Computer Vision Skill

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

509 stars

Best use case

Computer Vision Skill is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

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

Teams using Computer Vision Skill should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/computer-vision/SKILL.md --create-dirs "https://raw.githubusercontent.com/a5c-ai/babysitter/main/library/specializations/robotics-simulation/skills/computer-vision/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/computer-vision/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How Computer Vision Skill Compares

Feature / Agent	Computer Vision Skill	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

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

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# 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

Related Skills

sympy-computer-algebra

509

from a5c-ai/babysitter

Symbolic computation using SymPy for Python-based mathematical analysis

tax-provision-calculator

509

from a5c-ai/babysitter

ASC 740 income tax provision calculation skill with deferred tax analysis

process-builder

509

from a5c-ai/babysitter

Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.

Workflow & Productivity

babysitter

509

from a5c-ai/babysitter

Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)