Published skills
wireframe-to-3d
This skill converts 2D orthographic wireframe PNG drawings into 3D Blender models, exported as glTF/GLB. It's used when you provide wireframe images and want to generate a 3D model or .glb file.
landmark-fit-repair
Validate and repair source-locked Blender models using named landmarks such as leaf tips, shell corners, eyes, smile, rim thickness, aura center/radius, and view-specific depth markers. Use when bbox/IoU is insufficient and the model must align to templates at designed feature points.
fit-repair-optimizer
Turn multiview fit reports into a sequential or parallel repair queue for aligning Blender products to source-of-truth templates. Use after validation shows disalignment, when the agent must iteratively fix wireframe, texture, lighting, or projection mismatches, and when skill gaps should trigger self-refinement before another rebuild.
blender-lighting
Professionally light Blender scenes using three-point setups, HDRI environments, and various configurations like studio, cinematic, or dramatic, managing light groups, color temperature, and shadow types. Use this skill for any lighting-related request, from setting up lighting to achieving specific visual styles.
blender-skill-harmonizer
Harmonize multiple Blender skills into a coherent pipeline with clear activation precedence, handoff artifacts, dependency gates, and conflict-resolution rules. Use when a Blender task spans several skills, when reference-locked work conflicts with generic production workflow, after adding/updating skills, or when repeated failures indicate skill interference or missing inter/intra-play.
reference-to-3d
Reconstruct Blender models from supplied reference sheets, branding templates, texture atlases, orthographic views, or mascot/logo art, where visual fidelity to the source is more important than a plausible generated object. Use when the model must exactly match a template, wireframe, texture pack, character sheet, mascot sheet, or brand asset.
wireframe-to-3d
This skill converts 2D orthographic wireframe PNG drawings into 3D Blender models, exported as glTF/GLB. It's used when users provide wireframe images (like technical or line drawings) to generate a 3D model or .glb file.
orbital-hud-motion
Create tasteful circular/orbital HUD and aura animations around a Blender subject, utilizing source-derived arcs, dots, dashes, opacity, parallax, and restrained motion. This is for decorative circles, halos, or HUD effects that must correlate with a logo/mascot, not appear as random oversized rings.
source-part-segmentation
Segment overlapping visual parts from source images, wireframes, texture atlases, and decals before mesh reconstruction. Use when a mascot/logo/template contains touching or overlapping components and exact structural part masks are needed before contour-to-mesh, UV fitting, or landmark repair.
cc-blender-skill
The Claude Code skill plugin allows driving Blender 5.x like a senior 3D artist via natural language. It offers 10 chain-loadable skills (modeling, materials, lighting, cameras, rendering, animation, export, wireframe-to-3d, pro-workflow), validated on 6 scene classes.
contour-to-mesh
Build Blender mesh surfaces directly from extracted 2D contours/masks instead of approximate primitives. Use for 1:1 mascot/logo reconstruction, exact leaf/petal silhouettes, filled wireframe shapes, shallow bas-relief forms, or when the model outline must match a front template before adding depth.
blender-animation
Animates objects, cameras, lights, and properties in Blender using keyframes, F-curves, easing, shape keys, drivers, and NLA actions for reuse and layering.
mascot-logo-reconstruction
Orchestrate a fail-gated, source-locked Blender reconstruction of mascots, logos, brand avatars, and stylized flat characters from wireframes, texture packs, and orthographic views. Use when the user requires a 1:1 brand/model match rather than a plausible stylized interpretation.
texture-state-animation
Design and validate texture-state transitions for Blender animations without ugly whole-image crossfades, texture popping, misregistered morphs, or target-engine-incompatible Python-only swaps. Use when animating between multiple source textures, mascot/logo states, style states, lightmaps, decals, or UI skins.
blender-pro-workflow
Provides end-to-end production workflow guidance for Blender, detailing scene assembly order (from block-out to export), critique protocols, time budgets, and recovery patterns.
blender-materials
Creates and assigns PBR materials in Blender via Principled BSDF, covering physically-based recipes for metals, glass, plastic, fabric, skin, and organics. It includes features like Coat, Sheen, Subsurface scattering, Transmission, and procedural patterns, for requests like 'make it look like X material'.
