Back to Details

video-steal

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Video Steal

视频风格仿制

Someone's edit works and you want it on your own videos. This skill measures their edit, writes it down as a style, and proves it on one of your takes before you use it.
Output:
  • video-agent/styles/<name>.md
    : the style, read by 
    /video-edit <take> style <name>
    .
  • video-agent/styles/<name>/
    : its stills, sound effects and stickers.
  • video-agent/edits/<slug>-<name>/final.mp4
    : the test video.
Read references/learnings.md before you start. Each rule in it comes from a copy that got rejected.
某位创作者的剪辑效果很出色，而你希望在自己的视频中复现它。这个 skill 会测量对方的剪辑，将其记录成一种风格，并先在你的一段素材上验证效果，之后你再正式使用。
输出：
  • video-agent/styles/<name>.md
    ：风格文件，可由 
    /video-edit <take> style <name>
    读取。
  • video-agent/styles/<name>/
    ：该风格的静帧、音效和贴纸。
  • video-agent/edits/<slug>-<name>/final.mp4
    ：测试视频。
开始前先阅读 references/learnings.md。其中每条规则都源自一个被拒绝的仿制版本。

How to run it

如何运行

  • Preflight: 
    ffmpeg -version && yt-dlp --version
    . Missing: 
    /video-setup tools
    .
  • Talk in the creator's language. Say what you do in one line before each long step.
  • <name>
    : the creator's handle in lowercase with dashes, unless the user names the style.
  • Scratch files go in 
    video-agent/.tmp/steal-<name>/
    (
    W
    below).
  • 预检：
    ffmpeg -version && yt-dlp --version
    。如有缺失，运行：
    /video-setup tools
    。
  • 用创作者的语言交流。每个长步骤前用一行说明你要做什么。
  • <name>
    ：默认使用创作者账号名的小写形式并以短横线分隔，除非用户为该风格指定了名称。
  • 临时文件放在 
    video-agent/.tmp/steal-<name>/
    （下文记为 
    W
    ）。

1. Get the reel

1. 获取 reel

  • A local file: use it.
  • A YouTube link: 
    yt-dlp -o "W/reel.%(ext)s" "<url>"
    .
  • Instagram or TikTok: try 
    yt-dlp
    first. If it is blocked (login wall), and Treg is set up (
    treg balance
    answers), 
    treg catalog search "download an Instagram reel video file"
    , then 
    treg catalog get <id>
    for the price, then 
    treg call <id> --query url=<url>
    and download the video URL it returns. Otherwise ask the user to save the video and give you the file.
  • When you can, study 2 or 3 reels of the same format. One reel can be the exception.
  • 本地文件：直接使用。
  • YouTube 链接：
    yt-dlp -o "W/reel.%(ext)s" "<url>"
    。
  • Instagram 或 TikTok：先尝试 
    yt-dlp
    。如果被拦截（登录墙），且已配置 Treg（
    treg balance
    有响应），则执行 
    treg catalog search "download an Instagram reel video file"
    ，再通过 
    treg catalog get <id>
    查询价格，然后执行 
    treg call <id> --query url=<url>
    并下载其返回的视频 URL。否则，请让用户保存视频并提供文件。
  • 条件允许时，研究同一格式的 2 或 3 条 reel。只有一条 reel 的情况可以作为例外。

2. Measure

2. 测量

Do all three passes. A style copied from the frames alone misses half of it: the sound and the rhythm.
完成全部三遍分析。仅从画面帧复制风格会遗漏一半信息：声音和节奏。

