Qiaomu Cut
joeseesun/qiaomu-cut-skill
把一句话需求转成可复现、可验收视频工程的乔木智能剪辑导演。Use when the user asks to create, plan, edit, remix, explain, narrate, subtitle, animate, composite, or render a video—including one-line requests such as “制作一个科普视频：介绍…
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…
Install Video Talkcraft
$ npx skills add Vincentwei1021/video-talkcraft --skill video-talkcraft -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Vincentwei1021/video-talkcraft video-talkcraft --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "video-talkcraft" agent skill from https://github.com/Vincentwei1021/video-talkcraft/tree/main into .claude/skills/video-talkcraft/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-talkcraft", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Vincentwei1021/video-talkcraft --skill video-talkcraft -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Vincentwei1021/video-talkcraft video-talkcraft --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "video-talkcraft" agent skill from https://github.com/Vincentwei1021/video-talkcraft/tree/main into .agents/skills/video-talkcraft/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-talkcraft", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Vincentwei1021/video-talkcraft --skill video-talkcraft -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Vincentwei1021/video-talkcraft video-talkcraft --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "video-talkcraft" agent skill from https://github.com/Vincentwei1021/video-talkcraft/tree/main into .cursor/skills/video-talkcraft/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-talkcraft", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Vincentwei1021/video-talkcraft --skill video-talkcraft -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Vincentwei1021/video-talkcraft video-talkcraft --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "video-talkcraft" agent skill from https://github.com/Vincentwei1021/video-talkcraft/tree/main into .gemini/skills/video-talkcraft/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-talkcraft", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Vincentwei1021/video-talkcraft video-talkcraftInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Vincentwei1021/video-talkcraft --skill video-talkcraft -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "video-talkcraft" agent skill from https://github.com/Vincentwei1021/video-talkcraft/tree/main into .github/skills/video-talkcraft/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-talkcraft", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Vincentwei1021/video-talkcraft --skill video-talkcraft -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Vincentwei1021/video-talkcraft video-talkcraft --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "video-talkcraft" agent skill from https://github.com/Vincentwei1021/video-talkcraft/tree/main into .opencode/skills/video-talkcraft/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-talkcraft", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
video-talkcraft- GitHub stars
- 1.5k
- Token cost
- ~8.7k tokens
- SKILL.md length
- 1,955 words
- Files
- 1,071 (incl. scripts, references, assets)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
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…
- Works in 4 steps: 先搭全合成骨架：remotion/ 目录建好后先 bash… → 只实现样板镜（SHOTBOOK G0「样板镜」行，默认 s01）：按… → 渲一条有声单镜预览给用户看：只渲这一段的视频和这一段的音频，不渲整条音轨（其余镜头… → …
- Tasks that involve Video production
- SKILL.md covers 流程, ⓪ 开工体检：统一依赖 + 画幅与视觉语言, ① 口播稿 and ② 配音输入 → 预剪 → 字级时间戳（默认本机…, plus 6 more sections
- Runs JavaScript scripts from its folder; calls python3, npm and node; needs FISH_AUDIO_API_KEY
What it does
Video Talkcraft is an agent skill from Vincentwei1021/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。
Its SKILL.md is about 8.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1075 other files, including scripts, reference files and assets (for example `.github/workflows/deploy-pages.yml`, `README.md` and `README_EN.md`).
It sits in Media & Creative, covering Video production, Motion graphics and Text to speech and voice. It works with Remotion, Three.js and npm. The repository describes itself as: Agent skill that turns Claude Code / Codex into a motion-design studio for voiceover-driven explainer videos — word-level voiceover sync, 109 motion recipe cards, an…
When your agent uses it
- Tasks that involve Video production
- Tasks that involve Motion graphics
- Tasks that involve Text to speech and voice
Example prompts
- “解说/科普视频”
- “把文案变成视频”
- “给配音配画面动效”
- “/video-talkcraft”
Requirements
- Python 3
- Node.js
- A credential in FISH_AUDIO_API_KEY
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- 先搭全合成骨架：remotion/ 目录建好后先 bash /runtime/link-runtime.sh <本片工程>（node_modules 软链到统一依赖、package.json 依赖版本抄 runtime——不自建、不 npm install），
- 只实现样板镜（SHOTBOOK G0「样板镜」行，默认 s01）：按 SHOTBOOK 全量落地——蒙皮行、卡 tsx 复制、音效 cue、转场处置——不做"先糙后精"。
- 渲一条有声单镜预览给用户看：只渲这一段的视频和这一段的音频，不渲整条音轨（其余镜头都是占位，整条音轨没意义；2026-09-09 demo v4 实测 6s 首镜 47s 出预览：段 34s + 段音频 10s）
- 问一次，等回答（AskUserQuestion 类工具，两个选项，不替用户决定）：「样板确认，继续做其余镜头」/「先改样板」。
What it can do on your machine
Read from SKILL.md and the folder at commit 4cd673d. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (JavaScript, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
python3npmnodebashnpxpipcurlffmpeg
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
x.comdouyin.comxhslink.cn
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
FISH_AUDIO_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Video Talkcraft loads about 8.7k tokens when it runs, and up to ~375k if it reads all its reference files. Until then it costs about 86 tokens; SKILL.md has 1,955 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NoteMentions a .env fileSKILL.md:78
# 在 .env 配置 FISH_AUDIO_API_KEY=xxx 及可选 FISH_AUDIO_REFERENCE_ID=xxx（见 .env.example）
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,955 words (~8,709 tokens).
