Grasp Planning Skill

SkillProductivity

Grasp planning and execution for robotic manipulation tasks

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the Grasp Planning Skill skill

What this skill tells your AI

The instructions your AI receives, as published by a5c-ai/babysitter in library/specializations/robotics-simulation/skills/grasp-planning/SKILL.md and read by ahel’s review.

Overview

Expert skill for planning and executing robotic grasps, including grasp pose generation, quality metrics, and gripper control.

Capabilities

Configure grasp pose generation (GPD, GraspIt!)
Implement antipodal grasp detection
Set up grasp quality metrics
Configure approach and retreat vectors
Implement pre-grasp and post-grasp poses
Set up gripper control and monitoring
Configure grasp database and learning
Implement 6-DOF grasp pose estimation
Set up object affordance detection
Configure collision-aware grasp selection

Target Processes

moveit-manipulation-planning.js
object-detection-pipeline.js
rl-robot-control.js
hri-interface.js

Dependencies

MoveIt grasps
GPD (Grasp Pose Detection)
GraspIt!
moveit_simple_grasps

Usage Context

This skill is invoked when processes require grasp planning for manipulation, pick-and-place operations, or bin picking tasks.

Output Artifacts

Grasp pose configurations
Gripper action configurations
Grasp quality evaluations
Approach vector definitions
Grasp database entries
Collision-aware grasp selections

Signals

GitHub stars: 2k
Forks: 112
Last commit: Sep 2026

Advanced

Item type: skill
Key: grasp-planning-skill
Source: github.com/a5c-ai/babysitter

github.com/a5c-ai/babysitter