Claude Skills by sideshowroberto

Blender addon development - operator design, UI panels, bpy.props, poll() methods, and registration systems. Use when creating addons, building operators, designing UI panels, or when user mentions "addon," "operator," "UI panel," or "Blender Python."

Keyframe animation, rigging, constraints, and armatures in Blender. Use for animation, rigging, camera movement, or when user mentions "animate," "keyframe," "rig," or "armature."

Blender API compatibility across versions (4.2 -> 5.1+), breaking changes detection, and migration strategies. Use for API errors, version migration, breaking changes, or when user mentions "compatibility," "breaking change," "migration," "API error," or "doesn't work in newer Blender."

Compositor nodes, post-processing, and color grading in Blender. Use for compositing workflows, render pass integration, post-processing, color correction, or when user mentions "compositor," "post-process," "color grade," or "render passes."

Set up and render ControlNet conditioning passes from a Blender scene for AI image/video generation - grey clay override, compositor-normalized depth, cryptomatte EXR, optional wireframe overlay for temporal consistency. Wraps Blender/scripts/setup_controlnet_passes.py (Blender 5.x APIs, test-slice discipline, trailing-dot File Output naming). Use when preparing depth/edge conditioning inputs, clay renders for video models, or crypto mattes for comp. Triggers: \"controlnet passes\", \"render ...

Procedural modeling using Geometry Nodes in Blender. Use for scattering systems, node trees, parametric design, or when user mentions "procedural," "geometry nodes," "scattering," or "instances."

2D animation and Grease Pencil workflows in Blender. Use for 2D animation, hand-drawn animation, mixed media, stroke creation, layer management, or when user mentions "2D," "grease pencil," "hand drawn," "traditional animation," "NPR rendering," or "stylized animation."

Shader nodes, PBR materials, and procedural textures in Blender. Use for material creation, shader setups, PBR workflows, cross-engine compatibility (EEVEE_NEXT/Cycles), or when user mentions "material," "shader," "PBR," "texture," "node tree," or "Principled BSDF."

Physics simulations including particles, fluids (Mantaflow), rigid/soft body, and cloth in Blender. Use for physics, particles, fluid simulations, or when user mentions "physics," "particle," "fluid," "rigid body," "soft body," "cloth," "fire," "smoke," or "hair."

EEVEE_NEXT and Cycles rendering, lighting, and render optimization in Blender. Use for rendering setup, lighting, render settings, or when user mentions "render," "lighting," "EEVEE," "Cycles," or "materials."

Terrain creation, organic modeling, and surface details using Blender sculpting tools. Use for terrain, organic shapes, sculpted details, or when user mentions "sculpt," "terrain," or "organic."

ComfyUI advanced node patterns - MatchType, Autogrow, DynamicCombo, node expansion, MultiType, wildcard inputs. Use when building complex nodes with dynamic inputs, type matching, or node expansion.

ComfyUI custom node fundamentals - V3 node structure, Schema, inputs/outputs, registration. Use when creating new ComfyUI custom nodes, defining node classes, or setting up a custom node project.

ComfyUI data types - IMAGE, LATENT, MASK, CONDITIONING, MODEL, CLIP, VAE, AUDIO, VIDEO, 3D types, widget types, and custom types. Use when working with ComfyUI tensors, model types, or defining input/output data types.

ComfyUI frontend JavaScript extensions - hooks, widgets, sidebar tabs, commands, settings, toasts, dialogs. Use when adding UI features to custom nodes, creating custom widgets, or extending the ComfyUI frontend.

ComfyUI node input types - INT, FLOAT, STRING, BOOLEAN, COMBO widgets, hidden inputs, optional inputs, lazy inputs, force_input. Use when configuring node inputs, adding widgets, or customizing input behavior.

ComfyUI node execution lifecycle - caching, fingerprint_inputs/IS_CHANGED, validate_inputs/VALIDATE_INPUTS, check_lazy_status, execution order. Use when debugging execution, implementing caching control, input validation, or understanding execution flow.

