see-through-anime-layer-decomposition — Claude Code skill: anime
Splits a single anime illustration into semantic layers and exports a layered PSD with depth maps for 2.5D animation.
npx skills add reason-machines/trending-skills --skill see-through-anime-layer-decomposition -a claude-codeWhat see-through-anime-layer-decomposition does
This skill hands the agent working knowledge of See-through: it takes one anime character image and separates it into layers — hair, face, eyes, clothing, accessories. Occluded regions get inpainted so each layer is complete, and drawing order is inferred from pseudo-depth.
The pipeline runs on diffusion models. The main script inference/scripts/inference_psd.py takes a file path or a folder plus the --save_to_psd flag, and writes results to workspace/layerdiff_output/. After that, heuristic_partseg.py can split layers further: seg_wdepth by depth, seg_wlr left to right. Models are pulled from HuggingFace on first use, so there is no separate download step.
What you need up front: a conda environment with Python 3.12, PyTorch built for CUDA 12.8, and the packages in requirements.txt. Annotators such as detectron2, SAM2 or mmdet come from their own requirements files — install only the ones you actually use. Run every script from the repository root, or asset paths will not resolve.
What it helps with
- split an anime character into separate layers for animation
- turn one image into a layered PSD file
- inpaint occluded body parts on each layer
- infer drawing order from pseudo-depth
- stratify layers by depth or left-right
Example prompts for the agent
- decompose this anime illustration into layers and save a PSD
- run inference_psd.py over my image folder and export PSDs
- split the handwear layer by depth with heuristic_partseg.py
How to install see-through-anime-layer-decomposition
1Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill see-through-anime-layer-decomposition -a claude-code2Manually: put the files in place
~/.claude/skills/see-through-anime-layer-decomposition/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/see-through-anime-layer-decomposition/
1Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill see-through-anime-layer-decomposition -a codex2Manually: put the files in place
.agents/skills/see-through-anime-layer-decomposition/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill see-through-anime-layer-decomposition -a cursor2Manually: put the files in place
.cursor/skills/see-through-anime-layer-decomposition/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install reason-machines/trending-skills see-through-anime-layer-decomposition2Manually: put the files in place
.github/skills/see-through-anime-layer-decomposition/SKILL.md1Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill see-through-anime-layer-decomposition -a gemini-cli2Platform CLI
gemini skills install https://github.com/reason-machines/trending-skills --path skills/see-through-anime-layer-decompositionManually: put the files in place
.devin/skills/see-through-anime-layer-decomposition/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill see-through-anime-layer-decomposition -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about see-through-anime-layer-decomposition
How do I install see-through-anime-layer-decomposition in Claude?
Run npx skills add reason-machines/trending-skills --skill see-through-anime-layer-decomposition -a claude-code. The skill lands at ~/.claude/skills/see-through-anime-layer-decomposition/SKILL.md.
What does see-through-anime-layer-decomposition do?
It teaches the agent to work with the See-through framework: decompose one anime illustration into semantic layers with occlusion inpainting, then export a layered PSD with depth maps and segmentation masks.
What do I need to run the pipeline?
A conda environment with Python 3.12, PyTorch for CUDA 12.8, and the packages in requirements.txt. Scripts must be run from the repository root.