blender-uv-texturing
This skill handles UV unwrapping, atlas mapping, texture projection, alpha decals, and baking maps/lightmaps to prepare texture-driven Blender assets for glTF/GLB export. It's used when users provide texture packs, atlases, decals, UV layouts, lightmaps, or report stretched/off textures, aiming for a 1:1 fit.
multiview-fit-loop
Closed-loop compare-adjust-repeat workflow for fitting Blender models to supplied front, side, back, and top templates and originals.
reference-analysis-validator
Measure and validate supplied reference images, wireframes, texture atlases, and Blender renders before declaring a reconstruction 1:1. Use when an asset must match a template, when visual feedback says the output is off, when part counts must be exact, or before exporting a brand mascot/logo reconstruction.
quality-refinement-autoloop
A self-refinement loop runs when a Blender result is subpar, user expectations are not met, validation fails, or repeated issues reveal missing skill depth. This loop diagnoses the gap, decides whether to repair the artifact or acquire/refine a generic skill, sanitizes lessons, updates documentation, validates, and prepares for deployment when requested.
blender-modeling
Create and edit 3D meshes in Blender, using primitives, hard-surface modeling, mesh operators, modifier stacks (Bevel, Subdivision, Boolean, Mirror, Array, Solidify), bmesh-level edits, and retopology. Use for creating, modeling, or sculpting 3D objects, adding shapes, or applying modifiers.
atlas-uv-fitting
Detects texture-atlas regions and maps each source part to its own UV rectangle or projected UV surface. This is used when a texture pack must fit a Blender model 1:1, textures appear off/stretched, alpha decals or lightmaps are provided, or before exporting a textured GLB for a brand mascot/logo.
closed-surface-uv-coverage
Ensure textures and decals cover all visible surfaces of a closed or extruded Blender asset, including caps and sidewalls, rather than relying on partial projections. Use when textures are incomplete or separate UV treatment is needed for different surfaces.
texture-driven-mesh-fitting
Reshape source-locked mesh boundaries so the geometry fits texture-atlas or decal contours 1:1 before final UV/material work. Use when textures look off because the model behind them does not match the source texture region, or when the mesh must adapt to the texture instead of stretching the texture onto an approximate mesh.
multiview-constraint-solver
Determine whether front/side/back/top reference templates can be satisfied by one rigid 3D Blender model, choose a canonical source policy, and emit constraints before rebuilding. Use when multiview bboxes, silhouettes, part counts, or depth ratios contradict each other.
blender-cameras
Sets up Blender cameras with cinematic intent, covering focal length, depth of field, composition, animated movements (orbit, dolly, push-in), and tracking constraints. This skill activates when users request camera setup, framing, cinematic looks, depth of field, or camera animation.
text-to-blender
Drive Blender from natural language. It converts plain-English requests into Blender Python code executed via the Blender MCP server, acting as an orchestrator that picks and chain-loads specialized sub-skills.
orthographic-registration
Register front, side, back, and top orthographic reference views into a shared Blender coordinate contract. Use when a 3D model must match multi-view wireframes/templates, when side/back/top silhouettes are off, or before adding depth to a front-locked contour model.
blender-export
Exports Blender scenes to glTF/GLB (web/AR), FBX (game engines), OBJ (universal), USD (VFX pipelines), and STL (3D printing). Features include per-format settings, texture handling, axis conversion, polygon optimization, and target-platform validation.
reference-look-calibration
Calibrate Blender materials, lighting, and camera settings, including emission/glow and color management, to match reference images using measurable color, brightness, and saturation statistics. This is used when a product must align with a source image's look or when audits identify issues like incorrect brightness, hue, or glow.
blender-rendering
Renders Blender scenes using the appropriate engine and settings, such as Cycles for photorealism or EEVEE for speed, adjusting sample counts, denoising, and color management. Use for any request to render an image or animation.
animation-quality-gate
Validates Blender animation attempts before acceptance by rendering contact sheets and checking silhouette stability, flicker, framing, subject dominance, layer separation, export compatibility, and motion-design coherence. Use after animation renders or when motion, morph, or outside elements appear problematic.
Category alert