Frames and cuts

画面帧与剪切点

bash
ffmpeg -v error -y -i W/reel.mp4 -vf "fps=2,scale=270:480,tile=8x3:padding=4:color=black" W/sheet-%02d.jpg
ffmpeg -hide_banner -i W/reel.mp4 -vf "scdet=threshold=12" -an -f null - 2>&1 | grep -o "scd.time: [0-9.]*" | cut -d' ' -f2 > W/cuts.txt
ffprobe -v error -show_entries format=duration -of csv=p=0 W/reel.mp4
  • Each sheet holds 24 tiles at 2 per second. Sheet N, tile i (from 0) shows second 12(N-1) + i/2.
  • Seconds per shot = duration / (number of lines in 
    cuts.txt
    + 1).
Read EVERY sheet and write down:
  • Layouts: full camera, split screen (where the seam sits), flat color with text, cut-out person on a color, B-roll, screenshots.
  • Captions, per layout: font feel (condensed, rounded, serif), case, weight, size, where they sit on the body, how a word appears, which word gets emphasised and how.
  • Stickers and images: type, border, size, when they land (on the word that names them?), whether they stack.
  • Hook (first 2 s), CTA (last 3 s), color grade (bright and flat, or contrasty and dark).
Save 6 to 10 key stills to 
video-agent/styles/<name>/
:
bash
ffmpeg -v error -y -ss <seconds> -i W/reel.mp4 -frames:v 1 video-agent/styles/<name>/t<seconds>.jpg
bash
ffmpeg -v error -y -i W/reel.mp4 -vf "fps=2,scale=270:480,tile=8x3:padding=4:color=black" W/sheet-%02d.jpg
ffmpeg -hide_banner -i W/reel.mp4 -vf "scdet=threshold=12" -an -f null - 2>&1 | grep -o "scd.time: [0-9.]*" | cut -d' ' -f2 > W/cuts.txt
ffprobe -v error -show_entries format=duration -of csv=p=0 W/reel.mp4
  • 每张接触表包含 24 个图块，每秒采样 2 帧。第 N 张表中的第 i 个图块（从 0 开始）显示第 12(N-1) + i/2 秒的画面。
  • 每个镜头的秒数 = 时长 /（
    cuts.txt
    中的行数 + 1）。
务必查看每一张接触表，并记录：
  • 布局：全屏镜头、分屏（接缝位置）、纯色背景配文字、人物抠像置于纯色背景、B-roll、屏幕截图。
  • 字幕，按布局分别记录：字体风格（紧凑、圆润、衬线）、大小写、字重、字号、相对于人物身体的位置、单词如何出现，以及哪个词被强调及强调方式。
  • 贴纸和图片：类型、边框、尺寸、出现时机（是否出现在点明它名称的那个词上）、是否叠加。
  • Hook（前 2 秒）、CTA（后 3 秒）、调色（明亮平调，或高对比暗调）。
将 6 到 10 张关键静帧保存到 
video-agent/styles/<name>/
：
bash
ffmpeg -v error -y -ss <seconds> -i W/reel.mp4 -frames:v 1 video-agent/styles/<name>/t<seconds>.jpg

