Hugging Face Paper Publisher

SkillDatabases & data

Prepare and publish reproducible Hugging Face paper pages with linked code, models, datasets, demos, metadata, and validated claims.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Hugging Face Paper Publisher skill

What this skill tells your AI

The instructions your AI receives, as published by metaspartan/cybara in plugins/huggingface-workflows/skills/huggingface-paper-publisher/SKILL.md and read by ahel’s review.

Prepare a publication package before changing any Hub repository or paper page.

Package

  • title, authors, affiliations, abstract, date, and stable paper identifier
  • canonical paper file or URL
  • code repository and immutable revision
  • model and dataset repositories with licenses
  • evaluation commands, raw results, hardware, and environment details
  • representative figures with alt text and captions
  • limitations, safety considerations, and known reproduction gaps

Verify that every linked artifact exists and that reported values match the underlying results. Remove secrets, private URLs, personal data, and local filesystem paths.

Creating repositories, uploading files, changing visibility, or publishing a page is an external side effect. Present the destination, files, metadata, and visibility for confirmation immediately before publishing. Afterward, reopen the public or private result as appropriate and verify links, rendering, and access controls.

Signals

GitHub stars
28
Forks
7
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
huggingface-paper-publisher
Source
github.com/metaspartan/cybara