Writing & Content arxivpaper-publishingmarkdownyaml-frontmatterhugging-face-hubbibtexresearch-articles

Hugging Face Paper Publisher

Publish, connect, and manage research papers on the Hugging Face Hub.

FollowSkills review · FSRS-2.0
Not recommended
36/ 100 5-point scale 1.8 / 5
Trust9 / 25 · 1.8/5

The source requires HF_TOKEN and performs Hub reads and uploads, with linking defaulting to direct commits; it lacks user confirmation, least-privilege guidance, change preview, and rollback. The create-pr option still commits directly. Basic sanitization exists for external arXiv text, but token handling, data-flow disclosure, and provenance attribution are incomplete, so points are deducted.

Reliability6 / 20 · 1.5/5

The script includes input validation, exception handling, timeouts, and structured error returns, making the main paths statically plausible. However, documented commands such as list-my-papers, toggle-visibility, and validate are not implemented; search is only a placeholder, and dependency constraints do not match the documentation. No tests were executed, so the score remains low.

Adaptability6 / 15 · 2.0/5

The intended scenarios are fairly clear: paper indexing, repository linking, and article templates. Trigger conditions, non-fit boundaries, output contracts, and permission prerequisites are underspecified. Core behavior depends on Hugging Face and arXiv services, with no mainland-China reachability assessment or Chinese-language support.

Convention7 / 15 · 2.3/5

The skill has organized documentation, a quick reference, examples, templates, error handling, an Apache-2.0 repository license, and version 1.0.0. However, documentation and implementation diverge, while maintenance ownership, changelog, update path, and known limitations are not clearly stated; several templates remain placeholders. The unverified publisher identity is treated as unknown and is not independently penalized.

Effectiveness5 / 15 · 1.7/5

The code can plausibly perform some useful tasks: check papers, fetch arXiv metadata, edit repository READMEs, and generate drafts and BibTeX. But indexing does not actually perform indexing, several advertised features are absent, templates require substantial manual completion, and there is no static evidence of directly usable representative output or comparative benefit, warranting only a low score.

Verifiability3 / 10 · 1.5/5

The committed script, examples, and return structures provide limited auditable evidence, but there is no committed test suite, CI coverage, or third-party execution evidence. Documentation conflicts with the implementation, so conclusions are limited to static inspection and cannot receive a higher score.

Evidence confidence:Low Reviewed Jul 20, 2026 Reviewed revision 86cdeee824b7
The upstream repository has new commits since this review. The score still applies to the reviewed revision shown and may not cover the latest changes.
Before you use it
  • The link command uses HF_TOKEN to read and directly overwrite the target repository README; confirm the repository, permissions, and diff first, and keep a manual backup.
  • Do not treat create-pr as a safe preview or pull-request mode; the source says it is unimplemented and still commits directly.
  • Advertised features for visibility management, listing personal papers, and link validation have no corresponding implementation in the supplied script.
  • index, search, and parts of the template functionality are weaker than described; external Hugging Face/arXiv availability and rate limits may affect results.
  • Do not treat example metrics, authors, results, or citations in the templates as real research evidence.
See the full review method →

What does this skill do, and when should you use it?

This skill is for AI engineers and researchers who manage research outputs on the Hugging Face Hub. It indexes papers from arXiv, links them to models, datasets, and Spaces, supports authorship claims, and manages profile visibility. It also generates Markdown research articles from templates and converts them to HTML. It is a good fit for users already working in the Hugging Face ecosystem who want a repeatable paper-publication workflow.

It runs scripts/paper_manager.py with uv run to index or check papers by arXiv ID, search papers, link papers to model, dataset, or Space repositories, generate citations, start and check authorship claims, list a user's papers, and toggle profile visibility. It creates Markdown articles from the standard, modern, arxiv, and ml-report templates and converts Markdown to HTML. The scripts can read or update repository READMEs, YAML frontmatter, and paper links; Hugging Face Hub operations require an HF_TOKEN.

  1. A researcher indexes a newly published arXiv paper on Hugging Face Paper Pages.
  2. A model author adds a paper link and citation to a model card.
  3. A dataset maintainer connects one or more research papers to a dataset card.
  4. A listed author claims authorship and controls whether verified papers appear on their profile.
  5. An ML team generates a structured research article and a web-friendly HTML version from a template.

What are this skill's strengths and limitations?

