Video Wrapper skill
A Claude Code skill for interview videos: it proposes lower thirds and cards from subtitles and renders once you approve
- 343 ★ on the repository
- Last commit
Extended access
Why this level
- The skill runs Python scripts and the Chromium browser and writes video files to disk
- The Bash, Read and Write tools are allowed inside the project folder
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/video-wrapperDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The skill runs Python scripts and the Chromium browser and writes video files to disk
- The Bash, Read and Write tools are allowed inside the project folder
This is third-party code. Review the repository files before installing.
What it does
Video Wrapper adds variety-show style graphics to interview and podcast videos. The skill reads SRT subtitles and finds the guest, topic changes and terms, plus quotes and numbers. From these it builds a list of proposals that you review as markdown: edit it, remove what you do not need or add your own. Rendering starts only after that. The set has eight components, from a lower third with the guest's name to animated numbers and a subscribe call. The look comes from four themes: Notion, Cyberpunk, Apple and Aurora. The film is rendered by a browser engine on Playwright or by PIL on plain Python. In Claude Code the call looks like `/video-wrapper interview.mp4 subtitles.srt`, and the script can also be run directly through src/video_processor.py.
Who it is for. For authors of interviews, podcasts and educational videos who already have a recording and a subtitle file and want the graphics without an editing program.
Good fit when
- You have an interview recording with an SRT subtitle file and need a lower third with the guest's name and role
- You want to highlight key phrases and quotes in a video without marking up timings by hand
- Terms in the video should be explained by pop-up cards on their first mention
- You want to pick a look from ready themes and review the proposals before rendering
- Videos are made for YouTube or Bilibili and need simple graphics without editing software
Not a fit when
- There are no subtitles: you first need to get them with another tool
- You need cutting, joining and sound work: the skill only adds graphics
- You need your own templates: the themes come as four CSS sets in the static/css folder
- Chromium for Playwright cannot be installed in your environment, yet you need complex animations
Example request
/video-wrapper interview.mp4 subtitles.srt and show the design proposals in the Apple themeLimitations
You need Python with a virtual environment, the dependencies from requirements.txt and Chromium for Playwright, installed with `playwright install chromium`. The SKILL.md file is written in Chinese, so it is better to state the language of the proposals in your request.
GitHub did not detect a license for the repository, although the description shows an MIT badge. Rendering through PIL needs fewer dependencies but is behind the browser engine in animation quality.
How to disable. Delete the video-wrapper folder from ~/.claude/skills together with its virtual environment. If you installed through npx skills, delete the skill from the folder where it placed the files.
FAQ
How do I install Video Wrapper in Claude Code?
Run `npx skills add https://github.com/op7418/Video-Wrapper-Skills`. For a manual install clone the repository into ~/.claude/skills, create a virtual environment, install requirements.txt and run `playwright install chromium`.
Which graphic components does Video Wrapper have?
Eight: key phrases, a guest lower third, chapter cards, term cards, quote callouts, animated numbers, a list of main points and a subscribe call.
Do I need to approve proposals before rendering?
Yes, the skill first shows proposals in markdown, and you confirm, edit or delete them. The config.json file is built from the approved list.
How do the two rendering engines differ?
The browser engine on Playwright makes complex animations and is the one the author recommends. PIL runs on plain Python and needs no browser. You pick one with the `-r browser` or `-r pil` key.
Can I run Video Wrapper without Claude Code?
Yes, the script can be called directly: `python src/video_processor.py video.mp4 subs.srt config.json output.mp4`. You then prepare the component configuration yourself.
Discussion
No questions or reviews yet.
Related
SkillsClaude Code skills that turn a talking-head recording into a YouTube video with graphics, sound and thumbnails
A skill that turns a topic into a narrated 4K video: research, script, local TTS, Remotion composition and an FFmpeg mix
Claude Real Video
claude-real-video
A skill that lets Claude watch a video: it pulls scene-aware, deduplicated frames and a speech transcript through whisper from a link or file
A video editing skill for Claude Code and Codex: the agent cuts pauses and filler words, grades color, burns subtitles and adds animated overlays
Five Claude Code skills that produce faceless vertical YouTube Shorts from Remotion code, video models or paper collage
A director skill: it interviews you about a video idea and turns it into a second-by-second shot script for HyperFrames
Comparison with similar tools
Entries that share the main search query, and how they differ.
| Entry | Official | Repository stars | Main difference |
|---|---|---|---|
| Video Wrapper (this entry) | no | 343 | |
| Claude Remotion Skill | no | 708 | teaches an agent to build video from scratch as Remotion code |
| YouTube Clipper Skill | no | 2,267 | downloads a YouTube video and splits it into semantic clips |
| video-shotcraft | no | 14,693 | builds cinematic product videos |
README in short
The process has two steps with approval in between, and the author shows it on scenarios for education, podcasts and social media. A reference for the four themes closes the text.
README badge
Original SKILL.md
--- name: video-wrapper description: 为访谈视频添加综艺特效（花字、卡片、人物条、章节标题等）。支持 4 种视觉主题，先分析字幕内容生成建议供用户审批，再渲染视频。 argument-hint: <video-file> <subtitle-file> [config.json] [output.mp4] user-invocable: true allowed-tools: Bash, Read, Write context: fork agent: general-purpose --- # 访谈视频处理器 基于 Python + Playwright + MoviePy 的视频特效处理工具，使用 HTML/CSS/Anime.js 渲染高质量视觉效果。 ## 工作流程 ### 第一步：分析字幕内容 当用户提供视频和字幕文件时，先分析字幕内容，生成特效建议： 1. 读取字幕文件 (.srt) 2. 分析内容，识别： - 嘉宾信息（用于人物条） - 话题切换点（用于章节标题） - 关键词和术语（用于花字） - 专业名词（用于名词卡片） - 精彩观点（用于金句卡片） - 数字数据（用于数据动画） - 核心要点（用于要点列表） 3. 生成建议列表，展示给用户审核 ### 第二步：用户审核 将建议以 Markdown 格式展示给用户： ``` ## 视觉特效建议 **主题**: notion ### 1. 人物条 (Lower Third) - **姓名**: Dario Amodei - **职位**: CEO - **公司**: Anthropic - **出现时间**: 1000ms ### 2. 花字高亮 (Fancy Text) 1. **通用人工智能** (emphasis)