Agent Skills

atlas-uv-fitting

Detect texture-atlas regions and map each source part to its own UV rectangle or projected UV surface. Use when a texture pack must fit a Blender model 1:1, when textures look off/stretched, when alpha decals or lightmaps are provided, or before exporting a textured GLB for a brand mascot/logo.

Install

npx skills add https://github.com/roble3/cc-blender-skill --skill atlas-uv-fitting
SKILL.md

Atlas UV Fitting

This skill exists because assigning a texture material is not the same as fitting a texture.

Supplemental map sanity rule

Do not blindly wire emissive/roughness/bump/lightmap images into every atlas-mapped part. First verify the supplemental map has the same UV layout and semantic region as the basecolor. If it contains aura dots, guide marks, lightmap blobs, or decorations outside the part, leave it disconnected for that mesh and use constant roughness/bump plus explicit edge/glow geometry instead.

Hard rules

  • Atlas textures must be mapped by region; never apply the full atlas to every structural mesh.
  • Front-facing hero surfaces use front-projected UVs or a source-region rectangle.
  • Side/back surfaces use their own UV islands or procedural/baked fills.
  • Roughness, bump, normal, AO, and lightmap images are Non-Color.
  • Alpha decals must use alpha-connected materials and no black backing planes.
  • Base GLB should not include reference planes or optional aura unless explicitly requested.

Workflow

  1. Run scripts/atlas_region_detector.py on basecolor/decal/aura atlases.
  2. Name regions semantically in atlas_regions.json.
  3. Create/activate UV map per mesh.
  4. Remap local 0-1 UVs into the matching atlas rectangle.
  5. Audit the GLB/export material node graph: Principled BSDF + Image Texture nodes.
  6. Render texture overlay validation before export.

Sources distilled

  • Blender UV/Image Texture node uses UV maps for rendered/exported texture output.
  • Blender baking needs UV maps and active image targets.
  • Blender glTF exporter is most reliable with Principled BSDF, UVs, textures, normals.
  • Khronos glTF PBR: base color, metallic/roughness, normal maps are standard channels.

Semantic atlas mapping

Region detection is only a candidate list. For source-locked work, create an atlas_part_map.json that binds each structural part name to exactly one atlas region or declares procedural/no_texture.

Mapping order:

  1. Detect candidate regions from basecolor/decal/lightmap.
  2. Reject decorative/aura/composite-preview regions unless the target is context/aura.
  3. Match structural parts by role, aspect ratio, and relative size.
  4. Manually rename ambiguous regions before automated UV assignment.
  5. Verify supplemental maps share the same region layout before connecting roughness/bump/emission/lightmap.

Do not map a full rosette/composite atlas region onto individual petals unless the mesh is a single rosette sheet. Individual meshes need individual source regions.

Additional script

  • scripts/atlas_region_mapper.py proposes part→atlas-region mappings using aspect/size similarity. Treat output as a draft; semantic names still win.

Related skills

ai-image-generationgenmedia-labs713KGenerate and edit images on RunComfy via the `runcomfy` CLI — a smart router across the full image-model catalog: FLUX 2 (Klein 9B/4B, Pro, Dev, Flash, Turbo, Max), Google Nano Banana 2 / Pro, OpenAI GPT Image 2, ByteDance Seedream 5 / 4-5 / 4-0 and Dreamina 4-0, Alibaba Qwen Image and Z-Image Turbo, Wan 2-7. Covers both text-to-image (t2i) and image-to-image / edit (i2i) endpoints — the skill picks the right model for the user's actual intent (typography precision, photoreal portraits, sub-secoai-image-generation101-skills547KGenerate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stnano-banana-2prime-skills424KGenerate images with Google Nano Banana 2 (Gemini-family flash-tier text-to-image) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Nano Banana 2's strengths (rapid iteration, in-image typography rendering, predictable framing, optional web-grounded context), the resolution-tier pricing, the safety-tolerance dial, and when to route to Nano Banana Pro / GPT Image 2 / Flux 2 / Seedream insteimage-editprime-skills424KEdit images on RunComfy — this skill is a smart router that matches the user's intent to the right edit model in the RunComfy catalog. Picks Nano Banana Edit (batch up to 20, identity-preserving default), OpenAI GPT Image 2 Edit (multilingual in-image text rewrite, multi-ref composition, layout precision), Flux Kontext Pro (single-ref high-fidelity local edit), or Z-Image Turbo Inpaint (mask-driven precise region edit). Bundles each model's documented prompting patterns so the skill gets sharper

Search skills and MCP servers

Fuzzy search across 23,137 skills and servers