graph-robots/open-robot-skills
18 skills
$npx skills add graph-robots/open-robot-skillsSkillInstalls
curoboNVIDIA cuRobo motion planning — collision-free trajectories togemini-erOpen-vocabulary 2D object detection via the Gemini Robotics-ERgeometryPure-math 3D geometry toolbox — back-project masks and depth tograsping-direct-ikDirect IK align-then-descend grasping. The gripper pre-rotates tograsping-short-axis--- name: grasping-short-axis description: Deterministic short-axis-aligned grasp with CuRobo. The grasp pose is computed geometrically (NOT sampled/scored) — the gripper approaches straight down grasping-with-plannerTop-down grasping via a fast axis-locked linear descend with agrounding-dinoGrounding DINO zero-shot object detection — natural-languagemolmoVisual pointing and Q&A via the Molmo VLM served from amolmoact-liberoRun the MolmoAct LIBERO checkpointperceiving-next-item--- name: perceiving-next-item description: > Loop-head perception for pack-all / clean-all-items tasks. From ONE observation it localizes BOTH the destination container (basket, bin, box) AND tperceiving-object-partsHierarchical perception for subpart targeting. Detects a parent object first (DINO+VLM), crops the camera image to the parent's bounding box, then detects and segments the named subpart inside the croperceiving-objectsFast single-path 3D object perception. Runs Grounding-DINO broad detection, a pairwise VLM crop tournament to identify the target box, SAM3 box segmentation, and depth back-projection to a world-frameperceiving-objects-oneshotLightweight one-shot 3D object perception. Runs Grounding-DINO broad detection, a SINGLE VLM set-of-marks letter pick over the labeled boxes, SAM3 box segmentation, depth back-projection, and geometrypi05-liberoRun the openpi π0.5 LIBERO checkpoint (pi05_libero) as asam3Segment Anything 3 — text-, point-, and box-prompted instancetracking-objectsLong-running skill that drives the SAM3 tracker from thetransporting-objectsMove the currently-held object to a destination and release. ThevlmFree-form and yes/no visual question answering against a hosted