菜单
Recommend optimal Metashape processing settings based on dataset size and available RAM. Provides specific parameter values for each processing step with quality/speed trade-offs.
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
Guide UV mapping, texture atlas generation, color calibration, and texture quality optimization in Metashape MCP. Covers blending modes, ghosting filter, texture size selection by use case, and diagnosing common texture artifacts. Works through the Metashape MCP server.
Export all available products from the current Metashape project — point cloud, model, DEM, orthomosaic, tiled model, report, and cameras. Skips unavailable products automatically.
Diagnose alignment quality issues in the current Metashape project — checks camera alignment rate, tie point density, reprojection error, and sensor calibration. Provides actionable fix recommendations.
Download USGS 3DEP LiDAR DEM data, colorize with satellite imagery, and import into Metashape as laser scan ground truth. Use when extending photogrammetry environments with surrounding terrain.
Guide dense reconstruction, mesh building, and texturing in Metashape MCP. Covers depth maps, point cloud, mesh, texture, DEM, and orthomosaic generation with correct GPU/CPU settings and quality parameters. Works through the Metashape MCP server.
Set up a new Metashape project from scratch — import photos, load GPS reference, configure sensors (fisheye, rolling shutter, multi-camera), import EXR alpha masks, run image quality analysis, and disable bad frames. The first skill to use on any new capture. Works through the Metashape MCP server.
| name | quality-settings |
| description | Recommend optimal Metashape processing settings based on dataset size and available RAM. Provides specific parameter values for each processing step with quality/speed trade-offs. |
| user-invocable | true |
Recommend processing parameters tuned to the user's dataset and hardware.
Ask the user (or read from the project):
| Setting | <100 photos | 100–500 | 500–2000 | 2000+ |
|---|---|---|---|---|
| Match downscale | 1 (High) | 1 (High) | 2 (Medium) | 2–4 |
| Keypoint limit | 60000 | 40000 | 40000 | 40000 |
| Depth map quality | 2 (High) | 4 (Medium) | 4 (Medium) | 8 (Low) |
| Depth filter | mild | mild | moderate | moderate |
| Face count | high | high | medium | medium/custom |
set_gpu_config(cpu_enable=True) — BEFORE alignment (match_photos, align_cameras)set_gpu_config(cpu_enable=False) — BEFORE everything else (depth maps, meshing, texturing, DEM, ortho)CPU slows GPU operations. It is ONLY beneficial for alignment.
Read the chunk info, then provide specific parameter values for each processing step as ready-to-use tool calls.