Sound

声音

bash
ffmpeg -v error -y -i W/reel.mp4 -lavfi "showspectrumpic=s=3000x500:legend=0:scale=log:stop=11000" W/spectrum.png
  • The image is 3000 px wide, so a cut at t seconds sits at x = 3000 × t / duration. Read it next to 
    cuts.txt
    .
  • A bright thin vertical stroke high up = a click. Wide and low = a boom. A rising smear = a whoosh. A dark gap across the steady music band = the beat drops out.
  • Zoom on one cut to see its hit: 
    ffmpeg -v error -y -ss <cut - 1> -t 2 -i W/reel.mp4 -lavfi "showspectrumpic=s=1000x500:legend=0:scale=log:stop=11000" W/cut-<n>.png
    .
  • Beat: count the regular low strokes over 10 s on the spectrogram (or tap along while it plays): strokes per 10 s × 6 = BPM.
Music level under the voice (optional, needs 
ELEVENLABS_API_KEY
in 
video-agent/.env
, uses a few credits, say so first):
bash
set -a; . video-agent/.env; set +a
ffmpeg -v error -y -i W/reel.mp4 -vn -ac 1 -ar 44100 W/full.wav
curl -s -X POST https://api.elevenlabs.io/v1/audio-isolation -H "xi-api-key: $ELEVENLABS_API_KEY" -F audio=@W/full.wav -o W/voice.mp3
ffmpeg -v error -y -i W/voice.mp3 -ac 1 -ar 44100 W/voice.wav
for f in full voice; do ffmpeg -v error -i W/$f.wav -af "asetnsamples=882,astats=metadata=1:reset=1,ametadata=print:key=lavfi.astats.Overall.RMS_level:file=-" -f null - | grep -o "RMS_level=.*" | cut -d= -f2 > W/rms-$f.txt; done
paste W/rms-voice.txt W/rms-full.txt | awk '$1<-40{print $2}' | sort -n | awk '{a[NR]=$1}END{print "music while the voice is silent:", a[int(NR/2)+1], "dB over", NR/50, "s"}'
awk '$1>-30' W/rms-voice.txt | sort -n | awk '{a[NR]=$1}END{print "voice while talking:", a[int(NR/2)+1], "dB"}'
  • These commands measure the level every 20 ms. The music is the full mix in the moments the isolated voice is silent.
  • Music under the voice = the voice level minus the music level.
  • Under 1 s of silence (an edit with every pause cut) is too little to trust: judge it on the spectrogram.
  • Never subtract the isolated voice from the mix: it is not in phase with the original, so the result comes out louder than the voice.
  • Without a key, judge the level on the spectrogram.
Write down where the music starts and which event gets which sound: cut, sticker, zoom, impact.
bash
ffmpeg -v error -y -i W/reel.mp4 -lavfi "showspectrumpic=s=3000x500:legend=0:scale=log:stop=11000" W/spectrum.png
  • 图像宽度为 3000 px，因此 t 秒处的剪切点在横轴上的位置为 x = 3000 × t / duration。结合 
    cuts.txt
    阅读频谱图。
  • 位于高处、细而明亮的竖线 = click（点击声）。又宽又低的竖线 = boom（低频冲击声）。向上扩散的拖影 = whoosh（呼啸声）。稳定音乐频带中出现横向暗色缺口 = 节拍短暂消失。
  • 放大某个剪切点以查看其命中音效：
    ffmpeg -v error -y -ss <cut - 1> -t 2 -i W/reel.mp4 -lavfi "showspectrumpic=s=1000x500:legend=0:scale=log:stop=11000" W/cut-<n>.png
    。
  • 节拍：在频谱图上统计 10 秒内规律出现的低位竖线（也可以在播放时跟着打拍子）：每 10 秒的竖线数 × 6 = BPM。
人声下的音乐电平（可选，需要在 
video-agent/.env
中配置 
ELEVENLABS_API_KEY
，会消耗少量 ElevenLabs credits，执行前先告知用户）：
bash
set -a; . video-agent/.env; set +a
ffmpeg -v error -y -i W/reel.mp4 -vn -ac 1 -ar 44100 W/full.wav
curl -s -X POST https://api.elevenlabs.io/v1/audio-isolation -H "xi-api-key: $ELEVENLABS_API_KEY" -F audio=@W/full.wav -o W/voice.mp3
ffmpeg -v error -y -i W/voice.mp3 -ac 1 -ar 44100 W/voice.wav
for f in full voice; do ffmpeg -v error -i W/$f.wav -af "asetnsamples=882,astats=metadata=1:reset=1,ametadata=print:key=lavfi.astats.Overall.RMS_level:file=-" -f null - | grep -o "RMS_level=.*" | cut -d= -f2 > W/rms-$f.txt; done
paste W/rms-voice.txt W/rms-full.txt | awk '$1<-40{print $2}' | sort -n | awk '{a[NR]=$1}END{print "music while the voice is silent:", a[int(NR/2)+1], "dB over", NR/50, "s"}'
awk '$1>-30' W/rms-voice.txt | sort -n | awk '{a[NR]=$1}END{print "voice while talking:", a[int(NR/2)+1], "dB"}'
  • 这些命令每 20 ms 测量一次电平。在分离出的人声处于静音状态的时刻，完整混音反映的就是音乐。
  • 人声下的音乐 = 人声电平减去音乐电平。
  • 静音区间不足 1 秒（剪辑中每次停顿都被剪掉）时，结果不足以作为可靠依据：请结合频谱图判断。
  • 绝不要从混音中减去分离出的人声：它与原始人声并不同相，因此结果会显得比真实人声更响。
  • 没有 key 时，请根据频谱图判断电平。
记录音乐从何处开始，以及每个事件对应哪种声音：剪切、贴纸、变焦、冲击。

