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.
Automates Houdini with Python (HOM) - node creation, parameter manipulation, scene management and batch processing. Use when scripting Houdini workflows, e.g. 'houdini python', 'hom script', 'automate houdini' or batch processing hip files.
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.
Uploads local images to Magnific as generation references, moves them into folders, and downloads outputs to a local path. Use when using local photos as references, batch uploading a directory, or saving Magnific results to a local folder.
Generates video through the Magnific MCP - Seedance, Kling and Veo models, animating stills, start/end keyframes, camera motion, audio/lipsync and multishot. Use for 'magnific video', 'animate this image' or 'video from still'.
Creates and assigns Maya materials via MCP - Arnold aiStandardSurface, Lambert, Blinn and USD Preview Surface. Use for shader creation, texture assignment, assigning materials to geometry or look dev in Maya.
Queries and edits a live Maya scene via the MCP commandPort - objects, transforms, hierarchy, attributes, selection, FBX import/export. Use for listing scene contents, creating geometry, parenting, setting transforms or exporting FBX from Maya.
Writes GPU-accelerated BlinkScript kernels for Nuke - composition grids, procedural patterns, custom pixel effects. Use when creating a BlinkScript or "blink kernel", or a custom GPU effect the standard Nuke nodes cannot do.
Brings PyTorch models into Nuke via TorchScript export, CatFileCreator .cat files and the Inference node, e.g. DepthAnything depth. Use when tracing an ML model for Nuke, building a .cat file, or running ML inference in a comp.
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.
Builds particle effects in Nuke with the ParticleBlinkScript node (NukeX 16+) or procedural BlinkScript for snow, embers and dust on any Nuke. Use when asked for custom GPU particles, particle gadgets or atmospheric particle effects in Nuke.
Writes Nuke Python automation scripts using the NukeMCPLogger pattern so results and logs return through the MCP bridge. Use when scripting Nuke, automating comps, or when "nuke python", "nuke script" or the nuke logger come up.
Batch-creates Nuke visdev or comp v001 files, per-shot folders and a tracker CSV from a ShotGrid CSV and plates data, with ACES Reads and per-show config. Use for "set up shots" or "create comps from csv"; the team job ritual is shot-setup.
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 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 a Seedance 2.0 prompt mentions named characters, franchises, studios, celebrities, public figures, private people, brand logos, copyrighted scenes, songs, voices, or real-person likeness workflows and needs an IP-safe rewrite.
This skill should be used when a Seedance 2.0 prompt is blocked, rejected, silently degraded, or likely to trigger a content filter; or when the user asks for a safer rewrite without losing the creative intent.
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.
★not rated 16 22d agoA45 tokens
MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: