agentleFS
badgidsbadgids/Story-Film-Skills/skills/handdrawn-live-video-generator/SKILL.md

handdrawn-live-video-generator

Skill4 starsChanged 3 months agoApache-2.0View on GitHub

Adapt MiniMax H3 prompts for surreal single-scene clips where rough hand-drawn animation physically contacts, deforms around, or interacts with live-action hands, objects, surfaces, and camera motion.

9 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

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

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 3

    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:

    Use for live-action scenes containing a deliberately rough hand-drawn animated element that interacts physically with real-world objects or …

    line 11
  2. Distinctive:

    Keep the interaction continuous and physically readable within one scene unless the user explicitly requests multiple scenes.

    line 19
  3. Distinctive:

    Avoid automatically turning the result into polished CG, a plush character, horror jump scare, or generic compositing effect.

    line 20
  4. Very specific:

    Use this overlay for action and texture, then encode the final clip with h3-prompt-writing and Story-Film's minimax-h3 adapter.

    line 26

“Common” is measured: kept by at least 6 in 10 of the 7 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

Handdrawn Live Video Generator

Use for live-action scenes containing a deliberately rough hand-drawn animated element that interacts physically with real-world objects or a hand.

Prompt overlay

  • Clearly define the live-action environment, contact object/hand, drawn subject, first contact point, deformation, reaction, movement path, and final state.
  • The drawn layer should retain hand-made line texture and visibly react to contact rather than floating as an unrelated overlay.
  • Preserve convincing occlusion, surface contact, pressure/deformation cues, and local shadow/light interaction when appropriate.
  • Let handheld or observational camera movement react slightly after the drawn action rather than predicting it.
  • Keep the interaction continuous and physically readable within one scene unless the user explicitly requests multiple scenes.
  • Avoid automatically turning the result into polished CG, a plush character, horror jump scare, or generic compositing effect.
  • Respect the project's requested duration/aspect ratio instead of forcing example defaults.

H3 handoff

Whether this skill was selected automatically or invoked directly, return through h3-prompt-writing, then minimax-h3, then scripts/minimax_h3_prompt_validator.py, and finally prompt-qc; this skill is a content/style overlay, not a standalone final-prompt path. Use this overlay for action and texture, then encode the final clip with h3-prompt-writing and Story-Film's minimax-h3 adapter.

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.