Zooms

变焦

On the sheets, measure the face height as a share of the frame height on 10 tiles or so, and list the jumps in face size from one tile to the next:
  • a jump at a cut = a change of framing between two shots
  • a jump inside a shot = a punch-in
  • a slow growth over a shot = a push
Write the range (e.g. face 12 to 25 % of the frame), the punch-ins per 10 s, and whether there is a push. These numbers are the ceiling for your copy.
在接触表上选取大约 10 个图块，测量人脸高度占画面高度的比例，并列出相邻图块之间人脸尺寸的跳变：
  • 剪切点处发生尺寸跳变 = 两个镜头之间的构图或景别发生变化
  • 镜头内部发生尺寸跳变 = punch-in（快速推近）
  • 镜头内缓慢增大 = push（缓慢推进）
记录范围（例如，人脸占画面高度的 12% 至 25%）、每 10 秒的 punch-in 次数，以及是否存在 push。这些数值是仿制时的上限。

3. Write the style

3. 编写风格

video-agent/styles/<name>.md
, in the user's language, with the same sections as 
video-edit
's style.md. Each line gives a value and the measurement behind it:
markdown
undefined
video-agent/styles/<name>.md
，使用用户语言，章节与 video-edit 的 style.md 相同。每一行给出一个值及其背后的测量结果：
markdown
undefined

Style: <name>

Style: <name>

Copied from <link>, measured on <date>. Applied on top of video-edit's style.md: what is not here stays as there.
Copied from <link>, measured on <date>. Applied on top of video-edit's style.md: what is not here stays as there.

Cuts

Cuts

  • hard cut every 1.4 s on average (35 cuts in 50 s); no fade, no transition
  • hard cut every 1.4 s on average (35 cuts in 50 s); no fade, no transition

Framing

Framing

  • face 12 to 25 % of the frame; punch-in 1.1 at most, about every 4 s, held until the next cut; slow push 0.6 %/s
  • face 12 to 25 % of the frame; punch-in 1.1 at most, about every 4 s, held until the next cut; slow push 0.6 %/s

Captions

Captions

  • ...
  • ...

Stickers and images

Stickers and images

  • ...
  • ...

Sound

Sound

  • boom bap beat ~90 BPM from the hook impact, 12 dB under the voice, drops out 0.3 s on punch-ins
  • a dry high click on most cuts (sfx/cut.wav), a pop on each sticker (sfx/pop.wav)
  • boom bap beat ~90 BPM from the hook impact, 12 dB under the voice, drops out 0.3 s on punch-ins
  • a dry high click on most cuts (sfx/cut.wav), a pop on each sticker (sfx/pop.wav)

Grade

Grade

  • ffmpeg: eq=contrast=1.08:saturation=0.9,vignette=PI/5,unsharp=5:5:0.4
  • ffmpeg: eq=contrast=1.08:saturation=0.9,vignette=PI/5,unsharp=5:5:0.4

Left out

Left out

  • the AI video clips: replaced by your own footage or a callout
  • the AI video clips: replaced by your own footage or a callout

How video-edit applies it

How video-edit applies it

  • the components to add to the composition and the props they take

**Sound effects** (in `video-agent/styles/<name>/sfx/`):

- With an ElevenLabs key, generate 2 or 3 takes per sound and keep the one closest to the original on the spectrogram:
  ```bash
  curl -s -X POST https://api.elevenlabs.io/v1/sound-generation -H "xi-api-key: $ELEVENLABS_API_KEY" -H "content-type: application/json" -d '{"text":"single dry short high click, tight transient, no reverb","duration_seconds":0.5}' -o video-agent/styles/<name>/sfx/cut-a.mp3
  • Otherwise, use a royalty-free library.
Stickers:
  1. Generate them with 
    /codex-images
    . Use the user's REAL photos as the face reference, never a generated face. Ask for a flat #00FF00 background, no shadow, no text.
  2. Key the background out to a transparent PNG:
    bash
    ffmpeg -v error -y -i sticker.png -vf "colorkey=0x00FF00:0.3:0.08,despill=type=green" -pix_fmt rgba sticker-cut.png
Logos: every app named on screen shows its real logo, never a letter in a circle.
  • the components to add to the composition and the props they take

**音效**（位于 `video-agent/styles/<name>/sfx/`）：

- 配置 ElevenLabs key 后，为每种音效生成 2 或 3 个版本，并保留在频谱图上最接近原片的一个：
  ```bash
  curl -s -X POST https://api.elevenlabs.io/v1/sound-generation -H "xi-api-key: $ELEVENLABS_API_KEY" -H "content-type: application/json" -d '{"text":"single dry short high click, tight transient, no reverb","duration_seconds":0.5}' -o video-agent/styles/<name>/sfx/cut-a.mp3
  • 否则，使用免版税素材库。
贴纸：
  1. 使用 
    /codex-images
    生成。只能使用用户的真实照片作为人脸参考，绝不能使用生成的人脸。要求使用纯 #00FF00 背景，不要阴影，不要文字。
  2. 抠除背景并输出透明 PNG：
    bash
    ffmpeg -v error -y -i sticker.png -vf "colorkey=0x00FF00:0.3:0.08,despill=type=green" -pix_fmt rgba sticker-cut.png
Logo：屏幕中提及的每个应用都显示其真实 Logo，绝不能只用圆圈里的字母代替。

