agentleFS
PicsArtPicsArt/gen-ai-skills/skills/film-animatic/SKILL.md

film-animatic

Skill7 starsChanged 21 days agoMITView on GitHub

Draft a film or drama episode as a voiced storyboard animatic before any video is bought, with a still per shot, app screens built as scenes, every line voiced at its shot's time, cut with captions and watched until the user says yes. Use when a film's story and shots are worked on stills and sound first.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before a panel is bought, every shot card carries what film-story-writing's breakdown asks for, with two fields the animatic depends on: …

    line 20
  2. Distinctive:

    Continuity against the master: Look at each panel beside its scene picture before it goes on a board: the same faces and wardrobe as the …

    line 44
  3. Distinctive:

    Every line is voiced as the voice-over-generation skill says, but in each person's own locked voice (the cast's saved voice notes), one …

    line 56
  4. Very specific:

    Run animatic_plan.py again with each line's probed sec: it re-times every shot so the line fits, and gives each line its start in the …

    line 62
  5. Distinctive:

    every voice line an audio layer at its planned start, the scene's bed under it, each effect on its action.

    line 74
  6. Very specific:

    A cold watch first: Run quality-review's cold watch on the animatic against the film's viewer track, with the cast's voice lines as its …

    line 89

≈ “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

Film animatic

The animatic is the film before video: one picture per shot, the real voices at the shot's timing, cut together and watched. Stills and sound are cheap and video is not, so the story and the cinematics are settled here, and the user's yes to the animatic is what opens shooting. A first paid video is never where anyone first sees the movement or hears a voice.

The use case owns the gates; this skill owns the method. Every paid call below is a SPEND as picsart-video-rules says, quoted with picsart_preflight and bought on a yes (or a stated spend limit that covers it). Building, checking, the editor and the export are free.

1. Cards that can be drawn

Before a panel is bought, every shot card carries what film-story-writing's breakdown asks for, with two fields the animatic depends on: the mode (the camera's relation: lens, observed, point of view or voice-over) and the eyeline (who or what the person on screen looks at or speaks to). One action per shot, one feeling per face, one peak. Why someone decides is not a card field: it is a must-know in the film's viewer track, and the cold watch tests whether the picture gives it.

From this skill's folder, run python3 scripts/animatic_plan.py <file> on the cards (its header has the input). It fails a card with no mode or eyeline, a change of mode the picture does not show, and a film without exactly one peak, and warns an opening shorter than 1.5 s. Fix an error on the card before any picture; a fix that changes what happens is a story note, answered as film-story-writing says. A clean plan says the cards are complete, never that a viewer will follow them.

2. Panels

One panel per shot, at the film's frame:

  • Each scene's opening panel is its scene picture, made as film-shot-generation says. Every other shot gets a still compiled from its card with picsart_film_compile_prompt (kind: "still"), with the present people's locked views and the scene picture as references, checked as the compiler's check says, and sent verbatim to picsart_generate.
  • One quote for every panel of the film or episode, and one batch on the yes (at most 10 a call), filed in the project's Assets folder before you look at them.
  • Continuity against the master. Look at each panel beside its scene picture before it goes on a board: the same faces and wardrobe as the locked views, the same light and set, the eyeline and screen direction the card says. Put them on picsart_asset_approve, 12 tiles a board, with "continuity with the scene picture" as its judge. A changed panel is its own SPEND.
  • A real app's screen is built, never generated. A phone or a computer screen in a shot is a scene layer built from the user's own screenshots or recording (stills with picsart_media_video_stills), laid into the panel's screen area, one state per beat. A generated picture of an interface is not used, and a screen the user has not supplied is asked for, not invented.

3. Sound

Every line is voiced as the voice-over-generation skill says, but in each person's own locked voice (the cast's saved voice notes), one line per clip. Ambience is one bed per scene, and an effect goes where a card's action makes a sound (a tap, a shutter, a door). Quote the voices, the beds and the effects as one batch, then probe every voice line's real length with picsart_media_probe. A sound the user supplies is used as it came.

Run animatic_plan.py again with each line's probed sec: it re-times every shot so the line fits, and gives each line its start in the animatic. A line's real length moves its still, never its words.

