Communitygithub.com

captions

Burn animated captions into a vertical video in one of 7 styles: editorial-highlight, pop-sticker, paper-plane, smoke-exit, explosive-breakup, rolodex-flip, retro-typer. Free starter pack by @cornpop.studio. Trigger when someone types /captions, says 'add captions', 'caption my video', 'subtitles on my reel', names one of the 7 styles, or drops a talking video and asks for captions.

What is captions?

captions is a Cursor agent skill that burn animated captions into a vertical video in one of 7 styles: editorial-highlight, pop-sticker, paper-plane, smoke-exit, explosive-breakup, rolodex-flip, retro-typer. Free starter pack by @cornpop.studio. Trigger when someone types /captions, says 'add captions', 'caption my video', 'subtitles on my reel', names one of the 7 styles, or drops a talking video and asks for captions.

Works with~Claude Code~Codex CLI✓Cursor
npx skills add https://github.com/shubhamseth29/claude-skills/tree/HEAD/captions

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

/captions: 7 caption styles

Turns a talking video into the same video with animated captions burned in. Words are timed to the voice, one key word per line gets the highlight colour, and the original video and audio stay untouched (captions are laid on top).

The 7 styles

Type thisLook
editorial-highlightMagazine serif, key word on a deep-red paper strip, small page number above the line
pop-stickerColour blocks with black outlines and hard shadows, little stickers pop around them, key words purple with a star
paper-planeA paper plane in the highlight colour flies across and pulls the line in behind it
smoke-exitChunky sans words; when the line ends it dissolves into smoke, the key word smokes in its own colour
explosive-breakupBig condensed caps; at the end of the line every letter blasts outward, key word in sparks
rolodex-flipThe line builds word by word, each new word flips down like a rolodex card
retro-typerTypewriter letters typed in time with the voice, blinking block cursor (option: hazy box)

If the user gives no style, show this table and ask which one (suggest pop-sticker).

Setup (first time only)

Run inside this skill folder. Check first, install only what's missing:

  • ffmpeg and ffprobe (Mac: brew install ffmpeg, Windows: winget install ffmpeg)
  • Node.js 18+ and Google Chrome (or Edge/Chromium). Then npm install in this folder (small: it uses the Chrome already on the computer).
  • Python 3. scripts/words.py makes its own .venv here and installs faster-whisper on first use.

Steps

  1. Words. python3 scripts/words.py <video> writes <video>.words.json: [{"w":"Hello","s":0.21,"e":0.48}, ...]. Skip if the user already has one (/captions words <video> = only do this step).
  2. Tidy the words (edit the JSON, keep the timings):
    • Fix misheard words, names and brand spellings. Ask the user if unsure.
    • Mark one key word per line with "k": true: the word that carries the point (a result, number, name or the surprising word). Not every line needs one.
    • Mark line ends with "br": true so each line is 2 to 4 words and under ~20 letters, breaking where the speaker naturally pauses. Once any br exists, lines break only at br, punctuation and long pauses.
    • Write symbols the way people read them on screen: "slash" → "/", "percent" → "%" when it's part of a term.
  3. Check frames before the full render. node scripts/render.js <video> <words.json> <style> --still 1.5 --still 4 --still 8 (pick moments mid-line). Look at the PNGs: captions readable, not over the face or the app's own UI. Too high or low? Use --y (64 = default, lower number = higher up). Too big? --size 0.85.
  4. Render. node scripts/render.js <video> <words.json> <style> [--hl #ff7a59] [--y 64] [--size 1] [--box] → <video>_<style>.mp4 next to the original. About 3 minutes for a 60s reel.
  5. Tell the user where the file is. For a live look at all 7 styles on their own video, open index.html in Chrome and load the video and the words file.

Options

FlagWhat it does
--hl <#hex>Highlight colour for key words. Presets: yellow #ffd23f (default), coral #ff7a59, sky #7cc4ff, mint #9ff0b8
--y <0-100>Caption height, % from the top. 64 sits under the chin on a talking head
--size <n>Caption size, 1 = normal
--boxRetro Typer only: soft hazy box behind the text
--out <file>Output path
--still <s>Check frame at that second instead of a full render (repeatable)

Notes

  • HDR iPhone footage can look washed out after rendering. Export it as SDR first, or set the iPhone to Settings > Camera > Formats > Most Compatible.
  • Captions always sit on top of the video. This is the starter pack: words behind the speaker, glass and wall-text styles are not included.
  • Fonts load from Google Fonts, so the render needs an internet connection.

Related Skills