Communitygithub.com

reel-edit

Edit a recorded face-cam reel (Instagram Reels / Shorts / TikTok, 1080x1920) in an editorial style - HDR->SDR, grade, dead-air cut, word-synced Instrument Serif kinetic type, real-screenshot cutaways, SFX, render. Use when the user drops new clips/.MOV files to edit, says "edit reel N", "edit this reel", "make the video", or wants a reel rendered from footage and a script.

What is reel-edit?

reel-edit is a Claude Code agent skill that edit a recorded face-cam reel (Instagram Reels / Shorts / TikTok, 1080x1920) in an editorial style - HDR->SDR, grade, dead-air cut, word-synced Instrument Serif kinetic type, real-screenshot cutaways, SFX, render. Use when the user drops new clips/.MOV files to edit, says "edit reel N", "edit this reel", "make the video", or wants a reel rendered from footage and a script.

Works with✓Claude Code✓Codex CLI~Cursor✓Gemini CLI
npx skills add https://github.com/Aadi1659/reel-edit-skill/tree/HEAD/skills/reel-edit

Ask in your favorite AI

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

Documentation

Reel edit (editorial style, cheap path)

A repeatable face-cam reel pipeline. Do not rebuild anything the script or template already does.

R=~/.claude/skills/reel-edit/scripts/reel.py
P=./reels/reel-NN                              # one project per reel

Token rules (why this skill exists)

  • Do NOT load the hyperframes / hyperframes-cli / media-use skills unless something here fails or the user wants a look that isn't covered below. The template already follows the render contract.
  • Never cat the big reference files. Copy a pattern from ~/.claude/skills/reel-edit/examples/<scene>.html only when you need that exact scene (see list below), and read just that one file.
  • Look at frames with reel.py snap (a 270 px-wide strip), never full 1080x1920 PNGs, never by rendering.
  • Render the full reel once at the end. For music, give the user mp3 previews (beds), not renders.
  • Use the transcript only for timing. Its spelling is wrong for Hinglish (gunna, Chatjee); on-screen words come from the script.

Pipeline

python3 $R new   $P                                  # template: index.html, type/card/statement scenes, fonts; downloads logos + sfx
python3 $R prep  $P "/path/IMG_1.MOV" [more clips]   # HLG->SDR (swift), 1080x1920 30fps, cinematic grade; voice stays RAW
python3 ~/.claude/skills/reel-edit/scripts/recut.py $P --speed 1.05 --maxtail 0.7   # gentle cut: whole sentences (recommended)
python3 $R words $P                                  # Whisper on the CUT voice, onset-snapped -> edit/words.json (prints phrases)
python3 ~/.claude/skills/reel-edit/scripts/logos.py $P gemini="Google Gemini|Google LLC" site=https://example.com   # real logos

python3 $R cut $P is the older tight cut (removes micro pauses, 1.12x). It is faster but can clip soft word endings; prefer recut.py unless the speaker wants a very punchy rhythm.

  • Pass raw clips from wherever they are. Several clips = joined in the order given.
  • Words. Whisper usually returns good word times (use them as they are). For mixed-language speech such as Hinglish it sometimes translates to English instead; words then prints a WARNING. In that case write what was actually said (e.g. Roman Hinglish, with punctuation at each phrase break; the English shows you what was said) to edit/script.txt and run words $P --script $P/edit/script.txt. That aligns the script to the real pauses and onsets, accurate to about 0.1 s on most phrases but up to about 0.6 s on rapid lists ("caption, reply, DMs"). Snap those moments and nudge data-t by hand.
  • Flubbed take / repeated line: read the words output, then cut $P --drop 3.1-5.4 with the times as printed (drops add up across runs; --reset clears them). Then rerun words.
  • Retakes hide inside one clip. People repeat a line without stopping the recording, and Whisper often merges or skips the repeat. Slice the CUT assets/voice.wav into 1-2 s bursts and transcribe each one (-l en --prompt "<script>" keeps Hinglish in Roman script), then drop the weaker say of each repeated line.
  • cut options: --speed (1.12 default; 1.0 for a slow talker), --th (speech dB), --gap (pauses shorter than this stay inside a phrase, 0.14), --pre / --post (kept around each phrase, 0.05 / 0.07), --dip (micro-pause cut, dB above --th, default 0), --tail (hold after last word).
  • The auto threshold is max(-30.5, noise floor + 4, speech level - 10), so room noise in the pauses is not mistaken for speech. After cut, look at the energy envelope: any stretch longer than ~0.15 s that sits well below speech level is a pause the viewer will feel. Tighten with --th rather than a higher --speed.
  • After cut, every element with data-full gets the reel length, and the jump-cut punch toggles are written between // CUTS:BEGIN/END.