4. The animatic scene

Build it as scene-building-basics says, from the plan's timeline:

  • each panel an image layer for its shot's seconds, hard cuts between shots;
  • a move only where the card's camera moves (a slow push-in on a push-in card), eased in and out; a static card stays still. Never add a move to pass a motion check;
  • a code-built screen as its own layer over its panel, changing state on its beat;
  • every voice line an audio layer at its planned start, the scene's bed under it, each effect on its action;
  • the captions and on-screen text in the house style the user gave, otherwise as the spoken-captions skill says. A caption carries only what is said: never a speaker's name the viewer has not heard, a card's id or a stage direction. The viewer reads them as the film.

Then picsart_scene_validate, and fix every error. From quality-review's folder run python3 scripts/cut_check.py --slides <file> on it, as quality-review says: the joins, overlays and screens are checked, and the motion rules wait for the cut. Look at picsart_scene_contact_sheet with times at the middle of each shot (8 at most per sheet).

Without code execution, time the shots by hand the same way and say the scripts were not run.

5. Review as watched

  • A cold watch first. Run quality-review's cold watch on the animatic against the film's viewer track, with the cast's voice lines as its voices, quoted first as its reference says: a SPEND (quote it in one line, then get the yes with your host's own question tool, such as AskUserQuestion, "Yes, go ahead" / "Yes, up to N credits for this task" / "No", never as a typed question; only where the host has no such tool, those options numbered in one message; unless a spend limit the user stated covers it: N credits or an explicit no-limit ("as much as needed"), never inferred from words like "go ahead". Within it, ask nothing: quote it in one line ("About 8 credits; 12 of 20 left after this"), call it, then say what it spent and what remains, keeping a running total that includes failed calls, and stop to ask before the first call that would cross it. A money amount is asked once to restate it in credits; in unattended pace, never ask: call only with a consent or a stated spend limit already recorded, otherwise write the quote to pendingSpends and stop, as picsart-video-rules says) before round 1 unless every call is quoted at 0 credits. You wrote the story, so you can't tell whether a stranger follows it; nor can a critic who reads the cards. Fix what falls under its floor, the earliest gap first, by changing what is seen or heard, and watch again with fresh viewers, a round the yes did not cover quoted again. If the user says no, the review line says "no cold watch yet".
  • Then the critics, with the gap list. Where quality-review's critic panel runs, it judges the contact sheet and the gap list, never the cards or the timed script. Each critic says what it could not see or hear (the voices, the timing at speed): a thing it could not judge is not a pass.
  • Then the user watches it, cold. REVIEW the animatic in picsart_scene_editor, with its sound, as picsart-video-rules says: a draft opens cold.
  • An MP4 only when asked. picsart_scene_export (free) when the user wants a file to watch or share, or when the host cannot show the editor; give its downloadUrl.

Notes route by meaning. A note on what happens is a story note: film-story-writing rewrites the paragraph, the cards follow, and only the panels and lines it changes are made again, under their own SPEND. A note on one shot (the framing, a face, a line's reading) goes to that panel or that line alone. A note on timing or a cut is a free re-time or re-cut. Build it again, check it, and REVIEW again, until the user says yes. Keep each round's notes and changes in the record.

6. After the yes

The approved animatic is the film's plan for everything after it:

  • Its timing is the cut's reference, and each approved panel is that shot's key frame: it opens the shot's run as film-shot-generation says. An approved voice line can be the run's reference audio where the model takes one.
  • The user picks which shots go to video. Quote the picked shots only; a shot the user keeps as a panel stays in the cut as it was approved, a choice the user made, not a still played to fill a gap.
  • An animatic the user calls final for its own sake (a pitch, a table read) is delivered as it is, with no video.

Traps

  • Buying video before the animatic is approved, or calling the scene pictures alone an animatic.
  • A silent animatic called reviewed: the user has not heard the voices yet.
  • An animatic called reviewed with no cold watch, or a cold watch given the cards, the story or the track: whoever knows the story fills in what the picture never shows.
  • Captions carrying speaker names, card ids or stage directions.
  • A generated interface on a screen.
  • A move added to a still to pass a motion check, or to make the draft look busy.
  • Re-making every panel for one note.

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.