Communitygithub.com

long-form

Edits a whole talking-head video (minutes to an hour, horizontal 16:9 for YouTube or vertical 9:16) end to end. Shortens pauses and optionally cuts um/uh, hides the jump cuts with alternating punch-in zooms, burns in clean captions with key words on an accent pill, adds chapter cards, and splices in designed "moments" made by the other skills (explainer, split-screen, behind-the-person, ranking-list, storytelling) at exactly the right frames. Also writes an .srt and a YouTube chapter list. Use when the user runs /long-form or asks to edit a full video, a podcast-style talking head, a YouTube video, a course lesson or any clip longer than about a minute.

What is long-form?

long-form is a Claude Code agent skill that edits a whole talking-head video (minutes to an hour, horizontal 16:9 for YouTube or vertical 9:16) end to end. Shortens pauses and optionally cuts um/uh, hides the jump cuts with alternating punch-in zooms, burns in clean captions with key words on an accent pill, adds chapter cards, and splices in designed "moments" made by the other skills (explainer, split-screen, behind-the-person, ranking-list, storytelling) at exactly the right frames. Also writes an .srt and a YouTube chapter list. Use when the user runs /long-form or asks to edit a full video, a podcast-style talking head, a YouTube video, a course lesson or any clip longer than about a minute.

Works with✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/alisolanki/alis-claude-editing-skills/tree/HEAD/skills/long-form

Ask in your favorite AI

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

Documentation

/long-form

 source ──tighten──▶ tight take ──build──▶ edited.mp4  + .srt + .chapters.txt + .sheet.jpg
                     (pauses cut,          ├ plain stretches: punch-ins on the cuts, captions, chapter cards
                      words remapped)      └ moments: explainer / split-screen / ... rendered and spliced in

First use

This skill's folder is the "Base directory" Claude Code shows when it loads it.

SKILL_DIR="<base directory of this skill>"   # the path Claude Code printed as "Base directory for this skill"
KIT=$(python3 -c 'import os,sys;print(os.path.realpath(os.path.join(sys.argv[1],"..","..","kit")))' "$SKILL_DIR")
PY="$KIT/.venv/bin/python"; [ -x "$PY" ] || bash "$KIT/setup.sh" --cutout

GROQ_API_KEY must be set to transcribe (long videos go up in 10-minute chunks). Needs ffmpeg and Node.

Steps

  1. Probe. "$PY" "$KIT/reel.py" probe <video>: size, length, and the format auto will pick (wider than tall = horizontal 1920x1080, otherwise vertical 1080x1920). Ask only if the user wants the other shape (a horizontal source can be cut to vertical, which crops the centre).
  2. Tighten (recommended for raw recordings, skip for already-edited footage): "$PY" "$KIT/longform.py" tighten <video> [--max-gap 0.45] [--pad 0.12] [--cut-fillers] It transcribes, keeps every word, shortens each pause longer than --max-gap to about 2 × --pad, and writes <video>.tight.mp4 plus <video>.tight.transcript.json (words on the new timeline, and cuts: where each join landed). Use the tight file from here on. --cut-fillers also removes um/uh/erm.
  3. Read it. "$PY" "$KIT/reel.py" words <video> prints one sentence per line with times (on the tight timeline if you tightened). For long videos read it in parts with --start/--end. Note:
    • the chapters: where the topic turns (4 to 10 for a 10 to 20 minute video), each with a 2 to 5 word title;
    • 2 to 6 moments: 4 to 10 second stretches that make one concrete, visual point (a comparison, a step, a number, a ranking, a small story). Space them out; most of the video stays the plain take.
  4. Framing. "$PY" "$KIT/reel.py" frame <video> <t> frame.jpg and look: note the face centre (for face, used by the punch-ins) and the eye line and face x for any moment that needs them (eye_y, face_x, video_top...).
  5. Spec. Write <video>.long-form.json next to the video (below). Paths are relative to the spec file.
  6. Build. "$PY" "$SKILL_DIR/build.py" <spec.json>. Moments render first (about 20 to 40 s each, cached), then the timeline is encoded in segments in parallel. A 15 minute 1080p video takes roughly as long as one or two ffmpeg passes over it.
  7. Check <out>.sheet.jpg (12 frames, red = covered by the player or the reel UI), then spot-check each moment's join and one chapter card in the video itself. Fix the spec and rebuild; moments that didn't change are reused.
  8. Hand over the mp4, the .srt (upload it to YouTube for searchable captions, even if they are burned in), and the .chapters.txt (paste into the description).

