Babysitter Computer Vision Skill

Specialized skill for robot vision including feature detection, tracking, and camera calibration

install
source · Clone the upstream repo
git clone https://github.com/a5c-ai/babysitter
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/a5c-ai/babysitter "$T" && mkdir -p ~/.claude/skills && cp -r "$T/library/specializations/robotics-simulation/skills/computer-vision" ~/.claude/skills/a5c-ai-babysitter-computer-vision-skill && rm -rf "$T"
manifest: library/specializations/robotics-simulation/skills/computer-vision/SKILL.md
source content

Computer Vision Skill

Overview

Expert skill for robot vision applications including camera calibration, feature detection and tracking, stereo vision, and visual servoing.

Capabilities

  • Implement camera intrinsic calibration (pinhole, fisheye)
  • Configure stereo camera calibration and rectification
  • Set up camera-LiDAR extrinsic calibration
  • Implement feature detection (ORB, SIFT, SURF, SuperPoint)
  • Configure optical flow tracking (Lucas-Kanade, Farneback)
  • Implement depth estimation from stereo
  • Set up visual servoing pipelines
  • Configure image undistortion and rectification
  • Implement ArUco/AprilTag marker detection
  • Set up hand-eye calibration

Target Processes

  • robot-calibration.js
  • visual-slam-implementation.js
  • object-detection-pipeline.js
  • digital-twin-development.js

Dependencies

  • OpenCV
  • cv_bridge
  • image_geometry
  • camera_calibration

Usage Context

This skill is invoked when processes require camera calibration, feature detection, visual tracking, or image processing for robot vision applications.

Output Artifacts

  • Camera calibration files (YAML)
  • Stereo calibration parameters
  • Feature detection configurations
  • Visual servoing controllers
  • Image processing pipelines
  • Marker detection configurations