segment_object_pointcloud
100 / 100 · Low risk
Fine to try.
Clean multi-view point cloud of a named object. Runs Grounded-SAM on each camera, optionally verifies each mask with a sub-VLM yes/no check ("is this really {object}?"), unprojects survivors to world XYZ, fuses across cameras. Replaces ad-hoc per-skill SAM+unproject pipelines and shields downstream PCA / functional-point estimation from GroundingDINO false-positives (e.g. red robot-base detected as "coloured block").
What this skill can do
We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'segment-object-pointcloud' ] || [ -L ~/.agents/skills/'segment-object-pointcloud' ]; then echo 'A skill folder named segment-object-pointcloud already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/nssmd/RoboRSI' "$d" && git -C "$d" checkout --quiet '90c8569705bf4004a4f79e34e650c87ab7f075d4' -- 'roborsi/embodied/skills/base/segment_object_pointcloud/robotwin' && mkdir -p ~/.agents/skills && cp -R "$d"/'roborsi/embodied/skills/base/segment_object_pointcloud/robotwin' ~/.agents/skills/'segment-object-pointcloud' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'segment-object-pointcloud' ~/.claude/skills/'segment-object-pointcloud' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/nssmd/RoboRSI/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-13 | 90c8569 | 100 |