4. Test it

4. 测试

  1. Pick a 10 to 20 s take of the user from 
    video-agent/takes/
    .
  2. Run 
    /video-edit <take> style <name>
    . It reads the style file and adds what it describes to the composition: stickers on the word that names them, sound effects on the cuts, the grade.
  3. The slug is 
    <take slug>-<name>
    .
  1. 从 
    video-agent/takes/
    中选择一段用户素材，时长为 10 到 20 秒。
  2. 运行 
    /video-edit <take> style <name>
    。该命令会读取风格文件，并将其中描述的内容加入画面合成：贴纸出现在点明其名称的单词上，音效落在剪切点上，并应用调色。
  3. slug 为 
    <take slug>-<name>
    。

5. Compare before showing

5. 展示前比较

Put the original on top and the copy below, at the same seconds:
bash
ffmpeg -v error -y -i W/reel.mp4 -i video-agent/edits/<slug>/final.mp4 -filter_complex "[0:v]fps=1,scale=216:384,trim=end_frame=15,tile=15x1[a];[1:v]fps=1,scale=216:384,trim=end_frame=15,tile=15x1[b];[a][b]vstack" -frames:v 1 W/compare.jpg
Go tile by tile:
  • type size and weight
  • sticker and logo size (they fill the space like in the original)
  • grade
  • no fade where the original cuts hard
  • captions off the mouth
  • nothing upside down
Run the spectrogram on the copy too: the hits must land on the cuts, the beat must sit at the same level under the voice. Measure the face size on its sheets: no more zooms than the original, the face never bigger.
Fix every gap before showing. The user should never be the one to spot it.
将原片放在上方、仿制版本放在下方，在相同秒数处进行对比：
bash
ffmpeg -v error -y -i W/reel.mp4 -i video-agent/edits/<slug>/final.mp4 -filter_complex "[0:v]fps=1,scale=216:384,trim=end_frame=15,tile=15x1[a];[1:v]fps=1,scale=216:384,trim=end_frame=15,tile=15x1[b];[a][b]vstack" -frames:v 1 W/compare.jpg
逐个图块检查：
  • 字号和字重
  • 贴纸和 Logo 的尺寸（应像原片一样填满对应空间）
  • 调色
  • 原片采用硬切的位置不得出现淡入淡出
  • 字幕不得遮挡嘴部
  • 不得出现上下颠倒的内容
对仿制版本也要运行频谱图分析：音效命中必须落在剪切点上，节拍在人声下的电平必须与原片一致。测量仿制版本接触表中的人脸尺寸：变焦次数不得多于原片，人脸也绝不能比原片更大。
展示前修复每一处差距。用户不应该由自己来发现问题。

6. Deliver

6. 交付

Open 
final.mp4
, then tell the user in a few lines:
  • what was measured (seconds per shot, BPM, music level, zooms)
  • what was copied, and what was left out and why
  • where the style lives
From now on, 
/video-edit <take> style <name>
uses it. Each time the user rejects something, write it in the style file. When the lesson is general, add it to references/learnings.md.
打开 
final.mp4
，然后用几行告诉用户：
  • 测量了哪些内容（每个镜头的秒数、BPM、音乐电平、变焦）
  • 复制了哪些内容，以及省略了哪些内容及其原因
  • 风格文件存放在哪里
从现在起，
/video-edit <take> style <name>
会使用该风格。每次用户拒绝某些内容时，都将其写入风格文件。如果经验具有普适性，则添加到 references/learnings.md。