Claude subagent
Why this subagent
The HuggingFace papers feed moves fast, and saved links pile up into a folder nobody ever sorts. This tracker reads each new paper as it lands and files it into a real, searchable structure.
It classifies every entry into your topics, pulls out model names, datasets, and code links, and appends a tidy row to your knowledge base. Months later you can answer what came out on retrieval in March without re-reading a thing.
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)
Classify each HuggingFace paper into the provided taxonomy and return {category, subtopics[], models[], has_code} as JSON.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.