VjAlbert
UserConverts any video file into a comprehensive AI-readable report (Markdown + JSON) — because Claude Projects don't accept .mp4 uploads
Categories
Indexed Skills (2)
video-analyzer
Analyze a video file and produce a comprehensive AI-readable report (Markdown + JSON). Use this skill whenever the user uploads or references a video file (.mp4, .mov, .avi, .mkv, .webm, .m4v) and wants to: understand its content, create a report from it, extract what is said or shown, describe what happens, count or identify characters, summarize the video for use in a Claude project (where direct MP4 upload is not supported), or generate any written analysis of video content. Trigger even for casual phrasing like "what's in this video", "read this mp4", "make a report from this video", "transcribe this video", "describe this clip", "how many characters are in this video", "who appears in this video".
pith
PITH compresses inter-agent payloads to eliminate token waste in multi-agent pipelines. Use this skill whenever an agent produces verbose output that will be passed to another agent — tool results, reasoning traces, search summaries, intermediate context. Trigger on: "compress this for the next agent", "pith this output", "slim down this payload", "reduce context before passing", "this tool result is too long", "optimize this handoff", or any time intermediate agent output exceeds ~300 tokens and will be forwarded downstream. Also trigger PROACTIVELY when orchestrating chains of agents and noticing intermediate results growing large — do not wait to be asked. PITH preserves all code blocks, JSON, URLs, file paths, and numbers without touching them. Compresses only natural language using Zipf word-density scoring, validated by Benford's Law structural integrity check. Typical savings: 30–60% on verbose agent outputs. Zero external dependencies. No API calls. Works offline.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.