[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-11534":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":9,"language":10,"languages":9,"totalLinesOfCode":9,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":14,"subscribersCount":14,"size":14,"stars1d":14,"stars7d":13,"stars30d":15,"stars90d":14,"forks30d":14,"starsTrendScore":14,"compositeScore":16,"rankGlobal":9,"rankLanguage":9,"license":17,"archived":18,"fork":18,"defaultBranch":19,"hasWiki":20,"hasPages":18,"topics":21,"createdAt":9,"pushedAt":9,"updatedAt":32,"readmeContent":33,"aiSummary":34,"trendingCount":14,"starSnapshotCount":14,"syncStatus":35,"lastSyncTime":36,"discoverSource":37},11534,"ai-game-art-pipeline-skill","ybuild-ai\u002Fai-game-art-pipeline-skill","ybuild-ai","Agent skill for turning AI images and videos into playable game art assets",null,"Python",319,4,1,0,243,2.1,"MIT License",false,"main",true,[22,23,24,25,26,27,28,29,30,31],"agent-skills","ai-art","claude-code","codex","game-art","game-development","generative-ai","pixijs","sprite-animation","video-to-frames","2026-06-12 02:02:32","\u003Cdiv align=\"center\">\n  \u003Cimg src=\"media\u002Fpipeline-map.jpg\" alt=\"AI game art pipeline map\" width=\"100%\">\n\u003C\u002Fdiv>\n\n# AI Game Art Pipeline Skill\n\n> Provider-neutral workflows for turning AI images and videos into playable game assets.\n\n[![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fybuild-ai\u002Fai-game-art-pipeline-skill?style=flat&color=yellow)](https:\u002F\u002Fgithub.com\u002Fybuild-ai\u002Fai-game-art-pipeline-skill\u002Fstargazers)\n[![License](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flicense\u002Fybuild-ai\u002Fai-game-art-pipeline-skill?style=flat)](LICENSE)\n[![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fybuild-ai\u002Fai-game-art-pipeline-skill?style=flat)](https:\u002F\u002Fgithub.com\u002Fybuild-ai\u002Fai-game-art-pipeline-skill\u002Fcommits\u002Fmain)\n[![Skill](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FAgent%20Skill-Codex%20%2F%20Claude%20Code%20%2F%20Cursor-blue)](SKILL.md)\n\nThis 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.\n\nIt is not a prompt pack or a model leaderboard. The point is to ship assets that survive a real game loop.\n\n## Why This Exists\n\nMost AI game art demos stop at a beautiful image. Games need stricter things:\n\n- Transparent sprites that do not jitter.\n- Animation frames with stable identity and readable silhouettes.\n- Backgrounds that fit mobile GPU texture limits.\n- Cinematic effects that look rich without owning gameplay logic.\n- Audio, hit timing, anchors, and compression that hold up in runtime.\n\nThe core rule:\n\n> Pick the pipeline by runtime job, not by model hype.\n\n## Install\n\nRecommended, if you use the Agent Skills installer:\n\n```bash\nnpx skills add ybuild-ai\u002Fai-game-art-pipeline-skill --skill ai-game-art-pipeline -g\n```\n\nManual Codex install:\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fybuild-ai\u002Fai-game-art-pipeline-skill.git ~\u002F.codex\u002Fskills\u002Fai-game-art-pipeline\n```\n\nManual Claude Code install:\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fybuild-ai\u002Fai-game-art-pipeline-skill.git ~\u002F.claude\u002Fskills\u002Fai-game-art-pipeline\n```\n\nThen ask your agent for tasks like:\n\n- \"Use the AI game art pipeline skill to plan a 2D action RPG sprite pipeline.\"\n- \"Generate prompts and post-processing steps for a combat sprite sheet.\"\n- \"Turn a cinematic ultimate video into runtime frames and code-owned hit logic.\"\n- \"Audit these game assets for mobile runtime shipping risks.\"\n\n## What You Get\n\n| Runtime job | Recommended route |\n|---|---|\n| Static props, items, FX icons | Image model + style refs + removable background |\n| Existing or brand character | Reuse canonical sprite sheets before regenerating |\n| Combat character animation | Keyframe-first + 2D grid + post-processing + curation |\n| Walk\u002Frun\u002Fbody mechanics | Prefer video motion reference; use 3D skeleton only when cleanup is acceptable |\n| Ambient loops | Video model -> extracted frames |\n| Cinematic ultimate \u002F boss intro | Full-screen video-to-frames + code-driven hit logic |\n| Runtime feel | Deterministic code: hit pause, shake, particles, trails, SFX |\n\n## Visual Examples\n\n| Combat