Build the edit (the creative part)

Work from edit/words.json + the script/beat sheet.

  1. type.html - one .grp per phrase while the face is on screen. Small lowercase Inter line + one huge Instrument Serif italic keyword (170-240 px; shorter word = bigger). Each .w gets data-t = its word start. Group start = first word, group end = next group's start. Bottom of text at y 1290. g1 is the cover frame: visible at frame 0 with no reveal. Last group id="gLast" (no fade, loops). Extras already styled: .acc (coral word), .badge (white logo tile), .pair (logo × logo), .strike (coral strike-through).
  2. Cutaways (graphics over the face, 1.5-6 s each, while a proof is being said). Host div in index.html with root-timeline start/duration; inside, times are LOCAL. Duplicate a scene file + host for each use and give each a unique data-composition-id, ids and timeline key.
    • card.html - paper #f3efe8, REAL screenshot in a white card, 3D tilt in, push-in, coral ellipse draws around the proof.
    • statement.html - black #0e0e0e, real logo, 2-3 stacked serif words, coral tag line.
    • Patterns in examples/: viral.html IG reel grid → ranking row + counter rolling to 157x · hooks.html three hook cards dealt + score bar to 100 · skills.html grid of skill tiles · human.html robotic text crossed out · github.html = card · trio.html = statement · type.html incl. the typed "Add a comment… SKILL" box.
  3. Face motion in index.html: drift(t, d, 1.0, 1.06) on every face stretch between cutaways; punch(t, 1.06, 1.16) on 1-2 key words; flash + shutter for "screenshot".
  4. SFX (in assets/sfx): whoosh 0.22 at each cutaway entry (−0.05 s), pop 0.35-0.4 on badges/cards, tick 0.45 on counters, sfx_003 0.45 on clicks/cards, shutter 0.6 on flash. Same track index can't overlap - alternate 7-10.

Editing rules (learned from real redos)

These came from edits a creator sent back. Following them avoids the most common "redo this" notes.

Cut

  1. Never cut a sentence short. Keep soft endings ("-s", trailing vowels) and the pauses inside a sentence; only remove dead air between sentences and the retakes. Speed 1.05 at most. recut.py does this; --add / --cut / --drop take SOURCE seconds (one comma list per flag).
  2. Before building, transcribe every kept span on its own and check its last word. If a take trails off, use another take.
  3. Fade every join (40 ms in / 80 ms out). Extend an end only while the voice is still going; stop at real silence (--maxtail does this) and never run into the next sound.
  4. If something was playing in the room while recording (a reference video, music), keep the speech threshold above its level so fragments of it never survive the cut.
  5. Long Whisper runs on mixed-language speech can loop on one line. Transcribe 25 s chunks or each span separately.

Look 6. Keep the voice raw (gain + limiter only) unless the speaker asks for processing. 7. Real logos only: the product's official app icon (logos.py uses the App Store's artwork) or the product site's own icon/vector logo. Never a placeholder letter tile, never the parent company's logo for a product, never an upscaled 48 px favicon. Look at assets/logos/app/_sheet.png before building. 8. When a name is spoken, its logo and name pop in on that word. For lists, time names from per-sentence transcripts mapped onto the cut; a whole-reel alignment drifts by about a second. 9. Don't put small joiner words ("and", "or") between names in a big header: header = number + category, names under the logos. 10. Only web fonts render reliably: Inter and Instrument Serif ship in assets/fonts. System fonts and Apple Color Emoji fail check; draw emoji with Twemoji SVGs. 11. Every claim on screen must be true on the day you post. Put limits on screen ("50 free credits/day"); if a price can't be confirmed, don't call it free.