ComfyUI V1 to V3 node migration - converting legacy nodes to the V3 API. Use when migrating existing custom nodes from V1 to V3, understanding differences between API versions, or modernizing node code.

ComfyUI node output types - NodeOutput, UI outputs, PreviewImage, PreviewMask, SavedImages, PreviewAudio, PreviewText, PreviewVideo. Use when returning results from nodes, displaying previews, or saving output files.

ComfyUI custom node project structure - directory layout, __init__.py, registration, requirements.txt, publishing, WEB_DIRECTORY. Use when setting up a new custom node project, packaging nodes, or publishing to the registry.

Analyze downloaded ComfyUI workflow JSON files to extract required custom nodes and models, map them to correct install locations, and generate a setup checklist. Use when user shares a workflow JSON, asks "what nodes does this need", "what models does this use", "help me set up this workflow", or "analyze this comfy workflow".

Generate photoreal anchor keyframes from CG previs for reference-guided video generation (Seedance-class models). Covers previs shading for AI readability, anchor frame selection, bootstrapping action-pose reference sets from a single reference, lighting-accurate prompt language, and validation. Use when converting previs/CG animation to photoreal video, preparing anchor/reference frames for a video model, or when generations ignore CG placement or pose. Triggers on "anchor keyframes", "ancho...

Create and manage Houdini Digital Assets (HDAs) including parameter interfaces, compilation, versioning, and asset organization. Use when authoring reusable Houdini tools. Triggers: hda creation, digital asset, hda compile, hda parameters, create hda

Create procedural geometry workflows using SOPs including scattering, copying, instancing, and parametric modeling. Use for procedural modeling workflows. Triggers: procedural generation, scatter, copy to points, procedural modeling, sops

Automate Houdini workflows using Python (HOM - Houdini Object Model) including node creation, parameter manipulation, scene management, and batch processing. Use when scripting Houdini workflows. Triggers: houdini python, hom, python script, automate houdini, batch process

Work with USD (Universal Scene Description) in Houdini Solaris including stage creation, layer composition, variants, and USD export workflows. Use for USD workflows and Solaris. Triggers: solaris, usd, stage, layer, variant, usd export

Write VEX code for Houdini including wrangles, custom operations, attribute manipulation, and performance optimization. Use when writing VEX scripts or custom operations. Triggers: vex, wrangle, vex code, attribute wrangle, point wrangle

Magnific MCP image generation skill. Use when generating ANY images, concept art, product shots, reference images, or visual assets - Magnific is the default image generation tool. Also use for selecting models, resolution/aspect ratio, adding references, browsing/creating folders, upscaling, or generating variations. Triggers on: \"generate image\", \"generate images\", \"generate refs\", \"generate reference\", \"reference images\", \"image refs\", \"generate concept\", \"product shot\", \"...

Upload local images to Magnific as references for generation, then download outputs to a local folder. Use when user wants to upload photos from a local folder or drive, use local files as image/style references in Magnific, batch upload from a directory, move uploads to a Magnific folder, or save/download Magnific generated images to a local path. Triggers: \"upload local images\", \"use local photos as reference\", \"upload from folder\", \"upload these images to magnific\", \"download magn...

Magnific MCP video generation skill. Use when generating video via Magnific, selecting video models, animating stills, using start/end keyframes, camera motion, audio/lipsync, multishot, or video upscale. Triggers on: \"generate video with magnific\", \"magnific video\", \"animate this image\", \"magnific camera motion\", \"seedance\", \"kling video\", \"veo video\", \"video from still\".

Create and assign materials in Maya via MCP - Arnold (aiStandardSurface), Lambert, Blinn, and USD Preview Surface. Use for shader creation, texture assignment, material assignment to geometry, and look dev workflows. Triggers on "maya material", "assign shader", "aiStandardSurface", "maya texture", "look dev".

Query and manipulate Maya scene objects, transforms, hierarchy, and attributes via MCP commandPort. Use for listing scene contents, creating geometry, setting transforms, parenting objects, selecting, importing/exporting FBX. Triggers on "maya scene", "list objects", "create sphere", "cmds.ls", "FBX export from Maya".

