01
It starts by itself
weekday morning digest. Runs in Claude Code routine or cron.
- ↻ weekday morning digest
0 8 * * 1-5
huggingface · 2K installsHugging Face Paper Pages skill
Runs by itself, weekday morning digest.
Never miss an important paper.
Install the Hugging Face Paper Pages skill and make it a habit: follow https://gethabit.dev/skills/huggingface/huggingface-papers.md
- 1Copy
- 2Paste into Claude Code, Codex or Cursor
- 3It runs by itself
2K installs11K starsApache-2.0 licenceSource on GitHub ↗
Hugging Face Paper Pages
by huggingface · 2K installs
The skill
The hugging face paper pages skill reads AI research papers as markdown and pulls structured metadata such as linked models, datasets, spaces and GitHub repos, for anyone summarizing or tracking papers.
Only when you ask.
The habit
Never miss an important paper.
↻ Runs by itselfweekday morning digest
How the habit works.
You don't have to.
When does it start? How does it check its work? What does it remember?
One run, step by step.
Then it stops.
Stops after 10 papers per run.
- 01
Fetch the feed
The agent calls /api/daily_papers for today with sort set to trending.
- 02
Skip known papers
It drops paper IDs already in the digest log.
- 03
Read each paper
It fetches each paper as markdown from the .md endpoint, falling back to arXiv when needed.
- 04
Add linked work
It queries linked models, datasets and spaces with the arxiv filter.
- 05
Write the digest
Short summaries with paper IDs and links go into the digest log.
What it may do.
Nothing more.
It writes only in its own folder and asks you before anything goes out.
- Writes only inloops/daily-papers-digest-loop/**
- Talks tohuggingface.co, arxiv.org
- Sendsnothing
- Your OKNothing goes out, so it needs no OK.
Is it for you?
Use it when it fits.
Read both lists. If the left one sounds like you, the Hugging Face Paper Pages skill helps.
Use it when
- ✓ someone shares an arXiv link
- ✓ you want a paper summarized
- ✓ you track the daily papers feed
Skip it when
- – the paper is outside AI or CS
- – you need full PDF figure extraction
Hugging Face Paper Pages skill, answered.
Does it need a token?
Public paper pages need no auth; the skill's daily papers example sends an HF_TOKEN header.
Will it claim or index papers?
No. This loop uses only read endpoints; claim, index and link updates are write calls it never makes.
How do I install the Hugging Face Paper Pages skill?
Copy the prompt at the top into your agent. It installs the skill from huggingface/skills and sets up the habit. Or run npx skills add huggingface/skills --skill huggingface-papers.
Is the Hugging Face Paper Pages skill free?
Yes. It is published under Apache-2.0. Habit is free too.
Hugging Face Paper Pages. Now as a habit.
Install the Hugging Face Paper Pages skill and make it a habit: follow https://gethabit.dev/skills/huggingface/huggingface-papers.md
All huggingface skills →More notes skills →
Works in
- Claude Code
- Codex
- Cursor
- ChatGPT
- Claude app
Made by huggingface, published under Apache-2.0. Habit links to the original and never changes it. Is this your skill?