image-generation
Skill5 starsChanged 19 days agoMITView on GitHub
Generate game assets via the Google Gemini image API and process them into final sprite files. Triggers on: "generate an image/asset", "create a sprite", "make game art", or any request to produce or post-process image assets for a game. Wraps tools/generate-image.mjs (model, aspect ratio, reference image, batch count).
- Reads credentials
63 other projects use a version of this.
Adopted by
Most recently taken up by
- danielgwilson/luxintheir own version, first seen Nov 8, 2026
- CheehooLabs/SpureeSkillstheir own version, first seen Nov 8, 2026
- hex/claude-image-generationtheir own version, first seen Nov 5, 2026
- PostPlusAI/postplus-skillstheir own version, first seen Nov 5, 2026
- guinacio/claude-image-gentheir own version, first seen Nov 3, 2026
- Littlpinguin/marketing-cockpit-templatetheir own version, first seen Nov 3, 2026
Used with
Projects with it also use gift-evaluator, Podcast Generate and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
dav-niu474Skillgift-evaluator
The PRIMARY tool for Spring Festival gift analysis and social interaction generation. Use this skill when users upload photos of gifts (alcohol, tea, supplements, etc.) to inquire about their value, authenticity, or how to respond socially. Integrates visual perception, market valuation, and HTML card generation.
Also in 5 projects that use this
dav-niu474SkillPodcast Generate
Generate podcast episodes from user-provided content or by searching the web for specified topics. If user uploads a text file/article, creates a dual-host dialogue podcast (or single-host upon request). If no content is provided, searches the web for information about the user-specified topic and generates a podcast. Duration scales with content size (3-20 minutes, ~240 chars/min). Uses z-ai-web-dev-sdk for LLM script generation and TTS audio synthesis. Outputs both a podcast script (Markdown) and a complete audio file (WAV).
Also in 5 projects that use this
huang-x-hSkillVideo Generation
Implement AI-powered video generation capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to generate videos from text prompts or images, create video content programmatically, or build applications that produce video outputs. Supports asynchronous task management with status polling and result retrieval.
Also in 6 projects that use this
huang-x-hSkillVLM
Implement vision-based AI chat capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to analyze images, describe visual content, or create applications that combine image understanding with conversational AI. Supports image URLs and base64 encoded images for multimodal interactions.
Also in 6 projects that use this
- +1 more from huang-x-h
- +7 more from dav-niu474
Other versions63 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 63
- bytedance/deer-flow★ 85ksame name
- zhayujie/chatgpt-on-wechat★ 48ksame name
- zhayujie/CowAgent★ 48ksame name
- Devin-AXIS/A2V★ 7.4ksame name
- Devin-AXIS/iPolloWork★ 7.4ksame name
- jjyaoao/HelloAgents★ 3.2ksame name
- stophobia/deerflow2.0-enhanced★ 821same name
- langchain-ai/design-agent★ 596same name
- claude-office-skills/skills★ 433same name
- sonichi/sutando★ 396same name
53 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository19 other files it gives its agents.
- code-reviewSkill
- context-guardSkill
- graylog-searchSkill
- html-slide-deckSkill
- implement-specSkill
- jiraSkill
- lighthouseSkill
- mac-maintenanceSkill
- mysql-schema-designSkill
- phaser-gamedevSkill
- pixelart-cleanupSkill
- pixellab-apiSkill
- pixellabSkill
- product-hunt-launchSkill
- promo-videoSkill
- publish-report-artifactSkill
- seo-blogSkill
- seo-optimizationSkill
- usage-statuslineSkill
The file
Files
Image Generation & Asset Pipeline
Generuj game assety přes Google Gemini API a zpracuj je do finálních sprite souborů.
