verifying-placement

SkillDev tools

Confirms from one RGB-D view that a released object went through an aperture, accepting either that it vanished into the container or that its visible centre lies below the rim within the opening's footprint, and routing not_placed when it is still visible above or beside the aperture. Use when an insertion-and-release must be checked without simulator state, after the release has completed.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the verifying-placement skill

What this skill tells your AI

The instructions your AI receives, as published by graph-robots/open-robot-skills in skills/verifying-placement/SKILL.md and read by ahel’s review.

Use once, after executing-feature-mating has released the object. Take a fresh observation and call verify_placement with the aperture the fixture perception measured (aperture_center, rim_z).

The script segments object_description in camera_name. Below score_min the object is taken to have disappeared into the container, which is verified. Otherwise its mask is back-projected and the median must lie more than depth_margin_m below rim_z and within xy_tolerance_m of the aperture centre in XY; anything else, including a mask with fewer than min_points valid depth points, routes not_placed with the evidence spelled out. The script never raises on a verdict.

Boundaries

  • Only meaningful for an opaque container after a completed release; an object still in the gripper would also "disappear" from an overhead view.
  • No simulator query or object pose is read.

Signals

GitHub stars
41
Forks
7
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
verifying-placement
Source
github.com/graph-robots/open-robot-skills