“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）。”
- name
- video-talkcraft
Files
SKILL.md and 1,070 other files (scripts, references, assets) in the repository root of Vincentwei1021/video-talkcraft.
- SKILL.md
- .env.example
- .github/workflows/deploy-pages.yml
- .gitignore
- LICENSE
- README.md
- README_EN.md
- THIRD_PARTY_NOTICES.md
- assets/gallery-en.png
- assets/gallery-zh.png
- assets/logo.svg
- assets/wechat-group.jpg
- demos/_lib/demo-shell.css
- demos/_lib/demo-shell.js
- demos/_lib/dh-host.mov
- demos/_lib/dh-host.webm
- … and 1,055 more
Open the folder on GitHubat commit 4cd673d
Compare with similar skills
Video Talkcraft next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Video Talkcraft this skillVincentwei1021/video-talkcraft | 1.5k | — | ~8.7k | Automated safety check: Notes | Custom licence | |
| Qiaomu Cutjoeseesun/qiaomu-cut-skill | 372 | — | ~6.8k | Automated safety check: Notes | MIT | |
| Content To Videoarchitectds/modeldock | 117 | — | ~2.4k | Automated safety check: Pass | Apache-2.0 | |
| Painted Animationtuzhechen2005/opus-video-skills | 146 | 1 repos | ~1.9k | Automated safety check: Pass | Custom licence | |
| Anything2explainerVincentwei1021/anything2explainer | 2.4k | — | ~2.7k | Automated safety check: Pass | Custom licence | |
| Super Video MakerBomx/super-video-maker-skill | 310 | — | ~11k | Automated safety check: Notes | None |
Similar skills
Content To Video
architectds/modeldock
Turn arbitrary source content (README, article, story, slides, deck, data/report, product description, tutorial text, audio/transcript, or a bare topic) into a finished, high-quality MP4 video.
Painted Animation
tuzhechen2005/opus-video-skills
Make hand-painted watercolour-and-ink cartoon videos (MP4) with code — p5.js + p5.brush rendered frame by frame in headless Chrome, encoded with ffmpeg — starring Clawd or any character.
Anything2explainer
Vincentwei1021/anything2explainer
给一个主题，产出一条黑底 MG 风格（幕底可选星点或点阵波）、有配音字幕章节进度条的科普讲解视频（中文或英文；Remotion 代码动画；时长由用户定，常用 3–5 分钟）。内含可编译模板、图元库、配音/分镜/渲染工具、风格与动效规范、多 agent 分工协议与 QC 判据，以及一条完整样片（《RAG 与知识库》）作为质量标尺。Turn any topic into a narrated…
Super Video Maker
Bomx/super-video-maker-skill
End-to-end AI video production skill for agentic frameworks.
Remotion
zhuzhaoyun/Molio
Molio's builtin skill for MAKING a video from any source — wiki notes, articles, scripts, product info, or a brief — and rendering it to MP4.
Related
Categories
Questions about Video Talkcraft
What does Video Talkcraft do?
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…. Video Talkcraft is an agent skill from Vincentwei1021/video-talkcraft.
When should I use Video Talkcraft?
Video Talkcraft fits situations like: tasks that involve Video production; tasks that involve Motion graphics; tasks that involve Text to speech and voice.
How do I install Video Talkcraft in Claude Code?
Run `npx skills add Vincentwei1021/video-talkcraft --skill video-talkcraft -a claude-code`. Or copy the skill folder (the Vincentwei1021/video-talkcraft repository) into .claude/skills/video-talkcraft in your project. Claude Code loads it when a task matches its description.
How do I install Video Talkcraft in Codex?
Run `npx skills add Vincentwei1021/video-talkcraft --skill video-talkcraft -a codex`. Or copy the skill folder (the Vincentwei1021/video-talkcraft repository) into .agents/skills/video-talkcraft in your project. Codex loads it when a task matches its description.
Can I use Video Talkcraft in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Vincentwei1021/video-talkcraft --skill video-talkcraft -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/video-talkcraft, .gemini/skills/video-talkcraft, .github/skills/video-talkcraft and .opencode/skills/video-talkcraft in your project.
What does Video Talkcraft need to run?
Going by SKILL.md and its folder, Video Talkcraft needs JavaScript for the scripts in its folder, the command-line tools its instructions call (python3, npm, node, bash, npx and pip) and credentials named FISH_AUDIO_API_KEY. Our summary lists: Python 3; Node.js; A credential in FISH_AUDIO_API_KEY.
Does Video Talkcraft access the network?
SKILL.md names 3 domains. As links in the text: x.com, douyin.com and xhslink.cn. This is read from the text; nothing was executed.
Is Video Talkcraft safe to install?
Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Video Talkcraft use?
Video Talkcraft has a licence file (from the LICENSE file in the skill folder) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Video Talkcraft use?
About 8.7k tokens (SKILL.md is roughly 35k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 366k tokens, read only when the agent opens those files.
What are the alternatives to Video Talkcraft?
Skills that share tags, products or a category with Video Talkcraft: Qiaomu Cut (joeseesun/qiaomu-cut-skill, 372 stars), Content To Video (architectds/modeldock, 117 stars), Painted Animation (tuzhechen2005/opus-video-skills, 146 stars) and Anything2explainer (Vincentwei1021/anything2explainer, 2.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Video Talkcraft?
Vincentwei1021 (a GitHub user) maintains it in Vincentwei1021/video-talkcraft, which has 1,466 GitHub stars. The repository was last updated on October 1, 2026.
Source: Vincentwei1021/video-talkcraft on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.