open-robot-skills

In the author's own words, from each skill's SKILL.md — showing the first 30 of 43 files.

• molmoact-libero

  Run the MolmoAct LIBERO checkpoint (allenai/MolmoAct-7B-D-LIBERO-0812) as a closed-loop VLA policy for the dexterous pick-and-place segment of a task. Drives a Franka Panda in the LIBERO/robosuite OSC_POSE action space from agentview + wrist cameras, served behind a vLLM-style script speaking the openpi websocket protocol; the policy server is the bundle's own preset (no policy_id). Reads the gra…

  policies/molmoact-libero/SKILL.md on GitHub (opens in a new tab)

• pi05-libero

  Run the openpi π0.5 LIBERO checkpoint (pi05_libero) as a closed-loop VLA policy for the dexterous pick-and-place segment of a task. Drives a Franka Panda in the LIBERO/robosuite OSC_POSE action space from agentview + wrist cameras; the policy server is the bundle's own preset (no policy_id). Reads the graph-scoped observation_stream each window and terminates on a gripper open→close→open cycle, a…

  policies/pi05-libero/SKILL.md on GitHub (opens in a new tab)

• anchoring-a-free-end

  Pins one end of a cable with the support hand before any crossing is attempted — asks the support-hand planner for the anchor grasp as joint-space legs, refuses it when its worst IK error is past the limit, streams the legs, closes the jaws to the plan's own width and dwells for the fingers' travel, and carries the solved chain and grasp orientation out on the exit so later pay-outs seed from the…

  skills/anchoring-a-free-end/SKILL.md on GitHub (opens in a new tab)

• computing-feature-mating-poses

  Computes approach, engaged, and mate TCP poses from a held feature in the hand and a fixture feature, resolving free mate symmetries from the current robot pose without executing motion. Use when a held loop must go over a shaft or hook, or a held shaft or tip must enter an aperture, and explicit approach, engaged, and mate poses are needed for planning.

  skills/computing-feature-mating-poses/SKILL.md on GitHub (opens in a new tab)

• executing-feature-mating

  Executes a supplied feature-mating plan for an already-held rigid object - collision-aware planner legs tracked to millimetre precision, Cartesian servo for short corrections and fixture crossings, contact-controlled seating - then releases and retreats along the fixture axis or straight up. Use when the goal is a constrained mate such as a loop over a shaft, a shaft into an aperture, or a handle…

  skills/executing-feature-mating/SKILL.md on GitHub (opens in a new tab)

• executing-held-object-motion

  Executes an ordered, collision-aware pose sequence for an already-grasped rigid object without releasing it - the escape from support, clear-space rotation, fixture transit and orientation-locked local legs of a carry plan, or only the free-space approach waypoint of a placement plan. Use when a held object must be carried or reoriented before insertion, mating, packing, or sorting, and use execu…

  skills/executing-held-object-motion/SKILL.md on GitHub (opens in a new tab)

• grasping-concave-contour

  Grasp an awkward rigid part by the waists in its own silhouette — take the alpha shape of its point cloud from above, find where that boundary turns inward, and close the jaws across a pair of those inward runs. Use when a part has no graspable long axis and no pair of parallel walls an OBB would find — pliers and scissors gripped at the joint, a spool at its neck, a gear between two teeth, a bul…

  skills/grasping-concave-contour/SKILL.md on GitHub (opens in a new tab)

• grasping-direct-ik

  Direct IK align-then-descend grasping. The gripper pre-rotates to the grasp orientation at a safe height ABOVE the target before descending straight down, avoiding the twist-while-closing failure mode of a blended rotate+descend. The grasp rotation is rebuilt so the hand's declared closing axis (robot.describe_gripper, composed by robot.grasp_frame) closes across the target's short horizontal axi…

  skills/grasping-direct-ik/SKILL.md on GitHub (opens in a new tab)

• grasping-linear-feature

  Fit the full 3D axis of an elongated segmented feature and grasp it with a perpendicular, inclination-aware parallel-jaw pose. Use for handles, rods, shafts, tools, utensils, and other linear parts whose pitch or roll matters; use grasping-short-axis instead when an upright OBB and vertical approach are sufficient.

  skills/grasping-linear-feature/SKILL.md on GitHub (opens in a new tab)

• grasping-short-axis

  Deterministic short-axis-aligned grasp with CuRobo. The grasp pose is computed geometrically (NOT sampled/scored) — the gripper approaches straight down with its finger-opening axis locked to the OBB's SHORTER horizontal axis, so the jaws close ACROSS the narrow dimension of an elongated target. Use for pan/pot handles, bottles, tools, utensils — anywhere the OBB centroid is graspable but orienta…

  skills/grasping-short-axis/SKILL.md on GitHub (opens in a new tab)

