agentleFS
solankipravin374solankipravin374/visuals-skills/skills/paper/SKILL.md

paper

Skill0 starsChanged 21 days agoMITView on GitHub

Video effect - a torn-paper wipe turns the real laptop, its screen and your hand into a layered paper-craft diorama (flat colour sheets, thick shadows, stop-motion boil) while a sky, sun, clouds on strings, mountains, hills and trees pop up behind the lid, then it tears back to video. Use when the user types /paper or wants a paper cut-out / papercraft look on their laptop footage.

11 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use storytelling.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • jordiportalSkill

    storytelling

    Tecnicas para crear narrativas efectivas, comunicacion persuasiva y estructuras de mensaje.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 2

    Distinctive

    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:

    Every sheet gets a flat colour, a fibre texture, a lit cut edge and a soft drop shadow.

    line 13
  2. Very specific:

    The hand reads as one clean paper shape: If it has holes or picks up shadows, adjust --thr or choose a better --ref-time.

    line 53
  3. Distinctive:

    The scenery peeks over the lid top: If the laptop fills the frame, there is no room for it.

    line 55

“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “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

/paper

A jagged torn-paper edge sweeps across the frame. Behind it the scene is rebuilt as cut paper:

  • The laptop: a navy lid, a cream screen whose text lines become paper strips, coloured UI chips, key caps, a trackpad and stickers.
  • Your hand: a two-layer skin-tone sheet that follows it.
  • The scenery: the sun and clouds drop in on strings, and mountains with snow caps, layered hills and two trees pop up from behind the lid like a pop-up book. Paper puffs rise along the bottom edge.

Every sheet gets a flat colour, a fibre texture, a lit cut edge and a soft drop shadow. The edges boil at 12 fps like stop-motion. Then the paper tears away again. About 2.9 s.

Needs: a locked-off clip of a dark laptop on a desk with a plain wall above, hand(s) mostly still on the keyboard, and a frame from the same shot where the hand is off the laptop (--ref-time). Requires visuals-core.

Steps

  1. Zero-config first. The laptop, screen, text strips, colour chips, keys and stickers are all detected:
    python paper.py --in clip.mp4 --start 34.4 --dur 2.9 --out preview --preview 0.35,1.0,1.5 --ref-time 30.9
  2. Polish with measurements from python ../visuals-core/grid.py --in clip.mp4 --t 30.9 --out grid.jpg (use --crop y0,y1 for the keyboard). Look at the grid image and read the values:
    • --keyboard-rows rows.json: a clean full keyboard. One row per keyboard row: [bottom_y, left_x, right_x, key_height, [unit widths]]. Use 0.25 for a gap. examples/rows.json in the repo is a laptop with a number pad.
    • --trackpad "x,y;x,y;x,y;x,y": the 4 corners.
    • --cards "[[x0,y0,x1,y1,r],...]": app panels that should pop off the screen as white cards.
    • --hot x0,y0,x1,y1: text inside this box turns into orange strips. Use it for the user's typed prompt.
    • --sidebar-x 357 (tinted sidebar sheet), --webcam x,y, --hinge-y.
  3. Render the final:
    python paper.py --in clip.mp4 --start 34.4 --dur 2.9 --out paper.mp4 --ref-time 30.9 --keyboard-rows rows.json \
        --trackpad "266,1702;600,1698;632,1888;243,1892" --cards "[[385,1180,918,1326,16]]" --hot 385,1180,918,1326
    About 2-3 s per frame. A 3 s effect takes 3-4 minutes, so render it in the background.

Flags

flagdefaultmeaning
--ref-timerequiredhand-free frame: the paper laptop is built from it and the hand is keyed against it
--hinge-yscreen bottom + 60where the lid meets the deck
--keyboard-rowsauto (key bottom edges)JSON file or inline JSON, see above
--trackpad, --cards, --hot, --sidebar-x, --webcamoffoptional detail layers
--tear-in, --tear-out0.10,0.50 / dur-0.60,dur-0.18the torn-paper wipes
--thr30hand-difference threshold

Colours live in the PAL dict at the top of paper.py; change it to restyle the scene (e.g. a sunset sky).

Check before delivering

  • The hand reads as one clean paper shape. If it has holes or picks up shadows, adjust --thr or choose a better --ref-time.
  • No grey specks on the screen. Any that show are tiny dark UI bits; they are dropped when smaller than about 160 px².
  • The scenery peeks over the lid top. If the laptop fills the frame, there is no room for it. Reframe the shot or accept a laptop-only diorama.

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.