Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

img2mo-learn (2D Motion Knowledge Builder)

Analyzes videos, frame sequences, spritesheets and Spine assets to build a reusable 2D motion knowledge base inside your project.

Image & VideoIntermediate★ 213⑂ 6AI score 8/10Last updated: Jul 2, 2026

What it does

Run /img2mo-learn <resource> and Claude inspects the given action asset (mp4/mov/webm video, PNG frame folder, spritesheet, contact sheet, GIF, Spine .json/.atlas/.skel, or a previous output) and distills:

  • Motion timing: action type (attack, walk, idle, block, suffer, death, skill…), frame count, fps, loop behavior, and beat labels (anticipation → contact → follow-through → recovery)
  • Pose & topology lessons: active limb, weapon owner, anchor, facing, silhouette expansion, squash/stretch, foot baseline
  • Style lessons: line weight, palette, shading, effects, background/alpha handling
  • Reusable prompt clauses and rejection checks (hand swaps, scale popping, bad alpha, cut weapons, watermarks)

Everything is curated into a project-level img2mo-knowledge/ folder — index.md, a strictly-schemaed learnings.jsonl, plus action/style/prompt/failure pattern files — which the companion /img2motion skill reads before generating new motion.

Who it's for

  • 2D game artists and technical artists working with spritesheets or Spine rigs
  • Anyone iterating on AI-generated motion sheets who keeps hitting the same failures
  • Teams that want a shared, searchable reference-motion knowledge base

Examples

  1. /img2mo-learn sample/sword-slash.mp4 — probes fps/duration with ffprobe, builds a contact sheet, and records attack beat timing into action-patterns.md
  2. /img2mo-learn output/boss-death-01/ — logs alpha breakage and drifting foot baseline into failures.md plus a per-output retro.md
  3. /img2mo-learn motion/spine-mage/ — reads Spine animation, bone and slot names and adds cast-motion prompt clauses to prompt-patterns.md

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/WU-HAOTIAN34/2dimg2motion/HEAD/skills/img2mo-learn/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/img2mo-learn folder from the GitHub repo WU-HAOTIAN34/2dimg2motion into my ~/.claude/skills/img2mo-learn/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/WU-HAOTIAN34/2dimg2motion.git && mkdir -p ~/.claude/skills && cp -r 2dimg2motion/skills/img2mo-learn ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and go to your working directory.
  2. Clone the repo: git clone https://github.com/WU-HAOTIAN34/2dimg2motion.git
  3. Create the skills folder if needed: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r 2dimg2motion/skills/img2mo-learn ~/.claude/skills/
  5. Also copy the companion skill (img2motion) from the same repo so the learned knowledge is actually consumed at generation time.
  6. Install ffmpeg/ffprobe for video analysis (macOS: brew install ffmpeg, Ubuntu: sudo apt install ffmpeg).
  7. Restart Claude Code, open your project, and try /img2mo-learn sample/clip.mp4; the img2mo-knowledge/ folder is created automatically.
View source on GitHub ↗License: MIT