Pros
  • Covers indexing, repository linking, authorship, visibility, citation, and article-generation workflows.
  • Supports model cards, dataset cards, Spaces, and multiple papers per artifact.
  • Includes several paper templates, dynamic tables of contents, LaTeX math support, and HTML conversion.
  • Uses PEP 723 inline dependencies and recommends `uv run` for execution.
Limitations
  • Requires network access to Hugging Face services and arXiv-related URLs, plus a write-capable token for publishing operations.
  • Authorship claims may require administrator review and can fail when the email does not match author records.
  • The source provides no test-suite, platform-coverage, or performance evidence.
  • It does not replace the paper-writing process, and arXiv submission is described as an external step.

How do you install this skill?

Following the repository README, copy or symlink skills/huggingface-paper-publisher into a standard Codex .agents/skills location, such as $REPO_ROOT/.agents/skills or $HOME/.agents/skills. The README also documents on-demand installation with hf skills add <skill-name>; for this skill, use hf skills add huggingface-paper-publisher.

How do you use this skill?

Ask the coding agent something like “Use the Hugging Face paper publisher skill to index arXiv paper 2301.12345 and link it to username/model-name.” You can also run uv run scripts/paper_manager.py index --arxiv-id "2301.12345", link --repo-id "username/model-name" --repo-type "model" --arxiv-id "2301.12345", or create --template "modern" --title "Your Paper Title" --output "paper.md" from the skill directory. Set an HF_TOKEN with write access before running scripts; the source does not document the exact agent trigger behavior.

FAQ

What permissions are required?
Publishing and repository-linking operations require an `HF_TOKEN` with write access. The source does not specify additional permission scopes.
Can it submit a paper directly to arXiv?
That is not supported by the supplied evidence. The workflow treats arXiv submission as an external process and uses the skill afterward for Hugging Face indexing and linking.
Why might paper linking or authorship fail?
Documented causes include insufficient token permissions, invalid README YAML, a paper that is not indexed yet, an invalid arXiv URL format, an email mismatch, an existing authorship claim, or rate limiting.

More skills from this repository

All from huggingface/skills

Dev & Engineering

Hugging Face Paper Research Assistant

Read AI papers and retrieve structured metadata from Hugging Face paper pages.

Data & Analysis

Sentence Transformers Training Assistant

Train retrieval, similarity, reranking, and sparse-search models with Sentence Transformers.

Data & Analysis

Hugging Face Model Memory Estimator

Estimate inference memory without downloading model weights.

Dev & Engineering

Hugging Face Local Model Runner

Choose compatible GGUF quantizations from Hugging Face and run them locally with llama.cpp.

Dev & Engineering

Hugging Face MCP Assistant

Connect agents to Hugging Face Hub for searchable models, datasets, documentation, apps, and compute jobs.

Dev & Engineering

Hugging Face Hub CLI Skill

Give agents command-line control over Hugging Face Hub models, datasets, Spaces, jobs, and infrastructure.

Dev & Engineering

Hugging Face ZeroGPU Builder

Build dependable Gradio AI demos and GPU workloads on Hugging Face ZeroGPU.

Dev & Engineering

LoRA Space Demo Builder

Build and publish a tailored Gradio Space for a Hugging Face LoRA.

Dev & Engineering

Hugging Face Spaces Builder

Build, deploy, debug, and maintain machine-learning apps on Hugging Face Spaces.

Data & Analysis

Hugging Face Dataset Explorer

Explore, query, and extract Hugging Face datasets through the Dataset Viewer API.

Data & Analysis

Hugging Face LLM Trainer

Train, fine-tune, and preserve models on Hugging Face cloud GPUs.

Data & Analysis

Hugging Face Local Evaluator

Run controlled inspect-ai or lighteval evaluations for Hugging Face Hub models on local hardware.

Data & Analysis

Trackio Experiment Tracking

Log, monitor, and query machine-learning experiments with dashboards, diagnostic alerts, and automation-ready output.

Data & Analysis

Hugging Face Vision Trainer

Train detection, classification, and segmentation models on Hugging Face Jobs GPUs and persist the results to the Hub.

Data & Analysis

Hugging Face Model Finder

Recommends AI models by task, benchmark performance, and available device memory.

Dev & Engineering

Hugging Face API Tool Builder

Turn Hugging Face API calls into reusable, composable command-line tools.

Automation & Ops

AWS Context Discovery

Resolve the active AWS environment before any account operation.

Automation & Ops

SageMaker Deployment Planner

Choose a practical Amazon SageMaker deployment path for your model, traffic pattern, and latency needs.

Automation & Ops

SageMaker Python Environment Setup

Build an isolated, version-aligned Python environment for SageMaker and AWS automation.

Data & Analysis

TRL Language Model Trainer

Train and fine-tune transformer language models with TRL’s CLI for SFT, preference alignment, and reinforcement learning.

Related skills