agentleFS
BenitoowBenitoow/cinema-skills/skills/cut-list/SKILL.md

cut-list

Skill0 starsChanged 41 days agoMITView on GitHub

Turn a transcript, footage log or beat sheet into an edit plan (cut list) with in/out points, durations, transitions and pacing notes, with an optional EDL. Use when the user is planning a rough cut, tightening an edit, hitting a target runtime, or building a vertical short-form edit.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask only for what is missing:

    line 16
  2. Distinctive:

    Do the runtime math: sum durations and compare to target.

    line 26
  3. Distinctive:

    Start with a one-line edit concept and the runtime math (current total, target, delta).

    line 34
  4. Very specific:

    Use HH:MM:SS:FF timecode at the stated frame rate.

    line 41
  5. Distinctive:

    Only if the user asks, or if all in/out points are real timecodes.

    line 50
  6. Distinctive:

    Always tell the user to import the EDL into a test project and check the first events before trusting the rest, since reel names and …

    line 60
  7. Distinctive:

    Never invent footage, dialogue or timecodes.

    line 64

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Cut List

Produce an edit plan an editor can follow in Premiere, DaVinci Resolve or any NLE.

Inputs to collect

Ask only for what is missing:

  1. Source material: transcript with timecodes, footage log, or a beat sheet (required)
  2. Target runtime and platform (e.g. 60 s vertical, 5 min YouTube, 90 s trailer)
  3. Frame rate of the project (needed for any timecode math and the EDL)
  4. Tone and rhythm references

Process

  1. Define the structure first: hook, build, payoff (adapt to format). For short-form vertical, the hook must land in the first 1-2 seconds.
  2. Do the runtime math: sum durations and compare to target. If over, say what to cut and why, and propose the first cuts rather than leaving it vague.
  3. Choose cuts by purpose: each clip must advance information, emotion or rhythm. Flag clips that do none.
  4. Plan rhythm: alternate long and short, put the strongest moment at the climax, avoid three similar-length shots in a row unless intentional.
  5. Specify transitions only where they have a job (match cut, J/L cut for dialogue, impact cut on a sound hit). Default to straight cuts.
  6. Note audio: where music hits land, dialogue overlaps, room tone needs.

Output format

Start with a one-line edit concept and the runtime math (current total, target, delta).

Cut table

#Source / clipInOutDurationPurposeTransitionAudio / notes

Use HH:MM:SS:FF timecode at the stated frame rate. If the source has no timecodes, use clip names and estimated durations and say so.

Pacing notes

Three to five bullets: where the edit speeds up, where it breathes, where it risks dragging.

Trim candidates (if over runtime)

Ordered list of what to cut first, with the cost of each cut.

Optional: EDL (CMX3600)

Only if the user asks, or if all in/out points are real timecodes. Format:

TITLE: PROJECT_NAME
FCM: NON-DROP FRAME

001  CLIP01   V     C        01:00:00:00 01:00:02:12 01:00:00:00 01:00:02:12
* FROM CLIP NAME: clip_name.mov

Always tell the user to import the EDL into a test project and check the first events before trusting the rest, since reel names and drop-frame settings vary by NLE.

Rules

  • Never invent footage, dialogue or timecodes. If something is missing, ask or mark it as an estimate.
  • Be explicit about what is a creative suggestion and what follows from the numbers.
  • For vertical edits: respect safe zones for captions and keep key action centered.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.