hatch-pet

Generate and package Codex-compatible v2 animated pet spritesheets from art or brand references.

1|Updated Jul 16, 2026
One-click install
npx skills add https://github.com/sota411/codex-config --skill hatch-pet-sota411
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: hatch-pet
Source: https://github.com/sota411/codex-config/tree/main/archived-user-skills/2026-08-20/unused/hatch-pet
Command: npx skills add https://github.com/sota411/codex-config --skill hatch-pet-sota411

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Creating a custom animated pet for Codex requires producing a precise 8x11 spritesheet atlas with 9 animation states and 16 look directions, plus deterministic validation and packaging, which is impractical to do by hand. ## Core Features & Use Cases - End-to-end pet generation: Creates a base character from text, reference art, or researched brand cues, then generates all 9 standard animation rows and 16 look-direction poses. - Deterministic assembly and QA: Bundled Python scripts extract frames, validate rows, suppress chroma spill, compose the 1536x2288 atlas, and produce contact-sheet QA artifacts. - Repair and upgrade workflows: Upgrades existing 8x9 atlases to v2, repairs failed cells or rows, and packages the result with spriteVersionNumber 2. - Use Case: Give the assistant a company name or mascot sketch and receive a ready-to-install Codex pet folder containing pet.json and spritesheet.webp. ## Quick Start Ask the assistant to hatch a new Codex pet named after your brand or character idea 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 animated pet for Codex?▼

Provide a name, description, reference image, or brand name, and the skill generates a base character, nine animation rows, and sixteen look directions. It then assembles and validates an 8x11 atlas and packages it with spriteVersionNumber 2.

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 animation states and rows 9-10 hold 16 clockwise look directions, packaged with spriteVersionNumber 2 in pet.json.

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

Yes, the skill runs a lightweight web research worker that extracts palette, tone, and mascot cues from official brand sources. The resulting brief seeds the pet prompt without copying logos, text, or trademarked marks.

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

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

Why does my pet spritesheet get rejected by Codex?▼

Rejection usually happens when the manifest omits spriteVersionNumber 2, which makes the app treat the 2288-pixel-tall sheet as v1. Incorrect atlas dimensions or non-transparent unused cells also cause validation failures.

What dependencies do the hatch-pet scripts need?▼

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