BlinkScript kernel development for Nuke with GPU acceleration, composition grids, procedural patterns, and custom effects. Use when creating BlinkScript kernels, GPU-accelerated effects, or when user mentions blinkscript, blink kernel, nuke kernel, custom kernel, GPU effect.

PyTorch model integration in Nuke via CatFileCreator and Inference nodes. Use when tracing ML models for Nuke, setting up depth estimation, AI-powered effects, or when user mentions CatFileCreator, .cat file, Inference node, cattery, TorchScript, depth model, DA3, DepthAnything, or ML inference in Nuke.

Node graph compositing workflows for Nuke including Read/Write setup, grading, merging, keying, and multi-layer comp patterns. Use when setting up comps, creating node graphs, or when user mentions nuke comp, node graph, grade, merge, keying, aov.

Production-tested patterns for creating robust Nuke node trees programmatically. Use for avoiding auto-connection issues, dynamic positioning, expression masks, and gradient blending.

ParticleBlinkScript node development for NukeX 16+ - custom particle systems, GPU particle physics, and Foundry gadget templates. Also covers procedural BlinkScript atmospheric effects (snow, embers, dust) that bypass the particle system entirely. Use when user mentions particle blinkscript, ParticleBlinkScript node, custom particles nuke, blinkscript particles, GPU particles nuke, particle gadgets, procedural snow nuke, atmospheric blinkscript.

Python scripting for Nuke with NukeMCPLogger integration, script templates, and automation patterns. Use when writing Nuke Python scripts, using NukeMCPLogger, automating comps, or when user mentions nuke python, nuke script, nuke logger, nuke automation.

Batch shot setup for Nuke comp projects. Parses a ShotGrid CSV export, reads plate metadata from a plates CSV (or scans plates on disk), creates per-shot folder structures, generates Nuke v001 visdev/comp files with plates auto-connected (Read + Stamp/Anchor with proper ACES colorspace), and produces a Google Sheets-ready CSV shot tracker. Supports multiple sequences at once, show-specific config (OCIO, LUT, compression), and configurable work context (visdev, comp). Use when the user wants t...

Automated image tiling for ML processing in Nuke with seamless gradient blending. Use for large plates (4K+) through ML nodes (ViTMatte) optimized for 1K-2K tiles.

This skill should be used when directing Seedance 2.0 T2V, I2V, V2V, R2V, audio, safety, or API work.

This skill should be used when a Seedance 2.0 prompt contains generic AI filler, hollow superlatives, vague cinematic language, bloated adjectives, weak verbs, or needs sharper production-specific wording.

This skill should be used when the user asks for camera movement, shot scale, lens feel, framing, one-take direction, dolly, pan, tilt, push-in, handheld, aerial, macro, or camera-transfer guidance for Seedance 2.0.

This skill should be used when the user asks for character consistency, character tags, identity lock, multi-character blocking, wardrobe continuity, hand safety, expression control, or likeness-sensitive character guidance.

This skill should be used when the user wants a fast Seedance 2.0 creative brief, a short interview, a compressed intake flow, or a quick director-style clarification before prompt writing.

This skill should be used when the user has a vague Seedance 2.0 video idea and asks for creative guidance, story development, scene planning, a director interview, or help turning an undeveloped concept into a production-ready prompt.

This skill should be used when the user asks for lighting design, atmosphere, time of day, color temperature, shadow, reflections, weather light, practical lights, or mood transitions in Seedance 2.0.

This skill should be used when the user asks for body action, choreography, physics, object movement, movement timing, action continuity, stunt direction, or motion-reference mapping in Seedance 2.0.

This skill should be used when the user asks about Seedance 2.0 workflow operations, API planning, BytePlus ModelArk, Dreamina/Jimeng surfaces, ComfyUI, post-production, stitching, batch workflow, or integration planning.

This skill should be used when the user asks for a compact Seedance 2.0 prompt, short Chinese prompt, prompt compression, 30-100 word output, or removal of unnecessary prompt language.