菜单
Pipeline skill — configure Karma CPU/XPU render settings, material overrides, light mixer, and image output through typed tools. Pair with houdini-render for full render execution and houdini-camera-light for scene setup.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Pipeline skill — viewport capture/flipbook plus ROP render settings and render execution through typed, runtime-aware tools. Exports report written_files, elapsed time, and separate error/warning diagnostics without hanging the host. Pair with houdini-camera-light to set up cameras and lights first.
Scene skill — read-only inspection of the active Houdini hip file and node graphs. Use when you need frame range, hip path, object-level nodes, or node details. Not for creating geometry, sims, or exports — use authoring or interchange skills.
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 (frame range, cameras, output nodes, caches, written files). No dependency on private production services.
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 geometry/transform edits (use houdini-object-ops).
Set up dcc-mcp-houdini for an agent or operator: install Houdini Python dependencies with hython, generate MCP host configuration, guide the user through the Houdini package / 123.py autostart load step, and run a first live-tool smoke prompt.
| name | houdini-karma |
| description | Pipeline skill — configure Karma CPU/XPU render settings, material overrides, light mixer, and image output through typed tools. Pair with houdini-render for full render execution and houdini-camera-light for scene setup. |
| license | MIT |
| compatibility | dcc-mcp-houdini 0.1+, Houdini 20.5+, dcc-mcp-core 0.19.45+ |
| allowed-tools | Bash Read Write Edit |
| metadata | {"dcc-mcp":{"dcc":"houdini","layer":"domain","stage":"pipeline","version":"1.0.0","tags":["houdini","karma","renderer","xpu","cpu","material","light_mixer","lookdev","pipeline"],"search-hint":"karma cpu xpu render samples denoise material override light mixer output exr","tools":"tools.yaml"}} |
Typed Karma renderer configuration tools. All tools are affinity: main.
Parameter writes are defensive (multi-candidate parm names) to tolerate
Karma LOP, Karma ROP, and USD render product variants.
karma: configure_karma — engine (CPU/XPU), samples, noise threshold, denoise.material: set_material_override — global material override with presets
(clay, gray, white, chrome, checker, normals, uv) or custom paths.light_mixer: configure_light_mixer — enable light mixer and adjust
per-light intensity, exposure, and color.output: set_image_output — output path, format (exr/png/jpg/tif with
bit depth), resolution, color space, layer name.configure_karma(node_path="/stage/karmarenderproduct1", device="xpu", pixel_samples=256, noise_threshold=0.01, denoise=true)set_material_override(node_path="/stage/karmarenderproduct1", preset="clay")configure_light_mixer(node_path="/stage/karmarenderproduct1", enable=true, lights=[{"name":"key_light","intensity":1.5},{"name":"rim_light","exposure":0.5}])set_image_output(node_path="/stage/karmarenderproduct1", output_path="/tmp/render/beauty.$F4.exr", format="exr", resolution=[1920,1080], color_space="ACES - ACEScg")houdini-render (render_rop) for execution