Optional layout: face-down window

For proof-heavy reels, keep the hook full-frame, then slide the face video down into a rounded window in the lower half and put titles + proof cards above it. A cut-out of the speaker on top lets the hair or hands break over the window edge (optional: many creators prefer the plain video in the window, which is faster and keeps their real background; then hide the cut-out layer). scripts/lib_v2.py has the shared pieces for this layout: window move, header type groups, word reveals, SFX tracks.

  • Cut-out: npx --yes [email protected] remove-background assets/face.mp4 -o assets/face_cut.webm --quality best (runs locally, roughly 6 min for 14 s on Apple silicon). Give the cut-out clip data-start="0" data-media-start="0" so it decodes in sync.
  • Layers, bottom to top: dark stage background < face window (base video inside a clip-path: inset(...) round ... wrapper) < proof cards < cut-out < captions. Two face groups (window, cut-out) get the same slide/scale tweens; keep the cut-out hidden while the face is full-frame and fade its top ~80 source px with a mask-image gradient so a head cropped by the camera does not show a hard edge.
  • Close-up footage needs the window small (scale ~0.6, centred, top of the window around y 870) so the whole head and shoulders fit. Don't punch-zoom inside the window; jump-cut punches only while full-frame.
  • Captions become titles above the cards (bottom of text ~y 410) while the face is down, and go back to y 1290 when full-frame.

Real assets only

  • Logos: scripts/logos.py first (official app icons / the product site's own logo). For simple monochrome marks you can also use npx --yes [email protected] media-use resolve --type logo --entity "<Name>" (thesvg). If it returns a low-res .ico (ChatGPT did), use simple-icons: https://cdn.jsdelivr.net/npm/[email protected]/icons/<slug>.svg. new downloads claude/instagram/openai/github from simple-icons.
  • Web pages (GitHub, docs, product sites): screenshot with the cached chrome-headless-shell at deviceScaleFactor 2.7 → assets/shots/. Delete the placeholder shot.png.
  • Instagram thumbnails / view counts: read from the logged-in built-in browser. Blur other creators' handles.
  • Never invent numbers on screen; every stat must match a real screenshot.

Check, look, render

cd $P && npx --yes [email protected] check          # must pass; fix overlap/occlusion errors it lists
python3 $R snap $P 0.5,4.2,7.9,13.4                  # strip of key moments -> edit/snap.jpg (Read it)
python3 $R render $P reel-NN                         # -> renders/reel-NN.mp4 (SDR, 30 fps, high)

Snap the cover frame, one moment per cutaway, and the end. Fix, re-snap only what changed.

Music & delivery

  • Default delivery: voice + SFX only (music line commented out). Add a trending track in the Instagram app when posting.
  • If they want a baked bed: upbeat lo-fi / chill tech. Use tracks you have the rights to (CC0 / CC BY). python3 $R beds $P track1.mp3 track2.mp3 ... → mp3 previews to pick from; then python3 $R music $P <track> [--start S] → assets/music.wav (ducked under voice), uncomment the <audio id="music"> line, and put the CC BY credit in the caption.

Gotchas

  • iPhone clips are HLG HDR: prep tone-maps them; if a render comes out HDR/washed, the face file lost its bt709 tags.
  • Voice: prep reads the audio straight from the original clip and keeps it raw; the cut levels it to -14 LUFS with plain gain + a limiter. If a speaker wants a brighter sound, add EQ yourself and let them approve it by ear first.
  • A GSAP fromTo placed later on an element that is visible earlier needs immediateRender: false, or its from-state shows from frame 0.
  • Inter and Instrument Serif load from assets/fonts (each composition declares its own @font-face); never rely on system fonts.
  • Every timed element needs class="clip"; a scene's timeline must be registered as window.__timelines["<composition-id>"].
  • Text safe zone: y 230-1440, keep the right 230 px clear of key text (IG buttons).

Related Skills