
Hatch Pet
Create and package animated Codex-style pet spritesheets from art or prompts.
- Repository
- nexu-io/open-design
- Stars
- 105,448
- Licence
- Apache-2.0
- Files
- 5 files
What it does
This skill guides an AI agent through building an animated desktop-style pet. It plans the animation rows, asks the image-generation skill for each row of poses, then uses bundled scripts to cut the frames, check them, assemble an 8x9 spritesheet, create QA previews, and package a pet.json file. The result can be imported into a floating pet companion app.
Great for
- Creators who want a custom animated pixel-style desktop pet
- Developers building Codex pet assets who need a repeatable atlas workflow
- Artists turning an existing character drawing into a small sprite animation
Skip it if
- Full-resolution illustration or realistic animation work, since the skill deliberately simplifies art into a chunky pixel-mascot style
- Users without the $imagegen system skill installed, because the workflow depends on it and will stop if it is unavailable (generating rows locally is explicitly prohibited)
- Projects needing a single static image, since a normal run involves up to 10 image-generation jobs and is costly
Try asking
- “Hatch me a tiny pixel-art shiba pet that is friendly and sitting upright, with a small pomegranate prop”
- “Turn this screenshot of my mascot into an animated Codex pet with idle and running rows”
- “Repair the waving row of my existing pet spritesheet and repackage it”
- “Create a preview video and QA contact sheet for my pet spritesheet”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 5 original files, the Apache-2.0 licence and an attribution note.
hatch-pet.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip hatch-pet.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip hatch-pet.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Provide clear reference images with the character's colors and silhouette so the generated rows stay consistent
- Review the QA contact sheet and approve or repair individual rows before packaging
- Keep the pet description terse and sprite-specific, since the skill avoids extra style augmentation
What's inside
- open-design.json
- references/animation-rows.md
- references/codex-pet-contract.md
- references/qa-rubric.md
- SKILL.md
Redistributed unmodified from nexu-io/open-design under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.