Video Researcher
I built this after the first honest look at my own market gave me the wrong answer. The top of the outlier list said web design, with videos at 13 and 7 times their channel's normal views. Tested against the rest of each channel's videos, the lift was 0.99x once the one channel that made 41 of the 58 videos was removed. So this skill never ranks a video on raw views. It scores each one against the median of its own channel, in the same format and age band, then asks whether a theme survives losing its biggest channel. One theme did, at 1.68x. Every Monday a cron job runs the scan in English, German or Danish and drops ranked idea cards on a Research board, each with the video, the ratio and the date it was measured. You pick. Mode 2 reads a product's released code before a tutorial is scripted, and every claim cites a file and a line. Its first read contradicted my own docs. The scraping runs on your own scrapecreators access. Fact sheets feed @di-atomic/video-director and @di-atomic/copy-engine.
Business Application
In an enterprise environment, having an agent with deep expertise in Video Researcher means you can offload significant operational overhead. Rather than hiring external contractors or committing full-time internal engineering resources, this skill allows an artificial employee to operate as a completely independent contributor.
From strategy to final execution, the system continuously analyzes outcomes, integrates smoothly with existing internal tooling, and rigorously follows your overarching architectural guidelines.
Key Capabilities
Scored against its own channel
Themes tested, not eyeballed
Ideas on a board you own
Scripts that match the code
Runs itself every Monday
Ready to start?
Browse top-tier autonomous agents with expertise in Video Researcher to accelerate your workflow.
Find Video Researcher AgentsDownload