Tool
GEMINI_API_KEY=$(grep GEMINI_API_KEY .env | cut -d= -f2) \
node tools/generate-image.mjs "<prompt>" [--out <path>] [--aspect <ratio>] [--model <name>] [--count <n>] [--ref <image>]Modely
| Model | Poznámka |
gemini-3-pro-image-preview | Default — nejlepší kvalita |
gemini-3.1-flash-image-preview | Rychlejší |
imagen-4.0-generate-001 | Imagen 4, podporuje --negative |
Aspect ratios
1:1 | 16:9 | 9:16 | 4:3 | 3:4
Asset Pipeline (POVINNÝ WORKFLOW)
Krok 1: Generuj přes Gemini
Pro sprite sheet (více assetů najednou):
node tools/generate-image.mjs \
"Pixel art sprite sheet of 8 breakout bricks in horizontal row, evenly spaced on pure black background. Colors: pink, red, orange, gold, green, cyan, blue, purple. Each brick ~2.5:1 aspect ratio, neon style, dark outline. No text." \
--out public/assets/games/breakout/bricks-sheet.png \
--aspect 4:3Pro jednotlivý asset:
node tools/generate-image.mjs \
"Pixel art paddle bar for breakout game. Neon cyan, wide flat rectangle, white highlight, dark outline, glow. Pure black background. No text." \
--out public/assets/games/breakout/paddle-raw.png \
--aspect 16:9Promptovací pravidla
- Vždy specifikuj pozadí:
pure black background(pro tmavé hry) nebopure white background(pro světlé) - Vždy
No text, no other elements— jinak Gemini přidá random text - Specifikuj proporce:
~2.5:1 aspect ratio,7 times wider than tall - Styl:
pixel art,8-bit,retro arcade,neon glowing - Barvy PixelDen: cyan
#00FFF2, magenta#FF00E4, dark bg#0A0E17 - Aspect ratio volba:
4:3pro sprite sheety,16:9pro široké assety (paddle),1:1pro čtvercové (ball, ikony)
Krok 2: Zpracuj přes process-sprites.mjs
VŽDY po generování zpracuj obrázek. Gemini generuje velké obrázky (~1408x768) s hodně prázdného prostoru.
node tools/process-sprites.mjs <input> [options]Options:
| Flag | Popis |
--out <path> | Výstupní cesta (default: přepíše input; s --split: prefix) |
--bg <black|white> | Barva pozadí k odstranění (default: auto-detect) |
--threshold <n> | Práh detekce (default: 20) |
--split | Rozřež sheet na jednotlivé sprity |
--names <a,b,c> | Jména pro split sprity (default: 0,1,2...) |
--square | Paduj na čtverec |
--pad <n> | Padding kolem obsahu (default: 2) |
--no-crop | Přeskoč crop |
--no-transparent | Přeskoč odstranění pozadí |
Jednotlivý asset
node tools/process-sprites.mjs raw-paddle.png \
--out public/assets/games/breakout/paddle.png \
--bg blackSprite sheet → jednotlivé soubory
node tools/process-sprites.mjs sheet-raw.png \
--split --names head,body,corner,tail \
--out public/assets/games/snake/snake \
--bg white --squareDvouprůchodové zpracování (bílý sheet s černým pozadím spritů)
# 1. Rozřež sheet (odstraní bílé bg)
node tools/process-sprites.mjs sheet-raw.png \
--split --names head,body,tail \
--out public/assets/games/snake/snake \
--bg white --square
# 2. Odstraň černé bg z každého spritu
for name in head body tail; do
node tools/process-sprites.mjs "public/assets/games/snake/snake-${name}.png" \
--bg black --threshold 8 --no-crop
doneTool automaticky konvertuje JPEG/WebP na PNG (přes macOS sips).
Krok 3: Cleanup
# Smaž raw/sheet soubory, nechej jen finální assety
rm -f *-raw.png *-sheet.png *-gen.png *-new.pngKam ukládat finální assety
| Typ | Cesta |
| Game sprites | public/assets/games/{slug}/{asset}.png |
| Game thumbnail | public/assets/games/{slug}/thumbnail.png |
| Hero banner | public/assets/placeholders/hero-banner.png |
| Placeholder thumbs | public/assets/placeholders/game-thumb-{n}.jpg |
Důležité: Phaser sprite sizing
Gemini generuje velké obrázky (800-1400px). V Phaseru se zobrazují malé (40x16, 80x12, atd).
VŽDY v kódu:
sprite.setDisplaySize(TARGET_W, TARGET_H);
// Pro dynamic body:
sprite.body!.setSize(TARGET_W, TARGET_H);
// Pro STATIC body (bricks) — POVINNÉ:
(sprite.body as Phaser.Physics.Arcade.StaticBody).setSize(W, H);
(sprite.body as Phaser.Physics.Arcade.StaticBody).updateFromGameObject();Bez updateFromGameObject() na static bodies bude physics hitbox na špatné pozici!
Reference images
Pro style-matching přidej --ref:
node tools/generate-image.mjs "new brick style matching reference" \
--ref public/assets/games/breakout/brick-0.png \
--out public/assets/games/breakout/brick-new.pngDoes it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