• grasping-with-planner

  Top-down grasping via a fast axis-locked linear descend with a collision-aware cuRobo fallback. A single `grasp_descend_linear` node rises, translates over the target, and descends straight down (Z-locked, orientation held) onto the object; if the straight-line solve is infeasible (far-edge reach, no IK for the fixed wrist) it falls back to the cuRobo planner over the candidate fan. Use when the…

  skills/grasping-with-planner/SKILL.md on GitHub (opens in a new tab)

• perceiving-deformable-linear-objects

  Read a cable's ordered 3D centreline from one RGB-D frame and keep it current across a task — seed it from an unobstructed survey, re-fit it cold whenever the whole rod is in view, and fall back to tracking the carried prior only when the fresh fit comes back short. Use when a manipulation loop needs the current shape of a deformable linear object (a cable, rope, or hose) once per step rather tha…

  skills/perceiving-deformable-linear-objects/SKILL.md on GitHub (opens in a new tab)

• perceiving-functional-features

  Locates a language-described functional part of a rigid object or fixture from calibrated RGB-D and fits a typed loop, shaft, tip, aperture, surface, or region feature with a metric centre, axis, and radius, either inside an already-segmented parent or end to end from a described object, protruding shaft, directed tip, or lidded aperture. Use when a manipulation step depends on where a specific p…

  skills/perceiving-functional-features/SKILL.md on GitHub (opens in a new tab)

• perceiving-next-item

  Loop-head perception for pack-all / clean-all-items tasks. From ONE observation it localizes BOTH the destination container (basket, bin, box) AND the next remaining target item, using the pairwise VLM crop tournament with a container-excluding description so the target is never confused with the basket, then makes a clean found / none decision: an item was found (grasp it) or only the container…

  skills/perceiving-next-item/SKILL.md on GitHub (opens in a new tab)

• perceiving-object-parts

  Hierarchical 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 crop (DINO + SAM3), and uncrops + fuses depth to a world-frame OBB/mask/cloud — plus the parent object's OBB and cloud for downstream placement/collision reasoning. Use when the graspable affordance is…

  skills/perceiving-object-parts/SKILL.md on GitHub (opens in a new tab)

• perceiving-objects-oneshot

  Lightweight 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 geometry.filter_and_compute_obb. No pairwise tournament, no multi-view safe-gate. Returns a clean not_found output (no exception) when the VLM answers "none" or DINO emits no detections — making this the rig…

  skills/perceiving-objects-oneshot/SKILL.md on GitHub (opens in a new tab)

• perceiving-objects

  Fast 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-frame point cloud, finished by geometry.filter_and_compute_obb for a clean oriented bounding box, mask, and cloud. Multi-camera rigs get a verified wrist-camera fallback gate. Use when a manipulation work…

  skills/perceiving-objects/SKILL.md on GitHub (opens in a new tab)

• perceiving-relational-correspondences

  Perceives multiple source and destination instances and resolves language-conditioned one-to-one or many-to-one correspondences. Use when an instruction relates instances by spatial order, proximity, appearance, labels, or a shared destination and downstream manipulation needs stable candidate IDs, masks, point clouds, and OBBs. Do not use for single-instance localization or for functional-featur…

  skills/perceiving-relational-correspondences/SKILL.md on GitHub (opens in a new tab)

• perceiving-routing-fixtures

  Survey a cable-routing bench from one overhead RGB-D frame — find every station (spool, cleat) by colour, roundness and height off the work surface, fit the cable's ordered centreline through a text-prompted segmenter, derive the side each crossing owes from the instruction's alternation, and place the physical seat beside each post. Use when a routing plan needs the fixture layout and the starti…

  skills/perceiving-routing-fixtures/SKILL.md on GitHub (opens in a new tab)

• perceiving-sorting-pairs

  Discovers a labelled four-compartment destination from RGB-D and repeatedly perceives one remaining source object with its matching metric destination region, using an identity table the graph supplies for what each label looks like and what its graspable part is called. Use when a workflow must sort several visible objects into compartments identified by printed category labels.

  skills/perceiving-sorting-pairs/SKILL.md on GitHub (opens in a new tab)

• placing-held-feature

  Move a held object so one of its declared features lands on a target point — a ring onto a hook, a tip into a hole, a plug at a bore. Composes the hand pose from the live object pose and the feature's centre in the object's own frame, recomputed each round so in-jaw slip cannot compound. Use for any goal written as "this object's feature at that place"; do NOT drive the hand to the target directl…

  skills/placing-held-feature/SKILL.md on GitHub (opens in a new tab)

