mcpbeat Sign in

Texture Assembler Agent Skill

>- Guide for using the texassemble command-line tool to create cubemaps, volume maps, texture arrays, and other assembled DDS textures from individual images. Use this skill when asked about creating cubemaps, volume textures, texture arrays, merging channels, converting animated GIFs to textures, or extracting cubemap faces to cross/strip layouts.

5k tokens
context cost
the whole folder, loaded on every use
3
files
instructions only
0
copies elsewhere
how many repositories repackaged it
2136
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/microsoft/DirectXTex --skill texture-assembler

What comes with it

11 517 bytes besides the instruction
reference/examples.md
reference/options.md

The instruction itself

22 sections, as written by the author

Texassemble Texture Assembler

This skill provides guidance for using the texassemble command-line tool to create DDS files containing cubemaps, volume maps, or texture arrays from individual images.

When to Use

Invoke this skill when:

  • Creating cubemaps from six individual face images.
  • Creating volume (3D) textures from multiple slice images.
  • Creating 1D or 2D texture arrays from multiple images.
  • Creating cubemap arrays from multiple sets of face images.
  • Extracting cubemap faces into cross, strip, or tee layout images.
  • Creating cubemaps from cross, strip, or tee layout images.
  • Merging channels from two images into one output.
  • Converting animated GIFs into texture arrays.
  • Creating textures with custom mipmap levels from individual mip images.

Installation

winget install Microsoft.DirectXTex.Texassemble

vcpkg

vcpkg install directxtex[tools]

Syntax

texassemble <command> [options] [--file-list <filename>] <file-name(s)>

Input files can be dds, tga, hdr, or any WIC-supported format (bmp, jpg, png, jxr, heif, webp, etc.).

The command-line uses Windows-style - or / for options. It also supports --version, --help, and GNU long-option style parameters with --.

Commands

| Command | Description |

| --- | --- |

| cube | Creates a cubemap from six face images (ordered: +X, -X, +Y, -Y, +Z, -Z) |

| volume | Creates a volume (3D) texture from two or more images (depth = image count) |

| array | Creates a 1D or 2D texture array from two or more images (requires FL 10.0+) |

| cubearray | Creates a cubemap array from a multiple of six images (requires FL 10.1+) |

| h-cross | Extracts cubemap faces into a horizontal cross layout image |

| v-cross | Extracts cubemap faces into a vertical cross layout image |

| v-cross-fnz | Same as v-cross but flips the negative-Z face |

| h-strip | Extracts cubemap faces into a horizontal strip image |

| v-strip | Extracts cubemap faces into a vertical strip image |

| h-tee | Extracts cubemap faces into a horizontal "T" layout image |

| cube-from-hc | Creates a cubemap from a horizontal cross layout image |

| cube-from-vc | Creates a cubemap from a vertical cross layout image |

| cube-from-vc-fnz | Creates a cubemap from a vertical cross layout (flipped -Z) image |

| cube-from-ht | Creates a cubemap from a horizontal tee layout image |

| cube-from-hs | Creates a cubemap from a horizontal strip image |

| cube-from-vs | Creates a cubemap from a vertical strip image |

| array-strip | Extracts a 1D/2D array into a horizontal strip image |

| merge | Creates a texture by merging channels from two input images |

| gif | Converts an animated GIF into a texture array |

| from-mips | Creates a 2D mipmapped texture from individual mip images |

| cube-from-mips | Creates a cubemap texture from individual mip images |

Common Workflows

Create a cubemap from six face images

texassemble cube -w 256 -h 256 -o cubemap.dds posx.jpg negx.jpg posy.jpg negy.jpg posz.jpg negz.jpg

Create a volume (3D) texture

texassemble volume -w 256 -h 256 -o volume.dds slice0.png slice1.png slice2.png slice3.png

Create a texture array

texassemble array -o array.dds frame0.png frame1.png frame2.png frame3.png

Extract cubemap to horizontal cross layout

texassemble h-cross cubemap.dds

Create cubemap from a vertical cross image

texassemble cube-from-vc -o cubemap.dds cross_layout.png

Merge channels from two images

texassemble merge -o combined.png color.png alpha_source.bmp

Merge with custom swizzle (roughness into alpha)

texassemble merge --swizzle rgbR -o packed.png albedo.png roughness.png

Convert animated GIF to texture array

texassemble gif -o animation.dds animated.gif

Create mipmapped texture from individual mip images

texassemble from-mips -o texture.dds mip0.png mip1.png mip2.png mip3.png

Options Reference

See reference/options.md for the complete options reference.

