# Geometry

> Pure-math 3D geometry toolbox — back-project masks and depth to

- **Type:** Skill
- **Install:** `agentstack add skill-graph-robots-open-robot-skills-geometry`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [graph-robots](https://agentstack.voostack.com/s/graph-robots)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** Apache-2.0
- **Upstream author:** [graph-robots](https://github.com/graph-robots)
- **Source:** https://github.com/graph-robots/open-robot-skills/tree/main/tools/geometry

## Install

```sh
agentstack add skill-graph-robots-open-robot-skills-geometry
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# 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.

## Install

```bash
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.)
- `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.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [graph-robots](https://github.com/graph-robots)
- **Source:** [graph-robots/open-robot-skills](https://github.com/graph-robots/open-robot-skills)
- **License:** Apache-2.0

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-graph-robots-open-robot-skills-geometry
- Seller: https://agentstack.voostack.com/s/graph-robots
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.