Hugging Face Papers
SkillDatabases & dataDiscover and analyze Hugging Face papers with traceable sources, linked models and datasets, and clearly separated claims and evidence.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Hugging Face Papers skill
What this skill tells your AI
The instructions your AI receives, as published by metaspartan/cybara in plugins/huggingface-workflows/skills/huggingface-papers/SKILL.md and read by ahel’s review.
Use hf papers list --format json or the Hub papers pages for discovery, then inspect the original paper before relying on a claim.
Workflow
- Capture the title, authors, publication date, paper URL, and stable identifier.
- Read the abstract, method, training data, evaluation setup, ablations, limitations, and license.
- Follow linked model, dataset, code, and demo repositories only when they are relevant.
- Distinguish author claims from reproduced or independently verified results.
- Compare metrics only when tasks, splits, prompts, baselines, and compute settings are compatible.
- Cite the original paper and primary artifacts near each technical claim.
Do not infer implementation details that are absent from the paper or its linked source. State when evidence is missing, unpublished, or not reproducible from available artifacts.
Signals
- GitHub stars
- 28
- Forks
- 7
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
huggingface-papers- Source
- github.com/metaspartan/cybara