Length follows the material: cut stammers and repeats, not thoughts
The decision rule for how long a film should be. A target length makes you stretch a thin day or chop a full one; the material decides, and the checklist says what may be removed.
LENGTH, the decision checklist
1. Do not set a target length before reading the day as text. Set it after: how many scenes are there, and how long are they whole?
2. Allowed cuts: stammers, restarts, repeated sentences, filler at the ends of lines, dead air longer than {1.5} s where nothing happens, the second take of the same thing.
3. Not allowed: a thought cut in the middle, a lead-in removed to make a line land faster, a reaction trimmed to save a second, a scene removed because the film is 'already long'.
4. If the film is longer than you wanted: remove whole scenes, lowest stakes first, and keep the promise-payoff pairs. Never shave 10 percent off every scene.
5. If it is shorter: it is shorter. Do not add a montage of leftovers, do not slow down the cutaways, do not repeat the cold open at the end.
6. The test: does any line in the cut make less sense than it did raw? If yes, you cut a thought. In Claude Code, paste the prompt as a message, or run /video-edit which does this end to end.
Steps
- Read the day as one text file and count the scenes worth keeping whole. That count times their natural length is the first estimate; it is usually right.
- Apply the allowed cuts only, render, watch on a phone. Then decide whether to drop whole scenes, never whether to tighten all of them.
- If a platform needs a shorter version, cut a separate one from the finished film (a trailer); do not shorten the film.
Tips
- The urge to tighten comes from watching the raw footage ten times. A first viewer has seen it zero times and needs the lead-ins you are bored of.
- A 36-minute film and a 90-second trailer from the same day are two files from one master. Each has the length its job needs.
| works with | Claude Code: Runs as a skill or a prompt in the terminal; can read your files and write the result. · CapCut / any editor: A manual recipe for any editor. · By hand: No tool needed: a checklist or a technique. |
| skill | npx skills add fortunto2/solo-factory/video-edit · source |
| cost | Free. No API, no key. |
| status | Unverified: written from the technique, not yet run end to end by us. |
| license | CC BY 4.0 for the text here; skills are MIT. |
| updated | 2026-11-01 |
| for agents | length-follows-the-material.md |
Related
Scenes, not best phrases: keep the lead-in, the talk and the reaction
Why a reel of good lines confuses everyone who was not there, and the checklist for keeping a scene whole: the lead-in, the talk, the reaction, with filler trimmed only at the ends.
Take something from every clip, and list the ones you cut with a reason
A rule for cutting someone else's footage, or your own from a year ago: each clip was filmed because it mattered, so each gets a chance, and the rejects get a written reason the person can argue with.
The cutaway rule: what is said, same place and time, never over moving lips
Three constraints for every cutaway in a talking film, and the agent prompt that applies them to a transcript. Kills what viewers read as broken: a picture from elsewhere, a face out of sync.
The critic pass: repeats and sagging scenes first, mid-word joins second
A two-pass review prompt for a subagent or a second session: pass one on structure (repeats, sagging scenes), pass two on joins (mid-word cuts, audio seams). One read finds one kind of problem.
The day as one text file: an agent reads the speech and proposes the story
The step before any timeline: the day's speech in shooting order, numbered by clip and sentence, read by an agent like a scriptwriter. It proposes story, scenes, hook and cutaways; you argue in text.
Cold open, then hook: 8-10 s of best frames, hand-picked from a contact sheet
The opening that holds a viewer on real footage: 8-10 s of the strongest frames with no speech, then one line with a twist. What to look for on the sheet, and why the automatic pick is wrong.