reelbench-skills
Из публичных источниковУчебные заметки и навыки работы с инструментами для ИИ-видео - skill для AI видео
Машинный перевод · Показать оригинал
Learning notes and tooling skills for AI video - AI 视频相关的学习与工具 skill
Обзор
- ai-video
- claude-skills
- ffmpeg
- shot-analysis
- video-analysis
Установка
Команды только показываются, маркетплейс их не выполняет. Сверяйтесь с официальной документацией.- Сборка из исходниковИз публичных источниковиз метаданных каталога
Сборка из исходников: проверенного рецепта сборки нет — следуйте инструкциям репозитория.
github.com/eternityspring/reelbench-skills ↗
Совместимость
«Неизвестно» значит, что доказательств не найдено, а не что продукт несовместим.| Платформа | Статус | Архитектура | Доказательство | Уверенность |
|---|---|---|---|---|
| Claude Code | Неизвестно | — | — | — |
| Claude (web & desktop) | Неизвестно | — | — | — |
| OpenAI Codex | Неизвестно | — | — | — |
| ChatGPT | Неизвестно | — | — | — |
| Cursor | Неизвестно | — | — | — |
| GitHub Copilot | Неизвестно | — | — | — |
| Gemini CLI | Неизвестно | — | — | — |
Релизы
проверено 30 окт. 2026 г.Профиль качества
алгоритм quality-v1.0 · оценено 16 окт. 2026 г.Составляющие оценки
Лицензия
Apache-2.0Это статус политики каталога, а не юридическое заключение.
Источники
Отзывы
Отзывов пока нет.
Альтернативы
drama-skillsПохожийvideo-recap-skillsПохожийREADME
Из eternityspring/reelbench-skills · лицензия Apache-2.0 · загружено 30 окт. 2026 г.reelbench-skills
Claude Code / Codex skills for working with video.
English | 中文 | Telegram @ahao_dev | X @eternityspring
Skills · Install · Example · What it looks like
❤️ Sponsor
Skills
| skill | what it does |
|---|---|
| video-shots | 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 | 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 | 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 and mention github.
Install
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.
./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.
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.
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: 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:
If the player does not load, grab the file: demo-sync/demo-en-sync.mp4