AI Engineer building LLM agents, RAG systems, local AI agents, automation workflows, and evaluation-driven AI systems.
Sayed Allam is an AI engineer whose skills let an agent search and reason over video, from answering questions about past videos from a persistent cross-video index to extracting chapters, timestamps and bug reports from screen recordings. His most popular skills also cover configuring vision providers, verifying visual UI and animation changes, recording corrections as lessons, recovering from failed video pipelines, and exporting findings as offline shareable pages.
Watch Skill
10 skills · 558 stars · MIT
Asking With Evidence The user asks a question about a video that was already watched or indexed — "what did they say a…
Configuring Vision The user wants to connect an LLM or vision provider, already has an API key, asks "can I use Open…
Extracting Structure The user wants structure pulled out of a watched video — "make chapters for this video", "where d…
Learning From Mistakes The user corrected an answer about a video — "no, it actually says X", "that's the wrong timestam…
Recovering From Errors A Watch Skill command failed, video download broke, ffmpeg or yt-dlp is missing, a provider retur…
Sharing Results The user wants to share or hand off what was found in a video — "send this analysis to my team",…
The Loop The user built or changed something visual — a UI, an animation, a game, a generated video — and…
Video Memory The user asks about videos watched in the past or across sessions — "have we watched anything abo…
Watch Watch any video (URL, stream, or local path) via Watch Skill.
Watching Videos The user shared a video URL, a YouTube/TikTok/stream link, a local video file, a screen recording…