Claude subagent
Why this subagent
A popular video can have thousands of comments, and the useful signal, what people loved or got stuck on, is drowned in noise. This automation reads the whole comment section for you.
It groups comments into themes, counts each one, and pulls real quotes so you see the actual words. Creators learn what to make next; teams learn which complaint keeps repeating, without scrolling the thread by hand.
How it runs
Used at step 01 to kick off the pipeline.
Used at step 01 to kick off the pipeline.
Used at step 01 to kick off the pipeline.
Used at step 01 to kick off the pipeline.
Sample output
json// Sample output // (generated when the pipeline finishes) Cluster the video comments into themes and return each theme with a count, sentiment, and three verbatim example comments.
Unlock the rest
The full agent definition, install snippet, and starter task are gated for community members.
Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.