How do I install the Geometry skill?

Run npx skillmds@latest add graph-robots/geometry in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Geometry safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Geometry?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Geometry free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.

Who published Geometry?

graph-robots (@graph-robots) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Geometry by graph-robots — Agent Skill

Name: Geometry
Author: graph-robots

Geometry

Pure-math 3D geometry toolbox — back-project masks and depth to point clouds, DBSCAN-filter noise, fit oriented bounding boxes, derive top-down/front grasp poses, and reconstruct collision worlds from RGB-D frames. Use when a workflow needs perception geometry or planner inputs computed on CPU with no model weights.

graph-robots 507c484 6 files · 588.8 KB Updated Sep 17, 2026

File contents

geometry

Pure-math perception/planning geometry as in-process typed tools, from mask back-projection through OBB fitting to grasp-candidate generation, plus the two scalar helpers (geometry.iou, geometry.pose_distance). Fully CPU — no model weights, no GPU.

When to use

Turning a segmentation mask + depth + camera calibration into world-frame points (mask_to_world_points) and an object OBB (filter_and_compute_obb).
Deriving grasp poses from an OBB: top_down_grasp_candidates for tabletop pick (feed the full list to curobo.plan_to_grasp_poses as a goalset), front_grasp_from_obb for horizontal interactions (drawer/door handles).
Building the collision world for the planner: build_world_config with the target's mask in object_masks so the planner can ignore_obstacle_names it.
Estimating feature geometry for constrained mating: use fit_planar_feature for loops/openings and fit_linear_feature for rods/pegs. Their axis signs are geometrically ambiguous, so pass a workcell- or camera-derived normal_hint / axis_hint when direction matters.

Install

uv sync --extra geometry   # open3d + scikit-learn (cv2/scipy come with gap core)
# (pip: pip install -e ".[geometry]")

The module imports lazily — the bundle loads (and the light tools work) without the extra; only OBB fitting, DBSCAN filtering and world reconstruction need open3d/sklearn/cv2.

Gotchas (carried over from the service)

OBB extent is HALF-extents (gap.types convention, same as the proto). compute_obb is upright-only: rotation is around world Z (no 3D tilt), and extents use the 2nd/98th percentile of points, not strict min/max.
Single-camera clouds are 2.5D: only camera-facing surfaces are observed, so OBB centers carry a few cm of depth bias on opaque objects. (The service's rehearsal-sandbox ground-truth snap that compensated for this in-container was deliberately NOT ported — it depended on a /app sandbox file.)
A fitted plane normal has two valid signs and a fitted line has two valid directions. The feature-fit tools expose hints solely to resolve that sign; callers must derive the hint from observed support geometry, camera viewing direction, or a declared workcell frame rather than an evaluator target.
top_down_grasp_candidates default z_offset=-0.04: fingertip 4 cm below the OBB top. With z_offset=0.0 the fingers close above the object (silent empty grip). Grasp Z is clamped to -0.05 m (table-clearance floor; LIBERO table top is at world z=0).
mask_to_world_points keeps only depths in [0.015, 20.0] m (HyRL bounds); invalid/zero-depth pixels are dropped.
filter_noise returns the ORIGINAL cloud unchanged when DBSCAN labels everything noise (defensive fallback, mirrors HyRL).
build_world_config: table removal only runs when table_z_threshold != 0 (typical -0.01); robot-point exclusion is Franka-only (simplified DH FK) and skips non-7-DOF joint states; prefer explicit object_masks over the target_obb projection fallback — masks are pixel-accurate, the OBB projection is a corner-AABB approximation inflated by 2 cm.
top_down_grasp_from_obb yaw is NOT derived from the OBB — fingers may close across the wide axis; use the candidate fan when orientation matters.

---name: geometrydescription: Pure-math 3D geometry toolbox — back-project masks and depth to point clouds, DBSCAN-filter noise, fit oriented bounding boxes, derive top-down/front grasp poses, and reconstruct collision worlds from RGB-D frames. Use when a workflow needs perception geometry or planner inputs computed on CPU with no model weights.license: MIT---# geometryPure-math perception/planning geometry as in-process typed tools, frommask back-projection through OBB fitting to grasp-candidate generation,plus the two scalar helpers (`geometry.iou`, `geometry.pose_distance`).Fully CPU — no model weights, no GPU.## When to use- Turning a segmentation mask + depth + camera calibration into world-frame points (`mask_to_world_points`) and an object OBB (`filter_and_compute_obb`).- Deriving grasp poses from an OBB: `top_down_grasp_candidates` for tabletop pick (feed the full list to `curobo.plan_to_grasp_poses` as a goalset), `front_grasp_from_obb` for horizontal interactions (drawer/door handles).- Building the collision world for the planner: `build_world_config` with the target's mask in `object_masks` so the planner can `ignore_obstacle_names` it.- Estimating feature geometry for constrained mating: use `fit_planar_feature` for loops/openings and `fit_linear_feature` for rods/pegs. Their axis signs are geometrically ambiguous, so pass a workcell- or camera-derived `normal_hint` / `axis_hint` when direction matters.## Install```bashuv sync --extra geometry # open3d + scikit-learn (cv2/scipy come with gap core)# (pip: pip install -e ".[geometry]")```The module imports lazily — the bundle loads (and the light tools work)without the extra; only OBB fitting, DBSCAN filtering and worldreconstruction need open3d/sklearn/cv2.## Gotchas (carried over from the service)- **OBB `extent` is HALF-extents** (gap.types convention, same as the proto). `compute_obb` is upright-only: rotation is around world Z (no 3D tilt), and extents use the 2nd/98th percentile of points, not strict min/max.- Single-camera clouds are 2.5D: only camera-facing surfaces are observed, so OBB centers carry a few cm of depth bias on opaque objects. (The service's rehearsal-sandbox ground-truth snap that compensated for this in-container was deliberately NOT ported — it depended on a `/app` sandbox file.)- A fitted plane normal has two valid signs and a fitted line has two valid directions. The feature-fit tools expose hints solely to resolve that sign; callers must derive the hint from observed support geometry, camera viewing direction, or a declared workcell frame rather than an evaluator target.- `top_down_grasp_candidates` default `z_offset=-0.04`: fingertip 4 cm below the OBB top. With `z_offset=0.0` the fingers close above the object (silent empty grip). Grasp Z is clamped to -0.05 m (table-clearance floor; LIBERO table top is at world z=0).- `mask_to_world_points` keeps only depths in [0.015, 20.0] m (HyRL bounds); invalid/zero-depth pixels are dropped.- `filter_noise` returns the ORIGINAL cloud unchanged when DBSCAN labels everything noise (defensive fallback, mirrors HyRL).- `build_world_config`: table removal only runs when `table_z_threshold != 0` (typical -0.01); robot-point exclusion is Franka-only (simplified DH FK) and skips non-7-DOF joint states; prefer explicit `object_masks` over the `target_obb` projection fallback — masks are pixel-accurate, the OBB projection is a corner-AABB approximation inflated by 2 cm.- `top_down_grasp_from_obb` yaw is NOT derived from the OBB — fingers may close across the wide axis; use the candidate fan when orientation matters.

Frequently asked questions