community-automations/paper-digest

Research & Intel

PublicClaude subagent

Paper Digest

Keeping up with arXiv means scrolling hundreds of abstracts a day and still missing the paper that matters to your work. Paper Digest pulls the new arXiv and HuggingFace submissions and ranks them by how novel they look against recent work.

sonnet4 daysarXiv APIHuggingFace PapersOpenAINotion
ClaudeClaude
ROI for
README.md

Why this subagent

Keeping up with arXiv means scrolling hundreds of abstracts a day and still missing the paper that matters to your work. Paper Digest pulls the new arXiv and HuggingFace submissions and ranks them by how novel they look against recent work.

You get a short ranked digest with each top paper boiled down to problem, method, and result, plus a direct PDF link. Read five summaries instead of two hundred abstracts.

How it runs

    • Read

      Used at step 01 to kick off the pipeline.

    • Write

      Used at step 01 to kick off the pipeline.

    • WebFetch

      Used at step 01 to kick off the pipeline.

    • WebSearch

      Used at step 01 to kick off the pipeline.

Sample output

json
// Sample output
// (generated when the pipeline finishes)

Rank today's papers by novelty and return the top 10 as JSON entries with title, one-line contribution, novelty_score, and PDF link.

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.