human-extractor
Human Extractor Skill
Description
GPU-accelerated pipeline for detecting, tracking, and classifying humans in dashcam footage. Processes MP4 videos to extract human crops with optional CLIP-based head covering classification, saving all outputs to a unified directory with comprehensive indexing.
Purpose
Extract visual evidence of human presence from dashcam recordings for investigative analysis. Optimized for high throughput using NVDEC decoding, batched YOLOv8 detection, ByteTrack multi-object tracking, and optional CLIP classification.
Usage
Basic Invocation
Extract humans from Park_R videos on October 6, 2025
Advanced Invocation
More from yousufjoyian/claude-skills
tesseract
Pull and start Tesseract - the Information Mapping Knowledge Engine with Firebase backend. Provides localhost and Tailscale URLs.
9context-extract
Append conversation context to cumulative project history - never overwrites
7a2ui-embed
Write HTML visualizations to the A2UI panel or embed running apps
6youtube-transcript
Download YouTube video transcripts when user provides a YouTube URL or asks to download/get/fetch a transcript from YouTube. Also use when user wants to transcribe or get captions/subtitles from a YouTube video.
6folder
Display project folder contents in the TriClaude FOLDER panel
6context-manager
Maintain compiled context artifacts for stateless agent spawning. This skill produces BOOT_CONTEXT (stable project brain), DELTA_CONTEXT (recent changes), and feature bundles so any agent can spawn with deep understanding without reading the entire repo. Use this skill when setting up multi-agent workflows or when agents need fast, token-efficient onboarding.
6