mrrobertkent HelixLab — Developer Tools for AI Coding Agents
Version: 1.2.0 License: MIT Author: Robert Kent Jr. Homepage: https://github.com/mrrobertkent/helixlab-plugin
Available Skills
| Skill | Invoke | Description |
|---|---|---|
| Vision Replay | /helixlab:vision-replay <video-path> [instructions] |
Extract frames from video files using ffmpeg and analyze them with AI vision. Supports animation timing analysis, page load performance review, and user workflow progression. |
| Record Browser | /helixlab:record-browser [url] |
Launch a headed Chrome browser with recording controls and annotation tools. Draw annotations (lines, arrows, rectangles, circles, text) on the page — captured in the WebM recording for AI analysis with vision-replay. |
| Setup | /helixlab:setup [--check] |
Check prerequisites and install dependencies (ffmpeg, ffprobe, bc). Detects your OS and AI coding agent for tailored setup guidance. |
Prerequisites
- ffmpeg and ffprobe must be installed
- macOS: Run
bash scripts/setup.sh(downloads static build with drawtext support) - Linux (Debian/Ubuntu):
sudo apt install ffmpeg bc - Linux (RHEL/Fedora):
sudo dnf install ffmpeg bc - Windows: Requires WSL2 with
sudo apt install ffmpeg bc
- macOS: Run
- bash shell (available on macOS, Linux, Windows WSL)
- bc calculator (installed by default on macOS, may need install on minimal Linux)
Run /helixlab:setup --check to verify all prerequisites are met.
Quick Start
/helixlab:vision-replay /path/to/recording.webm analyze the page load animation
The skill will:
- Validate prerequisites (ffmpeg installed, file exists)
- Extract video metadata
- Generate a contact sheet overview
- Route to the appropriate analysis workflow
- Analyze frames with AI vision
- Produce a structured report
- Clean up temporary files