• planning-held-object-motion

  Plans the carry and engagement phases for an already-held rigid object: a clearance-first lift, the smallest feasible symmetry-equivalent reorientation, an orientation-locked transit above the fixture, or a direct plan to the approach pose; then a typed engagement or a straight linear insertion, optionally re-observing the held tip from the wrist first. Use when a held object must be brought to a…

  skills/planning-held-object-motion/SKILL.md on GitHub (opens in a new tab)

• plugging-a-cable-end

  Carries a cable's held free end into a terminal port after the last crossing — finds the port by vision as the terminal block furthest from the run's anchored end, takes the delivering hand and its working height from the support-hand planner, stages the carry three sides of a rectangle around the seated crossings at a hand's depth above the bench, drops into the mouth, opens the jaws and retreat…

  skills/plugging-a-cable-end/SKILL.md on GitHub (opens in a new tab)

• proposing-short-axis-grasps

  Propose top-down grasps whose jaws close ACROSS an elongated object's short axis, derived from its oriented box. Use when the object is longer than it is wide, as the first grasp-proposal rung — a handle, a spanner, a screwdriver, a bar, a laid-down bottle — where closing along the length would put the fingers down the object and meet them on each other. Declines when the short axis is wider than…

  skills/proposing-short-axis-grasps/SKILL.md on GitHub (opens in a new tab)

• proposing-side-grasps

  Propose horizontal (side-entry) grasps swept around an object's oriented box — twelve azimuths ranked by jaw margin. Use when top-down access is blocked by an overhead shelf, a lid or a bin wall, or when the object's vertical dimension is the only one the hand can span. Declines when the object is wider than the jaws from every azimuth.

  skills/proposing-side-grasps/SKILL.md on GitHub (opens in a new tab)

• reconstructing-collision-worlds

  Reconstructs a planner collision world from calibrated RGB-D views alone, excluding the grasp target, the robot, and a perceived fixture mask, dropping depth-edge slivers and invalid-depth sheets, and carving the free space an intentional-contact goal needs as an approach tube along a fixture axis or a corridor through a lid aperture. Use when a held-object motion must be planned against obstacle…

  skills/reconstructing-collision-worlds/SKILL.md on GitHub (opens in a new tab)

• registering-held-objects

  Reobserves a grasped rigid object from the wrist cameras, estimates its functional feature in the TCP frame, and fits attached collision spheres, retaining the grasp-time transform at low confidence when the object is not seen. Use when a held object must be localized in the hand right after grasping or re-checked at a pre-contact pose before a fixture engagement.

  skills/registering-held-objects/SKILL.md on GitHub (opens in a new tab)

• seating-a-cable-crossing

  Streams one planned crossing leg of a cable onto a routing station, lets the rod settle, then LOOKS — segments the rod, fits its centreline and counts how much of the curve lies inside the station's seat box on the side the route requires — and reports the fraction honestly rather than assuming the crossing took. It measures and does not correct. Use when a deformable-linear-object route is laid…

  skills/seating-a-cable-crossing/SKILL.md on GitHub (opens in a new tab)

• selecting-reachable-grasp

  Walk a ranked list of candidate grasp poses and take the first the arm can actually reach — IK solves it, the solution lands where it was asked, and (where `sim.clearance` is available) the arm is clear of the scene there. Use after any propose rung. This is the fix for taking candidate 0 on faith and closing the jaws on nothing.

  skills/selecting-reachable-grasp/SKILL.md on GitHub (opens in a new tab)

• tipping-over-a-surface-edge

  Turn a body over on the surface it rests on instead of carrying it — pinch two opposite walls LOOSELY and off centre so the pads act as a pin joint, lift so the surface and gravity stand the body up on its own edge, then press it onto the surface and pull the pins toward you about whichever edge is grounded until it is just past balance, and let go. Use when a rigid grasp cannot transmit the torq…

  skills/tipping-over-a-surface-edge/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 270k stars · 1 skill
• ponytailby DietrichGebert Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote. 164k stars · 6 skills
• agent-skillsby addyosmani Production-grade engineering skills for AI coding agents. 107k stars · 25 skills
• paperclipby paperclipai The open-source app everyone uses to manage agents at work 103k stars · 30 skills
• taste-skillby Leonxlnx Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages 97.3k stars · 13 skills
• archifyby tt-a1i Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more. 84.1k stars · 2 skills