hatch-pet

Generate, validate, and package Codex-compatible v2 animated pet spritesheets from art or brand cues.

Updated Jul 3, 2026
One-click install
npx skills add https://github.com/CHENHUI-X/toolbox --skill hatch-pet-chenhui-x
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: hatch-pet
Source: https://github.com/CHENHUI-X/toolbox/tree/main/codex-skill/codex/hatch-pet
Command: npx skills add https://github.com/CHENHUI-X/toolbox --skill hatch-pet-chenhui-x

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires Pillow, and includes scripts (resource) and references (resource) components.

What problem does it solve? Creating a Codex-compatible animated pet requires producing a precise 8x11 spritesheet atlas with 9 animation rows and 16 look directions, plus deterministic QA and packaging, which is error-prone to do manually. ## Core Features & Use Cases - End-to-End Pet Generation: Create a v2 pet from character art, generated images, brand cues, or text concepts, producing a 1536x2288 atlas with spriteVersionNumber 2. - Deterministic Assembly and QA: Use bundled Python scripts to extract frames, mirror running-left, compose atlases, suppress chroma spill, and validate every cell. - Repair and Upgrade Workflows: Repair existing pets, upgrade 8x9 atlases to v2, and run brand discovery for company-inspired mascots. - Use Case: Give the assistant a company name and it researches the brand, generates a mascot base image, produces all animation rows and look directions, validates them, and packages the pet under ~/.codex/pets. ## Quick Start Ask the assistant to hatch a new Codex pet named Sparky from your reference image and package it as a v2 spritesheet.

Frequently Asked Questions about hatch-pet

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a custom Codex animated pet?

Provide a concept, reference image, or brand name and the skill generates a base image, nine animation row strips, and 16 look directions. It then assembles the 8x11 atlas, runs QA, and packages it with spriteVersionNumber 2 under your Codex pets directory.

What spritesheet format does a Codex v2 pet require?

A v2 pet uses a 1536x2288 PNG or WebP atlas with 8 columns and 11 rows of 192x208 cells. Rows 0-8 hold standard animations, rows 9-10 hold 16 clockwise look directions, and the manifest must set spriteVersionNumber to 2.

Can I create a pet from a company or brand name?

Yes, the skill runs a brand discovery step that researches official sources for palette, tone, and mascot cues before generation. The resulting brief guides the base image and all animation rows without copying logos or text.

Can an existing 8x9 pet atlas be upgraded to v2?

Yes, a valid 8x9 atlas is used as the rows 0-8 intermediate after validation. The skill then generates look-direction rows 9 and 10 and packages the result as a v2 pet.

Why does my pet spritesheet get rejected by the Codex app?

Rejection usually means the manifest omits spriteVersionNumber 2, so the 2288-pixel-tall sheet is treated as v1. It can also fail if cells contain edge contamination, interior transparent holes, or incorrect dimensions.

What dependencies do the hatch-pet scripts need?

The bundled scripts require Python with Pillow for all image processing. The skill loads a workspace-provided Python runtime via load_workspace_dependencies rather than using a system Python.