Spec

{
  "video": "episode.tight.mp4",
  "format": "auto",
  "out": "episode.edited.mp4",
  "face": [880, 400],
  "punch_ins": {"every": "cut", "scale": 1.12, "min_hold": 2.5},
  "zooms": [{"start": 312.4, "end": 318.0, "scale": 1.25}],
  "captions": {"keys": ["carousel", "viral"], "karaoke": false},
  "chapters": [
    {"at": 0, "title": "Why carousels win"},
    {"at": "the second thing", "title": "Finding a viral post"}
  ],
  "moments": [
    {"skill": "explainer", "start": 61.2, "end": 67.0,
     "title": "Steal what *works*", "eye_y": 400, "face_x": 880,
     "visual": {"type": "list", "items": [{"text": "Find a *viral* post", "at": "find"}, {"text": "Recreate it", "at": "recreate"}]}},
    {"skill": "split-screen", "start": 140.0, "end": 147.5, "face_x": 880, "zoom": 1.2,
     "badge": "Step 2", "headline": "Pick *one*", "visual": {"type": "image", "src": "screens/app.png"}}
  ],
  "loudness": -14
}
  • video: the tight file, or the raw one. start/end (optional) use only part of it.
  • format: auto, horizontal or vertical.
  • face: [x, y] of the face on the canvas, the centre of every zoom. Default: centre, a little above middle.
  • punch_ins: alternate between the plain shot and scale (1.08 to 1.18) at every "cut" (needs a tightened transcript; it hides the jump cuts), every "sentence", or every N seconds (a number). min_hold (s) keeps zooms from flickering. Leave it out for no punch-ins.
  • zooms: explicit holds at a scale, on top of the punch-ins. Use sparingly, for an emphatic line.
  • captions: burned-in house captions: Inter ExtraBold, white with a soft shadow, keys on an accent pill. karaoke: true dims words until they are said. y and size move and resize them. false turns burned captions off (the .srt is still written). Inside moments the moment's own captions take over.
  • chapters: at is seconds or a spoken word ("pricing", "pricing#2", "pricing-0.5"). Each gets a card (an accent number tile and the title) for about 3 s; "card": false on one, or "chapter_cards": false for all, keeps only the .chapters.txt entry. A first chapter that isn't at 0 gets an "Intro" line (intro_title).
  • moments: skill + start/end (seconds, or words) + that skill's own fields, exactly as its SKILL.md describes (read it before writing one). Format, video and transcript are filled in for you. Moments cannot overlap. A cutout skill (explainer, behind-the-person) adds about 0.1 s per frame.
  • loudness: normalise the final mix to this LUFS (-14 suits YouTube). Leave it out to keep the voice as recorded.
  • keep_work: true keeps the encoded segments in .work/.

Taste

  • The take is the show. Captions and punch-ins carry the whole video; moments are seasoning (one every 1 to 3 minutes at most).
  • Every moment illustrates the exact sentence under it, landing on the words that name it, and uses the user's real images, screens and numbers. Never invent results.
  • Chapter titles are short and concrete ("Pricing", "The 3-step setup"), never clickbait.
  • Horizontal: keep captions and cards inside the safe area (the sheet shows it); YouTube's progress bar covers the bottom 120 px when paused.
  • Vertical long-form uses the same zones as reels; keep captions around y 1380.

Individual skills in this repo

This repo contains 2 individual skills — each has its own dedicated page.

Related Skills