剪映, 字幕, 草稿, 剪辑, 切片, 视频编辑).

Images, Video & AudioIn 2 lists136

Clawra Selfie

2.4k

sumelabs/clawra

Edit Clawra's reference image with Grok Imagine (xAI Aurora) and send selfies to messaging channels via OpenClaw

Images, Video & Audio374

Female Portrait Director

1.7k

liyue-aigc/female-portrait-director

Generate, visually expand, optimize, diagnose, and route structured AI image prompts for adult female portraits. Use for lifestyle, curve-focused, fashion, oriental, fantasy, realism, beauty, CCD, low-key cinematic, studio, sport, travel, and e-commerce portrait requests; onboarding or usage help; parameter recommendations; prompt rewrites; image-to-prompt preparation; direct image generation; or identity- and product-preserving edits from authorized reference images. Preserve explicit user parameters and locked reference subjects while creating a coherent photography-directed scene.

Images, Video & Audio210

Hand Drawn

2.6k

threerocks/hand-drawn-styles

Use when users ask for a hand-drawn or illustrated image prompt, name one of the repository's 22 numbered styles or the 3.1 stable variant, or mention triggers such as 亲子手绘、家庭蜡笔画、蜡笔、吉卜力、水墨、像素、淡彩速写、动画概念、水粉、北欧绘本、纸雕、软胶潮玩、墨线绘本、暖色扁平绘本、圆头红线、暖黄墨线、family-crayon-card、warm-flat-storybook、roundhead-redline、warm-yellow-ink-story、朱墨写意、朱墨水墨漫画、vermilion-ink-wash、ink-comic-transfer、皮影、皮影彩染、shadow-puppet、backlit-puppet. Produces prompt text or a formal reference-bearing call bundle and does not generate images.

Images, Video & Audio275

Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.