Authoring skill - create, connect, configure, cook, lay out, and delete Houdini nodes through typed HOM operations. Use when building SOP/OBJ/ROP networks or automating graph edits. Not for arbitrary Python snippets.
Authoring skill — object-level Houdini mutations: rename, duplicate, reparent, set display/render/template/bypass flags, hard-lock/unlock, and read/set pivot and translate-rotate-scale transforms. Use these typed tools instead of arbitrary Python for editing existing nodes. Not for creating nodes (use houdini-nodes)…
Authoring skill — inspect and edit Houdini node parameters, parameter templates, spare parameters, and channel expressions through typed atomic tools. Use instead of arbitrary Python for reading/setting parms, adding spare parms, and managing expressions. For node connections use houdini-node-graph.
Pipeline skill — generic, adapter-owned project and shot/package automation: set/query the project root, tag and read portable asset metadata, validate a scene for missing files / bad output dirs / dirty state / cook errors, collect file dependencies into a manifest (no copying), and export a shot/package manifest…
Pipeline skill — viewport capture/flipbook plus ROP render settings and render execution through typed, runtime-aware tools. Exports report writtenfiles, elapsed time, and separate error/warning diagnostics without hanging the host. Pair with houdini-camera-light to set up cameras and lights first.
Scene-management skill — typed Houdini scene lifecycle (new/open/save with dirty-scene safeguards), selection (get/set/find), camera discovery, and bounding-box queries. Use these atomic tools instead of arbitrary Python for everyday scene navigation and file operations. Not for node authoring (use houdini-nodes) or…
Scene skill — read-only inspection of the active Houdini hip file and node graphs. Use when you need the current selection, display-SOP geometry counts, frame range, hip path, object-level nodes, or node details. Not for creating geometry, sims, or exports — use authoring or interchange skills.
Bootstrap skill — controlled Python execution inside Houdini's hython interpreter. Use when no typed Houdini skill covers the task or you need session diagnostics. Not for routine scene edits — prefer houdini-scene or future domain skills.
Pipeline stage — bake ambient occlusion, lighting, texture maps (diffuse, normals, cavity, curvature etc.) from geometry to image files, list bake-compatible geometry with UV info, and transfer maps from high-res source to low-res target. Pair with houdini-render for render output and houdini-materials for shader…
Solaris/USD query skill — read-only inspection of a LOP node's composed Stage. Use it to list prims, inspect one prim, or read bounded attribute values. Not for USD authoring, import, or export.
Typed VEX creation and diagnosis workflow — create or update Wrangle nodes, validate VEX syntax, cook, and collect geometry diagnostics with failure localization. Never degrades to arbitrary script execution; all VEX code is set via typed node parameters only.
Typed COP/Copernicus tools for image-processing networks: create a COP network, build a bounded filter chain, inspect connections, and validate cook errors before handing the result to a render or compositing workflow.
Typed PDG/TOP graph tools for procedural task networks: create TOP containers and nodes, wire dependencies, apply bounded parameters, inspect work-item state, and cook a graph with an explicit readback contract.
Typed DOP simulation tools for Pyro, FLIP, RBD, and Vellum. Create a solver network, apply bounded parameters, inspect solver state, and validate a setup before committing to a long cook.
★not rated 12▲
+1 todayA49 tokens
originalMIT
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: