name: ai-game-art-pipeline description: Provider-neutral open-source skill for planning and producing game-runtime art assets and animation: static props/icons, canonical character sheets, combat sprites, 3D/video motion references, Veo/Seedance-style video-to-frames, cinematic ultimates, backgrounds, FX, SFX, runtime packaging, and QA. Use when building actual game assets for PixiJS/Canvas/Unity/Godot/SpriteKit/etc., not one-off marketing images.

AI Game Art Pipeline

Use this skill when a user wants to generate, plan, debug, or package game art that must run in an actual game runtime.

The skill is provider-neutral. It does not assume any specific API key or vendor SDK. If a model call is needed, use the user's available provider through an adapter or ask them to implement scripts/provider_stub.py.

Core Rule

Pick the pipeline by runtime job, not by model hype.

Default Workflow

1. Identify the runtime job and target engine.
2. Check whether canonical assets already exist.
3. Pick one scenario reference below.
4. Generate the smallest useful vertical slice, not the full asset set.
5. Post-process with deterministic scripts.
6. Preview at target size and target device.
7. Iterate surgically: rerun one animation, reprocess raw output, or repack frames.

Scenario References

Read only the relevant file:

• references/static-assets.md — props, icons, items, simple monsters, canonical asset reuse.
• references/battle-sprites.md — keyframe-first combat sprite sheets, 2D grids, anchors, contact sheets.
• references/motion-video.md — 3D skeleton pitfalls, video motion references, Veo/Seedance-style video-to-frames, cinematic ultimates.
• references/backgrounds.md — level backgrounds, master-first parallax, outpaint chains, mobile texture limits.
• references/runtime-shipping.md — formats, compression, CDN layout, audio/SFX, runtime QA.

Bundled Scripts

Scripts are local utilities only. They do not call model APIs.

• scripts/provider_stub.py — adapter interface the user can implement for their provider.
• scripts/chroma_key_magenta.py — remove magenta background from generated sheets/icons.
• scripts/sheet_contact.py — make numbered contact sheets for curation.
• scripts/extract_video_frames.py — extract/resize video frames for runtime texture sequences.

Provider Adapters

Do not write a full vendor SDK unless the user explicitly asks for one. Prefer a thin adapter around scripts/provider_stub.py so credentials, endpoints, retries, billing, and model choices stay in the user's project.

If the user wants examples, point them to examples/providers/README.md and adapt only the minimal file they need:

• fake/local provider for testing the pipeline without model calls.
• generic image HTTP provider for a user's image-generation proxy.
• generic async video HTTP provider for a user's video-generation proxy.

Output Standard

When using this skill, produce:

• A concise pipeline choice and why.
• The exact assets to generate or reuse.
• Prompt constraints if model generation is needed.
• Post-processing commands/scripts.
• Runtime packaging notes: dimensions, format, anchor, frame rate, texture limits.
• QA checklist for the target device.

Hard Warnings

• Do not regenerate a known character if a canonical sheet exists.
• Do not use 1xN horizontal strips for complex combat poses; use 2D grids.
• Do not let cinematic video own gameplay semantics. Damage, hitboxes, target tracking, cooldown, and SFX belong in code.
• Do not ship giant backgrounds because they look fine on desktop. Check mobile texture limits.
• Do not treat AI output as final. The production asset is the generated image plus cleanup, anchors, timing, compression, and runtime test.

AI Game Art Pipeline Skill

Provider-neutral workflows for turning AI images and videos into playable game assets.

This skill helps agents plan, generate, clean, package, and QA game-runtime art assets: sprites, icons, backgrounds, video-to-frames animation, cinematic ultimates, anchors, compression, and runtime checks.

Created by Y Build, an AI agent platform for building, launching, and growing apps.

It is not a prompt pack or a model leaderboard. The point is to ship assets that survive a real game loop.

Why This Exists

Most AI game art demos stop at a beautiful image. Games need stricter things:

• Transparent sprites that do not jitter.
• Animation frames with stable identity and readable silhouettes.
• Backgrounds that fit mobile GPU texture limits.
• Cinematic effects that look rich without owning gameplay logic.
• Audio, hit timing, anchors, and compression that hold up in runtime.

The core rule:

Pick the pipeline by runtime job, not by model hype.

Install

Recommended, if you use the Agent Skills installer:

npx skills add ybuild-ai/ai-game-art-pipeline-skill --skill ai-game-art-pipeline -g

Manual Codex install:

git clone https://github.com/ybuild-ai/ai-game-art-pipeline-skill.git ~/.codex/skills/ai-game-art-pipeline

Manual Claude Code install:

git clone https://github.com/ybuild-ai/ai-game-art-pipeline-skill.git ~/.claude/skills/ai-game-art-pipeline

Then ask your agent for tasks like:

• "Use the AI game art pipeline skill to plan a 2D action RPG sprite pipeline."
• "Generate prompts and post-processing steps for a combat sprite sheet."
• "Turn a cinematic ultimate video into runtime frames and code-owned hit logic."
• "Audit these game assets for mobile runtime shipping risks."

What You Get

Visual Examples

Combat sprites	Cinematic ultimate

Motion reference tradeoff	Pipeline map

Repository Layout

SKILL.md
references/
  static-assets.md
  battle-sprites.md
  motion-video.md
  backgrounds.md
  runtime-shipping.md
scripts/
  provider_stub.py
  chroma_key_magenta.py
  sheet_contact.py
  extract_video_frames.py
examples/
  prompts.md
  batch_generation_example.py
  providers/
    README.md
    minimal_provider_example.py
    http_image_provider_example.py
    http_video_provider_example.py
media/
  pipeline-map.jpg
  battle-sprite-grid.jpg
  seedance-awakening-frames.jpg
  skeleton-vs-video-motion.jpg

Bundled Scripts

Scripts are local utilities only. They do not contain API keys, endpoints, private paths, or vendor SDK code.

Examples:

python scripts/chroma_key_magenta.py input.png output.png
python scripts/sheet_contact.py frames/ contact.png --cols 6
python scripts/extract_video_frames.py ultimate.mp4 frames/ --fps 14 --start 0.6 --duration 3.6 --width 1280

Provider Adapters, Not SDKs

The skill intentionally does not ship a real image/video SDK. Model APIs change quickly, and users should own credentials, endpoints, model names, retry policy, and billing behavior.

Instead, the repo includes thin adapter examples:

Read examples/providers/README.md before wiring a real provider.

Quick Workflow

1. Identify the runtime job and target engine.
2. Check whether canonical assets already exist.
3. Pick the smallest useful vertical slice.
4. Generate or reuse source visuals.
5. Post-process with deterministic scripts.
6. Preview at target size and target device.
7. Iterate surgically: rerun one animation, reprocess raw output, or repack frames.

Good Fit / Bad Fit

Good fit:

• 2D action RPGs, tactics games, card battlers, mobile games, UI-heavy games.
• Teams using image/video generation but needing runtime-ready assets.
• Agents that can run local scripts and edit asset pipelines.

Bad fit:

• One-off marketing art.
• Pure concept-art exploration with no runtime target.
• Fully automated "make my whole game art set" workflows with no curation.

Contributing

Contributions are welcome. The most useful additions are:

• New provider adapters that keep credentials outside the repo.
• Runtime preview templates for PixiJS, Canvas, Godot, Unity, SpriteKit, or web games.
• More post-processing utilities for trimming, anchors, packing, and QA.
• Real pipeline notes from shipped projects.

See CONTRIBUTING.md.

License

MIT. See LICENSE.