Generate Minecraft-focused raster assets with Codex's built-in image generation tool, including pack icons, promo art, concept textures, thumbnails, server banners, and UI mockups. Use when the deliverable should be a bitmap image rather than JSON models, SVG, or code-native assets.
npx skills add https://github.com/Jahrome907/minecraft-agent-skills --skill minecraft-imagegen
Use this skill when a Minecraft project needs new raster art or a visual concept
that will later be refined into a resource pack, release post, store listing, or
server brand asset.
Use when: the task is generating or editing a bitmap image for a Minecraft project, such as pack.png, release art, store thumbnails, concept textures, UI mockups, or server/banner art.Do not use when: the task is deterministic resource-pack implementation work such as pack.mcmeta, block/item model JSON, blockstates, fonts, sounds, or shader files (minecraft-resource-pack).Do not use when: the task is vector/code-native UI, an existing SVG/logo system, or non-image code/assets.Do not use when: the current host does not expose built-in image generation or an equivalent image-editing tool.references/prompt-patterns.md when the request is underspecified or you need a stronger generation vs edit prompt shape.references/asset-recipes.md when the user names a concrete deliverable such as pack.png, a release banner, a server header, or a texture concept sheet.scripts/scaffold-asset-brief.sh to create a reviewable asset brief in the active workspace before generation when the task needs multiple rounds or stakeholder feedback.--out values such as docs/briefs are resolved from the project workspace, not from the installed skill directory.--out <project-dir> path or set CODEX_WORKSPACE_ROOT.image_gen tool by default when the host supports it.pack.png concepts or replacements for mods, datapacks, or resource packsbash ./scripts/scaffold-asset-brief.sh --type <asset-type> --name <slug> when the script is already being run from your project workspace.--out values still resolve from the project workspace; if the workspace cannot be inferred, pass an absolute project destination such as bash ./scripts/scaffold-asset-brief.sh --type <asset-type> --name <slug> --out /abs/path/to/project/docs/briefs or set CODEX_WORKSPACE_ROOT.pack-icon-v2.png or release-banner-hero.png.10. If the asset will ship inside a resource pack, hand off final pack wiring to minecraft-resource-pack.
Use a short, labeled spec when the request is not already precise:
Use case: <pack-icon | texture-concept | promo-art | server-banner | ui-mockup>
Asset type: <where the image will be used>
Minecraft context: <vanilla-faithful | modded sci-fi | medieval RPG server | etc>
Primary request: <main prompt>
Input images: <reference or edit target, if any>
Style/medium: <pixel art | painterly splash art | clean UI mockup | product-style render>
Composition/framing: <close-up | square icon | wide banner | negative space left>
Palette: <color direction>
Pixel treatment: <flat tileable | hand-painted | chunky retro | crisp UI>
Text (verbatim): "<exact text>"
Constraints: <must keep / must avoid>
Avoid: <negative constraints>
For edits, explicitly say what must stay unchanged, for example: change only the background; keep the logo, silhouette, and text layout unchanged.
64x64 icon manually if needed.pack.png Refreshpack.png.pack-v2.png.minecraft-resource-pack for final pack structure, sizing, tiling, and JSON wiring.Pack icon:
Use case: pack-icon
Asset type: resource-pack icon
Minecraft context: vanilla-faithful fantasy mining pack
Primary request: a glowing emerald pickaxe crossed over a cave entrance
Style/medium: crisp pixel-art-inspired emblem
Composition/framing: centered square icon with bold silhouette
Palette: emerald green, deepslate gray, warm torch gold
Constraints: no text, no watermark, readable at very small size
Texture concept:
Use case: texture-concept
Asset type: reference sheet for a block texture
Minecraft context: modded industrial factory pack
Primary request: concept art for a rusted steel machine casing block
Style/medium: flat texture concept
Composition/framing: straight-on tile, no perspective
Pixel treatment: tileable, lighting-neutral, easy to simplify into 16x16 or 32x32
Constraints: no background scene, no labels, no watermark
Promo banner:
Use case: promo-art
Asset type: GitHub release banner
Minecraft context: cooperative sky-islands server
Primary request: sweeping hero art of floating islands linked by rope bridges and glowing lanterns
Style/medium: polished cinematic illustration
Composition/framing: wide banner with negative space on the left for release text
Palette: sunrise oranges, cool blue shadows, warm lantern gold
Constraints: no logos, no watermark, no tiny unreadable text
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for presentations, documentation, or social media posts.
Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.
Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.
Microscopy data management platform. Access images via Python, retrieve datasets, analyze pixels, manage ROIs/annotations, batch processing, for high-content screening and microscopy workflows.
Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.
This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.
Take jahrome907/minecraft-imagegen from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.