This skill should be used when comparing two videos to analyze compression results or quality differences. Generates interactive HTML reports with quality metrics (PSNR, SSIM) and frame-by-frame visual comparisons. Triggers when users mention "compare videos", "video quality", "compression analysis", "before/after compression", or request quality assessment of compressed videos.
npx skills add https://github.com/nicepkg/ai-workflow --skill video-comparer
Compare two videos and generate an interactive HTML report analyzing compression results. The script extracts video metadata, calculates quality metrics (PSNR, SSIM), and creates frame-by-frame visual comparisons with three viewing modes: slider, side-by-side, and grid.
Use this skill when:
python3 scripts/compare.py original.mp4 compressed.mp4
Generates comparison.html with:
# Custom output file
python3 scripts/compare.py original.mp4 compressed.mp4 -o report.html
# Custom frame interval (larger = fewer frames, faster processing)
python3 scripts/compare.py original.mp4 compressed.mp4 --interval 10
# Batch comparison
for original in originals/*.mp4; do
compressed="compressed/$(basename "$original")"
output="reports/$(basename "$original" .mp4).html"
python3 scripts/compare.py "$original" "$compressed" -o "$output"
done
FFmpeg and FFprobe (required for video analysis and frame extraction):
# macOS
brew install ffmpeg
# Ubuntu/Debian
sudo apt update && sudo apt install ffmpeg
# Windows
# Download from https://ffmpeg.org/download.html
# Or use: winget install ffmpeg
Python 3.8+ (uses type hints, f-strings, pathlib)
.mp4 (recommended), .mov, .avi, .mkv, .webmThe script automatically validates:
Clear error messages with resolution guidance appear when validation fails.
The script calculates two standard quality metrics:
PSNR (Peak Signal-to-Noise Ratio): Pixel-level similarity measurement (20-50 dB scale, higher is better)
SSIM (Structural Similarity Index): Perceptual similarity measurement (0.0-1.0 scale, higher is better)
For detailed interpretation scales and quality thresholds, consult references/video_metrics.md.
The script extracts frames at specified intervals (default: 5 seconds), scales them to consistent height (800px) for comparison, and embeds them as base64 data URLs in self-contained HTML. Temporary files are automatically cleaned after processing.
The generated HTML report includes:
The script implements:
shell=True, validated arguments)ValidationError, FFmpegError, VideoComparisonError"FFmpeg not found": Install FFmpeg via platform package manager (see Requirements section)
"File too large": Compress videos before comparison, or adjust MAX_FILE_SIZE_MB in scripts/compare.py
"Operation timed out": Increase FFMPEG_TIMEOUT constant or use larger --interval value (processes fewer frames)
"Frame count mismatch": Videos have different durations/frame rates; script auto-truncates to minimum frame count and shows warning
The script includes adjustable constants for file size limits, timeouts, frame dimensions, and extraction intervals. To customize behavior, edit the constants at the top of scripts/compare.py. For detailed configuration options and their impacts, consult references/configuration.md.
Consult these files for detailed information:
references/video_metrics.md: Quality metrics interpretation (PSNR/SSIM scales, compression targets, bitrate guidelines)references/ffmpeg_commands.md: FFmpeg command reference (metadata extraction, frame extraction, troubleshooting)references/configuration.md: Script configuration options and adjustable constantsassets/template.html: HTML report template for customizing viewing modes and stylingAutomate YouTube tasks via Rube MCP (Composio): upload videos, manage playlists, search content, get analytics, and handle comments. Always search tools first for current schemas.
Create and audit truthful, accessible, publication-ready scientific figures with Matplotlib, Seaborn, or Plotly. Use for figure design, multi-panel layouts, uncertainty and missing-data displays, color/contrast review, image metadata validation, and journal export planning.
Python bridge to ImageJ2/Fiji for macros, plugins (Bio-Formats, TrackMate, Analyze Particles), NumPy↔ImagePlus/ImgLib2 exchange, and ImageJ Ops. Automates Fiji headlessly from Python. Use scikit-image for pure Python without Fiji plugins; napari for visualization.
Create 3D scenes, interactive experiences, and visual effects using Three.js. Use when user requests 3D graphics, WebGL experiences, 3D visualizations, animations, or interactive 3D elements.
Generate publication-quality PNG chart images from data, supporting line, bar, area, candlestick, pie, and heatmap charts. Triggers when the user asks to visualize data, create a graph, plot a time series, or generate a chart for a report, alert, or dashboard. Runs as a lightweight, headless Node.js process without a browser.
Performs deep Root Cause Analysis (RCA) on NVIDIA TAO Visual ChangeNet classification experiments with image-evidence-driven investigation. Use when analyzing ChangeNet model failures, investigating poor recall / FAR / PASS-NO_PASS metrics, auditing visual inspection pipeline quality, or running an RCA report for an AOI defect-detection model. Trigger phrases include "RCA on my ChangeNet model", "why is my AOI model failing", "audit ChangeNet predictions", "investigate FAR regressions", "root cause analysis on visual-changenet".
Build 3D web apps with Three.js (WebGL/WebGPU). Use for 3D scenes, animations, custom shaders, PBR materials, VR/XR experiences, games, data visualizations, product configurators.
> SERP-informed outline generation with H2/H3 heading hierarchy, competitive content gap analysis, section-by-section word count targets, chart and image placement markers, optional FAQ question planning, and internal linking zones. blog-brief instead if you need full competitive analysis, statistics research, and image suggestions. Lighter than a full content brief, generates article skeleton and structure only, ready for /blog write to consume. Use when user says "outline", "blog outline", "content outline", "structure blog", "plan sections", "article skeleton", "heading structure", "SERP analysis", "competitive outline", "plan article".
Take nicepkg/video-comparer from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.
The instructions reference brew.
Without those the skill loads but fails at the first command.