SuperAPI AI Directory
Partner中文AI newsFavorites
Skillscarl-motion

carl-motion

Design & creation

View repository

Updated 10-29 06:52

About this skill

carl-motion

<skill> below means the folder this file is in. Everything you need is inside it: style cards in references/styles/, engines in scenes/, tools in scripts/.

Which track you are on

  • Open track. You are Claude Opus 5.5 or stronger. Read anything here, combine engines, write your own renderer. Two things are fixed: the clip ends with scripts/deliver.py, and a red verdict means it is not done.
  • Rail track. Any other model, or you cannot tell. Follow the numbered path below and read only the files it names.

The rail

  1. Check the machine. python3 <skill>/scripts/doctor.py. If it reports anything missing, tell the user what to install and stop.

  2. Pick the style. Open references/styles/INDEX.md. If the user named a style, match it by English name, Chinese name or slug. If they described a feel (flat, warm, hand-made, techy), offer the two or three closest rows, one line each, and let them choose. Ask at most one question.

  3. Read that card in full (references/styles/NN_slug.md). Its status decides the next step:

    • Implemented or implemented on an upstream library: go to 3a.
    • Upstream only or research: go to 3b.

3a. Start from the engine. cp -R <skill>/scenes/<engine> <project>/engine, then python3 <skill>/scripts/doctor.py <engine>. Read <project>/engine/README.md; if it has a Keep / replace section, follow it. Change the subject only: names, captions, shapes, story beats. Keep the code that makes the look (texture passes, stepping, halftone, brush flow). Preview single frames first where the README offers it (most Python engines take ONLY=60,150). Then <project>/engine/render.sh <project>/work.

3b. Build a new engine. Read references/scene-contract.md and write <project>/engine/render.sh plus the scene code by those rules, using the card's prompt and pipeline. Render one still at 4 s first and show it to the user. Animate only after they say it reads as the style.

  1. Design against the pitfalls. Before the full render, list each line of the card's Pitfalls and say where the code handles it.

  2. Deliver. python3 <skill>/scripts/deliver.py --frames <project>/work/frames --out <project>/<slug>.mp4 --palette "<the card's palette>" (add --crf if the card says so). Exit code 0 is green, 1 is yellow (the clip is still written), 2 is red. info: lines, such as palette distance, never change the verdict; the card palette is sampled from the example clips, so a different topic will drift.

    • Red: nothing was delivered. Apply the printed fix, re-render, run it again.
    • Yellow: the clip is written. Say for each flagged item whether it is intended (a designed cut, a beat change) or a problem.
    • Green or yellow: show the user <slug>.mp4.qa/contact.jpg.

  3. Log it. Append one line to <project>/carl-motion-log.md: - YYYY-MM-DD · <slug> · <topic> · <verdict> · <what broke> · <how you fixed it>

Output

Give the filled prompt as one copy-pasteable block, the style and its status, and the pitfalls you designed against. When you rendered, add the MP4 path, the verdict, and the contact sheet. List anything that did not pass.

Open track extras

  • references/workflow.md: the A/B method, ordering many styles by complementary colour, the 9:16 explainer layout.
  • pipeline/: the tools behind a multi-style video (color_order_v4.py, color_stitch_verify.py, script_layout.py). They work on a delivery folder; see pipeline/README.md.

Language

Answer in the user's language. Every card carries the prompt in English and Chinese.