Quick Reference (most common options)

| Option | Description |

| --- | --- |

| -o <file> | Output filename (default: DDS based on first input, BMP for cross/strip) |

| -f <format> | Output DXGI format (e.g., R8G8B8A8_UNORM, B8G8R8A8_UNORM) |

| -w <n> / -h <n> | Output width / height in pixels |

| -if <filter> | Image filter (POINT, LINEAR, CUBIC, FANT, BOX, TRIANGLE) |

| -srgb | Input and output are sRGB |

| -y | Overwrite existing output file |

| -dx10 | Force DX10 header extension |

| -fl <level> | Target feature level (default: 11.0, max texture size: 16384) |

| --swizzle <mask> | Channel swizzle for merge command |

| --strip-mips | Strip mipmaps from input textures |

| -r | Recursive wildcard search |

| -nologo | Suppress copyright message |

Output Format

By default, texassemble writes DDS files. The output filename is derived from the first input file with a .dds extension. For cross/strip extraction commands, the default output is a .bmp file and you can specify any supported image extension.

Notes

  • The tool does not support mipmap generation or texture compression. Use the texture-converter skill to further process the resulting DDS file.
  • Any texture-compressed input file is decompressed on load.
  • Partial cubemaps are not supported; all six faces must be provided.
  • Cubemap face order is: positive-X, negative-X, positive-Y, negative-Y, positive-Z, negative-Z.
  • Support for OpenEXR (exr) format requires building from source with USE_OPENEXR defined.
  • Additional WIC codecs (HEIF, WEBP) work automatically if installed on the system.
  • Texture arrays require Direct3D feature level 10.0 or better hardware.
  • Cubemap arrays with more than one cubemap require feature level 10.1 or better.

Further Reading

Other skills for the same job

different authors, same section of the catalogue
Legacy Circuit Mockups
by github
vendor ×1

Generate breadboard circuit mockups and visual diagrams using HTML5 Canvas drawing techniques. Use when asked to create circuit layouts, visualize electronic component placements, draw breadboard diagrams, mockup 6502 builds, generate retro computer schematics, or design vintage electronics projects. Supports 555 timers, W65C02S microprocessors, 28C256 EEPROMs, W65C22 VIA chips, 7400-series logic gates, LEDs, resistors, capacitors, switches, buttons, crystals, and wires.

37k tokens
Hyperframes Keyframes
by aiskillstore
×1

> Use when a HyperFrames composition needs seek-safe 2D/3D keyframes, GSAP timelines, CSS keyframes, Anime.js, WAAPI, FLIP, paths, masks, SVG morph/draw, text trails, 3D depth, or `hyperframes keyframes` diagnostics. Don't use for broad scene strategy, brand design, media sourcing, captions, or general video planning.

17k tokens
Anydesign
by uxKero
×1

Analyze images, websites, and Figma files to extract their design and generate a `design.md` with token system, component inventory, and reconstruction notes. Use this skill whenever the user wants to understand, document, replicate, or audit the design of something visual: a screenshot, a URL, a Figma link, a Pinterest reference, a mockup, a competitor's site, a component, a dashboard, a landing page. Also when they ask 'extract the design system from X', 'document the style of Y', 'analyze this visually', 'convert this image into tokens', 'help me replicate this design', 'what palette does this site use', 'how is this built'. Also for single elements: 'copy this navbar', 'recreate this illustration', 'give me a prompt to regenerate this graphic' — element mode outputs a focused element.md, with token-grounded image-model prompts when the element is visual art. If the user brings any visual source and wants to understand it at a design level — this skill should activate.

728k tokens scripts
Brandkit
by lornshrimp
×1

Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional logo concepting, refined composition, sparse typography, strong symbolic meaning, premium mockups, art-directed imagery, and flexible grid layouts.

4k tokens
Imagegen Frontend Mobile
by lornshrimp
×1

Elite mobile app image-generation skill for creating premium, app-native screen concepts and flows. Designed for iOS, Android, and cross-platform mobile products. Prioritizes clean hierarchy, comfortably readable text, strong multi-screen consistency, controlled color palettes, non-generic creative direction, textured surfaces, image-led composition, tasteful custom iconography, and clean phone mockup framing. By default, screens should be shown inside a subtle premium iPhone or similar phone mockup with a visible frame, while the main focus stays on the app content itself. This skill generates images only. It does not write code.

10k tokens
Perf Web Optimization
by christophacham
×1

Optimize web performance: bundle size, images, caching, lazy loading, and overall page speed. Use when site is slow, reducing bundle size, fixing layout shifts, improving Time to Interactive, or optimizing for Lighthouse scores. Triggers on: web performance, bundle size, page speed, slow site, lazy loading. Do NOT use for Core Web Vitals-specific fixes (use core-web-vitals), running Lighthouse audits (use perf-lighthouse), or Astro-specific optimization (use perf-astro).

4k tokens
Brandkit
by nexu-io

| Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional logo concepting, refined composition, sparse typography, strong symbolic meaning, premium mockups, art-directed imagery, and flexible grid layouts.

4k tokens
Gsap Performance
by nexu-io

| Official GSAP skill for performance — prefer transforms, avoid layout thrashing, will-change, batching. Use when optimizing GSAP animations, reducing jank, or when the user asks about animation performance, FPS, or smooth 60fps.

1k tokens

How to use it

Copy the folder

Take microsoft/texture-assembler from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

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.