sprites | Cinematic ultimate |\n|---|---|\n| ![Battle sprite grid](media\u002Fbattle-sprite-grid.jpg) | ![Seedance awakening frames](media\u002Fseedance-awakening-frames.jpg) |\n\n| Motion reference tradeoff | Pipeline map |\n|---|---|\n| ![3D skeleton versus video motion reference](media\u002Fskeleton-vs-video-motion.jpg) | ![Pipeline map](media\u002Fpipeline-map.jpg) |\n\n## Repository Layout\n\n```text\nSKILL.md\nreferences\u002F\n  static-assets.md\n  battle-sprites.md\n  motion-video.md\n  backgrounds.md\n  runtime-shipping.md\nscripts\u002F\n  provider_stub.py\n  chroma_key_magenta.py\n  sheet_contact.py\n  extract_video_frames.py\nexamples\u002F\n  prompts.md\n  batch_generation_example.py\n  providers\u002F\n    README.md\n    minimal_provider_example.py\n    http_image_provider_example.py\n    http_video_provider_example.py\nmedia\u002F\n  pipeline-map.jpg\n  battle-sprite-grid.jpg\n  seedance-awakening-frames.jpg\n  skeleton-vs-video-motion.jpg\n```\n\n## Bundled Scripts\n\nScripts are local utilities only. They do not contain API keys, endpoints, private paths, or vendor SDK code.\n\n| Script | Purpose |\n|---|---|\n| `scripts\u002Fprovider_stub.py` | Adapter interface users can implement for their own image\u002Fvideo provider |\n| `scripts\u002Fchroma_key_magenta.py` | Remove solid magenta backgrounds from generated assets |\n| `scripts\u002Fsheet_contact.py` | Build numbered contact sheets for sprite curation |\n| `scripts\u002Fextract_video_frames.py` | Extract and resize video frames for runtime texture sequences |\n\nExamples:\n\n```bash\npython scripts\u002Fchroma_key_magenta.py input.png output.png\npython scripts\u002Fsheet_contact.py frames\u002F contact.png --cols 6\npython scripts\u002Fextract_video_frames.py ultimate.mp4 frames\u002F --fps 14 --start 0.6 --duration 3.6 --width 1280\n```\n\n## Provider Adapters, Not SDKs\n\nThe skill intentionally does not ship a real image\u002Fvideo SDK. Model APIs change quickly, and users should own credentials, endpoints, model names, retry policy, and billing behavior.\n\nInstead, the repo includes thin adapter examples:\n\n| Example | Use it when |\n|---|---|\n| `examples\u002Fproviders\u002Fminimal_provider_example.py` | You want a fake provider to test the pipeline shape locally |\n| `examples\u002Fproviders\u002Fhttp_image_provider_example.py` | You have an image-generation HTTP proxy that returns a URL or base64 image |\n| `examples\u002Fproviders\u002Fhttp_video_provider_example.py` | You have an async video-generation HTTP proxy with job polling |\n| `examples\u002Fbatch_generation_example.py` | You want to turn a small art plan into provider requests |\n\nRead [examples\u002Fproviders\u002FREADME.md](examples\u002Fproviders\u002FREADME.md) before wiring a real provider.\n\n## Quick Workflow\n\n1. Identify the runtime job and target engine.\n2. Check whether canonical assets already exist.\n3. Pick the smallest useful vertical slice.\n4. Generate or reuse source visuals.\n5. Post-process with deterministic scripts.\n6. Preview at target size and target device.\n7. Iterate surgically: rerun one animation, reprocess raw output, or repack frames.\n\n## Good Fit \u002F Bad Fit\n\nGood fit:\n\n- 2D action RPGs, tactics games, card battlers, mobile games, UI-heavy games.\n- Teams using image\u002Fvideo generation but needing runtime-ready assets.\n- Agents that can run local scripts and edit asset pipelines.\n\nBad fit:\n\n- One-off marketing art.\n- Pure concept-art exploration with no runtime target.\n- Fully automated \"make my whole game art set\" workflows with no curation.\n\n## Contributing\n\nContributions are welcome. The most useful additions are:\n\n- New provider adapters that keep credentials outside the repo.\n- Runtime preview templates for PixiJS, Canvas, Godot, Unity, SpriteKit, or web games.\n- More post-processing utilities for trimming, anchors, packing, and QA.\n- Real pipeline notes from shipped projects.\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md).\n\n## License\n\nMIT. See [LICENSE](LICENSE).\n","该项目旨在将AI生成的图像和视频转换为可在游戏中使用的游戏美术资源。其核心功能包括规划、生成、清理、打包及质量保证游戏运行时所需的美术素材，如精灵图、图标、背景、视频转帧动画等，并确保这些素材能够满足实际游戏循环的需求。技术上采用Python编写，支持透明度处理、稳定身份的动画帧生成以及符合移动GPU纹理限制的背景制作等功能。适用于需要高质量且实用的游戏美术资源开发场景，特别是那些追求在真实游戏环境中表现良好的项目。",2,"2026-06-11 03:32:02","CREATED_QUERY"]