Skip to the rows

agentsclimarketplace

Grasping direct ik

Skill graph-robots/open-robot-skills/skills/grasping-direct-ik

Skill and tool bundles for gap (graph as policy) — Anthropic Agent Skills format, discovered by path

Install

npx -y skills add graph-robots/open-robot-skills --skill grasping-direct-ik

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its author says it does

Copied from the file, not written here

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. Use when no trajectory planner (curobo) is deployed or the scene is uncluttered enough that a straight-line approach is safe.

SKILL.md

5.5 KB, as published. Nobody here has run it

grasping-direct-ik

Direct-IK grasp: rotate the gripper to grasp orientation at a safe height above the target, then descend straight down, then close. No trajectory planner — works on platforms where CuRobo is not deployed, or in uncluttered scenes where planning is overkill.

When to use

The curobo tool bundle is not deployed (no collision-aware planner available).
The scene is uncluttered enough that a straight-line approach is safe.

When NOT to use

Cluttered scenes where the arm must thread between obstacles. Prefer grasping-with-planner if available.

Recommended subgraph state flow

The subgraph state machine the agent generates should look like (6 states):

open → compute_grasp → compute_align → rotate_align → descend → close → grasped

(grasped is the success-marker noop from sg.add_exit("grasped"), with an edge to END.)

State details:

open — type: tool, tool: "robot.open_gripper", inputs: { settle_steps: 40 }.
compute_grasp — type: tool, tool: "geometry.top_down_grasp_candidates", inputs: { obb: Ref("in.target_obb") }.
compute_align — type: script, file scripts/<sg>/compute_align_pose.py (from this bundle's canonical_scripts). Inputs: grasp_pose = Ref("compute_grasp.candidates.poses.0"), target_obb = Ref("in.target_obb"). Returns align_pose.
rotate_align — type: tool, tool: "robot.go_to_pose", inputs: { pose: Ref("compute_align.align_pose") }.
descend — type: tool, tool: "robot.go_to_pose", inputs: { pose: Ref("compute_grasp.candidates.poses.0") }.
close — type: tool, tool: "robot.close_gripper", inputs: { settle_steps: 60 }. Edge directly from close to the grasped success marker; the subgraph's on_error: "failed" catches any raise from earlier steps. Whether the gripper actually closed on the object is checked by the target_held postcondition checkpoint (see ## Checkpoints), NOT by a re-check-and-raise node (none such exists).
```
"edges": [ ..., ["close", "grasped"], ["grasped", "END"] ],
"conditional_edges": {},
"exit": { "router_field": null, "success_values": ["grasped"] },
"on_error": "failed"
```
The lift onto a safe carry height is handled by the next transporting-objects subgraph (its waypoint_move script lifts before lateral motion); do NOT add a lift step here.

Hard rules

Use geometry.top_down_grasp_candidates (returns candidates: {poses: list[Se3Pose]}), not geometry.top_down_grasp_from_obb (single bare pose). The align-pose construction in step 3 assumes compute_grasp.candidates.poses.0 exists.
The align_pose descends straight down with the gripper pre-rotated. Do NOT skip the compute_align + rotate_align states — a direct robot.go_to_pose to the grasp pose blends rotation and descent and twists the gripper against the object.

Required end states

End state	Meaning
`grasped`	Gripper has closed on the object after the descend. Route to next subgraph (typically `transporting-objects`).
`failed`	Any grasp-attempt failure: planning failure or trajectory execution error (a raise to `on_error`). Coordinator routes to abort. Lives only in `on_error` — never declare a `failed` node.

See also

references/design_align_then_descend.md — why pre-rotate-then-descend beats blended rotate+descend.
scripts/compute_align_pose.py — the canonical align-pose construction.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.