All skills
openai avatar

/hatch-pet

@c25113b official
by openaiopenai/skills28k stars
1,891

Create, repair, validate, visually QA, and package Codex-compatible animated pets and pet spritesheets from character art, generated images, company or prospect brand cues, or visual references. Use when a user wants a lightweight-worker Codex pet workflow, a non-pixel custom pet style, a prospect or company mascot pet, or a full 8x9 animated pet atlas with transparent unused cells, QA contact sheets, and pet.json packaging. This skill composes the installed $imagegen system skill for visual generation and uses bundled scripts for deterministic spritesheet assembly.

Use this Skill: https://skilld.dev/gh/openai/skills/hatch-pet

This session only. Nothing lands on disk.

referencescodex-pet-contract.md

≈197 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Codex Pet Contract

Sprite Atlas

  • Format: PNG or WebP.
  • Dimensions: 1536x1872.
  • Grid: 8 columns x 9 rows.
  • Cell: 192x208.
  • Background: transparent.
  • Unused cells: fully transparent.

The webview animation uses CSS background positions from the fixed row and column counts. Do not add labels, gutters, borders, grid lines, shadows outside the cell, or extra frames.

Local Custom Pet Package

Place files under:

${CODEX_HOME:-$HOME/.codex}/pets/<pet-name>/
├── pet.json
└── spritesheet.webp

Manifest shape:

{
  "id": "pet-name",
  "displayName": "Pet Name",
  "description": "One short sentence.",
  "spritesheetPath": "spritesheet.webp"
}

The app loads custom pets from the folder name under ${CODEX_HOME:-$HOME/.codex}/pets/.

Source: SKILL.md on GitHub

1 warning16d3 checks · Risk SAFE
  • Gen Agent Trust Hub16d

    This skill provides a structured workflow for creating and packaging animated pets using image generation and local processing scripts. It features security considerations such as isolating generation tasks into subagents and using deterministic scripts for image validation. A minor consideration is the ingestion of external data for brand research, which is a core part of the skill's design and is handled appropriately.

  • Socket16d

    No alerts

  • Snyk16d

    Risk: MEDIUM · 1 issue

Signed by skilld at c25113b. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 months ago.

Activeupdated 5 months ago
  • codex
  • spritesheet
  • animation
  • pet
  • imagegen
  • atlas
  • mascot
  • brand
  • transparent-png

README badge

README badge for openai/skills/hatch-pet

Creates Codex-compatible animated pets from text descriptions, brand cues, or reference images by delegating visual generation to an installed imagegen skill and using deterministic scripts for spritesheet assembly, validation, and packaging. Supports non-pixel styles (plush, clay, vector, 3D toy, painterly) and handles brand discovery via web search when a company or product name is provided instead of a concrete avatar description.

Generated from the current SKILL.md.

Does this skill generate images itself, or does it delegate to another system?
It delegates all visual generation to the installed $imagegen system skill. This skill handles only deterministic spritesheet assembly, validation, QA, and packaging.
What animation states does the final pet support?
The skill produces all 9 Codex app states: idle, running-right, running-left, waving, jumping, failed, waiting, running, and review.
Can I use non-pixel art styles for the pet?
Yes. Plush, clay, sticker, vector, 3D toy, painterly, and brand-inspired styles are supported as long as the pet fits readable in a 192x208 cell with a clean removable background.
How does the skill handle company or brand mascot requests?
If you provide only a brand or company name, the skill runs a lightweight discovery worker to research visual and personality cues from official sources before generating the pet.
Can the running-left animation be automatically created from running-right?
Only if running-right is generated first, visually inspected, and explicitly approved as safe to mirror. Otherwise, running-left is generated as a separate $imagegen job.

Generated from the current SKILL.md. These answers refresh after source changes.