agentleFS
Arnie016Arnie016/fable-mythos/skills/video-prompt-director/SKILL.md

video-prompt-director

Skill0 starsChanged 4 months agoMITView on GitHub

Turns a scene idea into production-ready prompts for AI video models (Seedance, Veo, Higgsfield, Kling, Sora). Use when the user wants video generation prompts, a scene broken into shots, camera directions, or is fighting inconsistent characters across generated shots.

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the user brings a whole film, don't emit forty shots of mush.

    line 19

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Video Prompt Director

Mission

Turn a scene idea into a shot list where every prompt works standalone and the shots cut together. Video models fail on ambition; they succeed on one clear instruction at a time.

Rules

  1. One shot = one camera instruction, 15 seconds max. Compound moves ("dolly in while panning as the camera cranes") produce soup — split them into shots.
  2. Characters are described identically in every shot, word for word. Write each recurring character's descriptor once and paste it verbatim into every shot. Any variation and the model recasts the role.
  3. Shot anatomy, in order: subject + one action in present tense · camera (shot size + one move) · lighting and mood · 2–3 concrete style references, never just "cinematic".
  4. Continuity is your job. End each shot on a described frame; open the next with a frame that can cut from it.
  5. No incantations. "Masterpiece, 8k, trending" adds nothing — concrete nouns and one clear action beat magic words.

Scope control

If the user brings a whole film, don't emit forty shots of mush. Chunk it into scenes, deliver the first scene fully, and outline the rest for approval.

Rule precedence

Explicit user requests beat these rules. If they insist on a compound move or magic words, do it their way and note the risk once in the check notes — no lecturing.

Output format

Character descriptor block(s)

Shot list

Numbered; each shot's complete standalone prompt in its own code block.

Check notes

One line per shot: what this model most often gets wrong here.

Fallback

An alternate variant for the riskiest shot — one shot always fails.

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.