Sprite Sheet Pipeline

Community

LayrKits

sprite-sheet-pipeline

Guide an AI assistant through this repo's 2D animation sprite-sheet workflow. Use when creating animation-safe character image prompts, writing image-to-video prompts, extracting frames from animation videos, matting backgrounds, building and validating horizontal 256 x 256 sprite sheets, promoting final outputs, or explaining game integration.

Overview

Publisher	LayrKits
Repository	`Sprite-Pipeline`
Skill name	`sprite-sheet-pipeline`
Stars	595
Forks	61
Bundled files	Instructions only
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by LayrKits on GitHub. Read the source before you install it.

Installation

Install the Sprite Sheet Pipeline AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/LayrKits/Sprite-Pipeline/tree/main/skills/sprite-sheet-pipeline
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/LayrKits/Sprite-Pipeline.git /tmp/Sprite-Pipeline
mkdir -p .claude/skills
cp -r /tmp/Sprite-Pipeline/skills/sprite-sheet-pipeline .claude/skills/sprite-sheet-pipeline

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Sprite Sheet Pipeline in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Sprite Sheet Pipeline on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Sprite Sheet Pipeline is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Sprite Sheet Pipeline Skill

Use this skill as a routing guide for the repo. Keep detailed rules in the project docs; read only the document needed for the current task.

Start Here

Repo overview and folder map: README.md
Copy-paste processing commands: docs/QUICKSTART.md
Folder roles and cleanup rules: docs/WORKSPACE_CONVENTIONS.md
Active pipeline contract and validation rules: docs/ANIMATION_PIPELINE_NOTES.md
Frame extraction details: docs/FRAME_EXTRACTION.md
Game-side usage assumptions: docs/INTEGRATION_GUIDE.md

Prompting Tasks

If the user asks to create an animation and provides only a still image, do not try to process the image directly through the cleanup pipeline. Reply in substance:

This pipeline is designed to process videos into sprite sheets. Would you like me to write a prompt for a video model based on the provided image and animation description?

Tailor the response to the user input. If they provided no animation description, ask what motion they want. If they provided no asset at all, check Videos/To Be Processed/ for queued videos before asking for a new source.

For a new character image, first pose, character reference, or transition frame, read docs/reference/PROMPTING_IMAGE_MODELS.md.

Default image-prompt goal:

one full-body 2D game character
animation-safe margins
full weapon, hair, cape, cloth, and effects visible
centered character
flat exact #00FF00 background
no shadow, floor, text, watermark, border, props, or background objects

For image-to-video, Kling, or source-footage animation prompts, read docs/reference/PROMPTING_VIDEO_MODELS.md.

Default video-prompt goal:

uploaded image is the exact first frame
footage is for 2D game animation, not cinematic video
define an invisible core registration anchor, usually belt/pelvis/torso core
keep that body anchor locked to the same screen-space point
do not let the model center on weapon, cloth, hair, effects, or bounding-box extremes
locked camera with no zoom, pan, rotation, cuts, or shake
character remains registered/centered with all motion inside frame
no horizontal screen travel
flat exact #00FF00 background with no variation
timestamped step-by-step visible motion
preserve character design, anatomy, proportions, weapon, and 2D style

For image-to-video jobs, use the context-engineered prompt pattern in docs/reference/PROMPTING_VIDEO_MODELS.md: task, production context, subject scope, fixed registration rule, chroma matte rule, locked camera rule, character preservation, facing/framing rules, timestamped timeline, and failure conditions. Keep the reusable non-motion control block at 2500 characters or less and the motion description at 500 characters or less, including labels.

Return one copy-paste prompt by default. Include avoid/negative constraints inside that prompt unless the target tool explicitly has a separate negative prompt field.

Processing Tasks

Use the current frame-directory workflow. The source of truth is an animation video or ordered frame folder, not a generated grid sheet.

Normal processing order:

Put one source animation video in Videos/ or Videos/To Be Processed/.
Extract ordered PNG frames into work/extracted/<character>/<action>/.
Matte light/off-white backgrounds into work/matted/<character>/<action>/ when needed.
Build a horizontal 256 x 256 sprite strip with tools/animation_pipeline.py.
Review the preview PNG, individual cleaned frames, and JSON report.
Run node tools/serve_sprite_viewer.mjs and open the generated sheet with the Codex integrated Browser tool first. Use a regular desktop browser only after the integrated Browser tool is unavailable or fails. Do not use Playwright CLI as the default human review handoff path. After the server is running, include a Markdown link to the exact review URL in your response so Codex shows a Web preview card with an Open button. Use the link label open sprite viewer for normal review pages.
If vertical or horizontal alignment ran, open the server-hosted alignment review page instead of the plain sheet viewer, and include a Markdown link labeled open alignment review.
Promote only approved sheets and matching cell frames into Final Sprite Sheets/<GameName>/<CharacterName>/<animation>/.

Use --layout-mode preserve-canvas for normal video-derived animations. Use --layout-mode fit-foreground only for legacy recovery or an explicitly foreground-normalized export.

If the user does not specify a frame count, default to 24 frames. Pass --frames 24 to tools/animation_pipeline.py and use 24f_256 in output paths.

Validation And Promotion

Do not promote raw extracted frames. Promote only cleaned pipeline outputs.

Before promotion, verify:

output sheet is exactly frames * 256 by 256
report status is pass
warnings have been visually reviewed
no important source or final pixels are clipped
preview order and timing feel correct
apparent character scale stays consistent across animations
final sheet and individual cell frames match exactly

When the hosted alignment review is used, Finalize saves the current working copy, promotes it into Final Sprite Sheets/<GameName>/<CharacterName>/<animation>/, writes exact matching individual frame cells, and opens the promoted sheet in the viewer.

After approval, move the source video to Videos/Processed/ and move non-promoted generated artifacts for that pass into Cleanup/.

Frequently asked questions

What does the Sprite Sheet Pipeline AI skill do?

Why use Sprite Sheet Pipeline on TypingMind?

Because you install it once and use it with any model. Sprite Sheet Pipeline is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Sprite Sheet Pipeline in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/LayrKits/Sprite-Pipeline/tree/main/skills/sprite-sheet-pipeline. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Sprite Sheet Pipeline?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Sprite Sheet Pipeline?

As many as you like. As long as a model supports skills, you can use Sprite Sheet Pipeline with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Sprite Sheet Pipeline AI skill free?

It is published on GitHub by LayrKits. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Brand Discovery

affaan-m

CommunityPopular

Use when a brand needs to discover or articulate its identity through structured multi-session interviews. Covers purpose, positioning, audience, personality, voice, narrative, and founder-brand…

Competitive Platform Analysis

affaan-m

CommunityPopular

Use when scoping a competitive landscape — identifying, categorising, and score-filtering a competitor set before any benchmarking begins. Decides who counts as a competitor, which tier they belong…

Frontend Slides

Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a…

Plan Canvas

Open plans and HTML artifacts in a local browser canvas where the human annotates elements, chats, and approves or requests changes without leaving the page. Use when presenting a plan for review, or…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Sprite Sheet Pipeline Skill

Start Here

Prompting Tasks

Processing Tasks

Validation And Promotion

Frequently asked questions

Related AI Skills

Set up your own AI workspace now