reelbench-skills
Learning notes and tooling skills for AI video - AI 视频相关的学习与工具 skill
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Badge for your README
Markdown
[](/listings/eternityspring-reelbench-skills)HTML
<a href="/listings/eternityspring-reelbench-skills"><img src="/api/listings/eternityspring-reelbench-skills/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
git clone https://github.com/eternityspring/reelbench-skills.git cd reelbench-skills ./scripts/install.sh
软链到 `~/.claude/skills/` 和/或 `~/.codex/skills/`(哪个装了就装到哪),**`git pull` 之后立刻生效**。
./scripts/install.sh --claude # 只装到 Claude Code ./scripts/install.sh --codex # 只装到 codex ./scripts/install.sh video-shots # 只装某一个 skill ./scripts/install.sh --uninstall # 取消软链
依赖只有 `node` >= 18 和 `ffmpeg` / `ffprobe`(macOS:`brew install node ffmpeg`)。 **零 npm 依赖、零 API key**,用当前会话额度。
不想软链就直接拷:`cp -r skills/video-shots ~/.claude/skills/`——skill 自包含,拷走就能用。
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
README.md · README · 113 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- <div align="center">
- # reelbench-skills
- **Claude Code / Codex skills for working with video.**
- English | [中文](README.zh.md) | [Telegram @ahao_dev](https://t.me/ahao_dev) | [X @eternityspring](https://x.com/eternityspring)
- **[Skills](#skills) · [Install](#install) · [Example](#example) · [What it looks like](#what-it-looks-like)**
- </div>
- ## ❤️ Sponsor
- > [Want to appear here?](mailto:eternityspring@gmail.com)
- <details open>
- <summary>Click to collapse</summary>
- <table>
- <tr>
- <td width="180"><a href="https://studio.reelbenchai.com"><img src="assets/reelbench-first-screen-en.png" alt="Reelbench Studio" width="150"></a></td>
- <td><a href="https://studio.reelbenchai.com">Reelbench Studio</a> is a paid AI video workspace built by the author of these skills, delivered as source code that runs offline. Local Codex handles understanding, breakdown and orchestration, a self-hosted ComfyUI generates the images and video, and your assets and projects stay on your own machine.</td>
- </tr>
- <tr>
- <td width="180"><img src="assets/reelref-miniapp-qr.png" alt="赛博班底 mini program code" width="150"></td>
- <td>赛博班底 is a WeChat mini program built by the author of these skills: reference images for AI short video, covering characters, costumes, expressions and more, filterable by category and tag. Every image comes with a Chinese prompt you can copy in one tap, and you can long-press the full-size image to save it. Scan the code on the left in WeChat to open it.</td>
- </tr>
- </table>
- </details>
- ## Skills
- | skill | what it does |
- | --- | --- |
- | [video-shots](skills/video-shots/README.en.md) | **Shot breakdown**: turns a finished film into a shot-by-shot table — duration, shot size, category, camera move, frame description, rhythm role. Cuts and durations are measured by ffmpeg; the model only judges what it should; 15 quality gates check every call. |
- | [video-sync](skills/video-sync/README.en.md) | **Composites a video with the shot data alongside it**: footage on one side, the current shot's data on the other, switching at every cut with the list scrolling and highlighting itself. Landscape stacks, portrait sits side by side; the layout is one CSS file. |
- | [video-scrub](skills/video-scrub/README.en.md) | **Strips metadata**: rebuilds the film as a clean file carrying only picture and sound — GPS, device, account IDs and telemetry tracks all left behind. The hard part is the three layers `ffprobe` cannot see: SEI, the AAC DSE, and compressorname. Byte-for-byte picture by default, verified by 12 byte-level gates. |
- ## AI video community
- I run a paid group about AI video — workflows, tools, and how this stuff actually gets done.
- Interested? Message me on Telegram **[@ahao_dev](https://t.me/ahao_dev)** and mention **`github`**.
- ## Install
- ```bash
- git clone https://github.com/eternityspring/reelbench-skills.git
- cd reelbench-skills
- ./scripts/install.sh
- ```
- This symlinks the skills into `~/.claude/skills/` and/or `~/.codex/skills/` (whichever exists),
- so **`git pull` takes effect immediately**.
- ```bash
- ./scripts/install.sh --claude # Claude Code only
- ./scripts/install.sh --codex # codex only
- ./scripts/install.sh video-shots # one skill only
- ./scripts/install.sh --uninstall # remove the symlinks
- ```
- Requirements: `node` >= 18 and `ffmpeg` / `ffprobe` (macOS: `brew install node ffmpeg`).
- **No npm dependencies, no API keys** — it runs on your current session.
- Prefer a copy over a symlink? `cp -r skills/video-shots ~/.claude/skills/` —
- each skill is self-contained.
- ## Example
- `demo-report/` is the **real output** of running the skill on `demo-video.mp4`
- (a 202.9-second AI-generated short film, *啥是AI*): 53 shots, 3.83 s average shot length,
- 15.7 cuts per minute, all 15 gates green. `demo-report-en/` is the same pipeline run on a
- 287.4-second English excerpt with `--lang en` — an entirely English report: 46 shots, 6.25 s
- average, and one 46.92 s take that scene detection never cut, because it genuinely never cuts.
- [](demo-report/shots-report.html)
- The report is a **single interactive page**: an embedded player (playback highlights the current
- shot, click a shot to jump), a pace strip, a shot list you can search, filter and sort (list or
- card view, first and last keyframe side by side, click a frame to enlarge), distributions, cast,
- and the quality gates. No external dependencies — double-click it offline.
- <img src="skills/video-shots/assets/report-mobile.png" width="360" alt="the shot list on a narrow screen">
- ```
- demo-report/
- ├── shots-report.html ← clone and double-click
- ├── shots.json ← the breakdown data for all 53 shots
- ├── shots.md ← Markdown shot list
- ├── track.json ← frame-difference motion curve (the machine's evidence)
- └── frames/ ← first and last keyframe of every shot, 106 files
- ```
- `demo-scrub/` is what **video-scrub** produces — four pieces of text and no video, because its
- output looks **exactly like the source**, which is the whole point. What is worth reading is the
- reconciliation, above all [`half.txt`](demo-scrub/half.txt): the textbook recipe leaves `ffprobe`
- looking spotless while the bitstream still carries x264's encoder-settings SEI in 4 places and the
- AAC DSE in 8 — **no `ffprobe` command shows either of them**.
- What **video-sync** produces is at the bottom of this page — as a video, not a screenshot.
- ## What it looks like
- A 287.4-second English excerpt with its 46-shot breakdown, 1280×1296 (the source is 640×360,
- blown up with `--scale 2`). The panel switches with every cut; the list scrolls up and the
- highlight rides along:
- <video src="https://github.com/eternityspring/reelbench-skills/raw/main/demo-sync/demo-en-sync.mp4" controls muted playsinline width="760"></video>
- If the player does not load, grab the file: [`demo-sync/demo-en-sync.mp4`](demo-sync/demo-en-sync.mp4)
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.