Dev & Engineering hugging-facearxivpaper-metadataresearch-apimarkdown

Hugging Face Paper Research Assistant

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

FollowSkills review · FSRS-2.0
Not recommended
49/ 100 5-point scale 2.5 / 5
Trust14 / 25 · 2.8/5

The skill mainly performs public-page and API lookups, so its stated permission scope is relatively limited. However, it also documents write operations for indexing papers, claiming authorship, and updating links, requires HF_TOKEN, and lacks explicit user confirmation, sensitive-data handling, data-flow disclosure, or rollback guidance; points are deducted for these gaps.

Reliability7 / 20 · 1.8/5

Input formats, primary API paths, 404 handling, and fallbacks are reasonably clear. However, there are no helper scripts, committed tests, or static reproducibility evidence, and failure feedback for authentication errors, network failures, rate limits, and API changes is thin; points are deducted accordingly.

Adaptability10 / 15 · 3.3/5

Trigger conditions, arXiv ID parsing, and intended paper-analysis use cases are clear. Non-fit boundaries, output-format expectations, semantic false-trigger protections, Chinese-language support, and mainland-China network reachability are not addressed; points are deducted for those uncertainties.

Convention8 / 15 · 2.7/5

The documentation is readable and includes installation context, use cases, API parameters, error handling, and fallbacks. Repository context supplies Apache-2.0 licensing, CI validation, and a maintenance workflow, but the skill lacks its own version, changelog, explicit maintenance owner, dependency notes, and fuller examples; points are deducted for these omissions.

Effectiveness6 / 15 · 2.0/5

The documented Markdown and structured-metadata APIs plausibly support lookup, reading, and linked-resource analysis, with outputs that could be directly used. Static review provides no representative executed outputs, and API availability, content completeness, and comparative benefit are not demonstrated; points are deducted for that uncertainty.

Verifiability4 / 10 · 2.0/5

Concrete endpoints, parameters, error codes, and authorization requirements provide limited auditability. There is no third-party execution evidence, key-path test coverage, or cross-source corroboration, and static review cannot verify current endpoint behavior; points are deducted accordingly.

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
  • Write endpoints can modify paper indexing, authorship claims, or links; confirm user intent separately and restrict the scope and exposure of HF_TOKEN.
  • Core functionality depends on huggingface.co, arxiv.org, and network access; mainland-China reachability and offline alternatives are not documented.
  • Rate limits, authentication failures, network interruptions, and API evolution are not covered; manually verify responses in actual use.
Review evidence [1][2][3][4][5]
See the full review method →

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

This skill looks up and reads Hugging Face paper pages and their corresponding arXiv papers. It can fetch paper content as Markdown and use the Hugging Face papers API to retrieve structured information such as authors, summaries, linked models, datasets, Spaces, GitHub repositories, and project pages. It is intended for requests to summarize, explain, or analyze AI research papers. Public reads require no authentication, while authorship claims, indexing, and link updates require HF_TOKEN.

Parses a paper ID from a Hugging Face paper URL, Markdown paper URL, arXiv URL, or arXiv ID; requests paper Markdown with curl; retrieves structured metadata from /api/papers/{PAPER_ID}; searches for linked models, datasets, and Spaces; calls paper search, listing, and Daily Papers endpoints; and, with HF_TOKEN and the required permissions, claims authorship, indexes papers, or updates project-page, GitHub, and organization links.

  1. A researcher shares a Hugging Face paper page and needs machine-readable Markdown for an agent to read.
  2. An engineer provides an arXiv ID and wants the paper's authors, abstract, and linked Hugging Face resources.
  3. A reviewer searches papers by topic, title, authors, or full-text content.
  4. A project maintainer checks which models, datasets, Spaces, GitHub repositories, or project pages are linked to a paper.
  5. A paper author claims authorship or updates paper links with HF_TOKEN and the necessary permissions.

What are this skill's strengths and limitations?

Pros
  • Accepts both Hugging Face paper pages and arXiv URLs or IDs.
  • Offers both Markdown content and structured metadata access.
  • Can discover linked models, datasets, Spaces, GitHub repositories, and project pages.
  • Covers paper search, listing, Daily Papers, and selected paper-management operations.
Limitations
  • Requires network access to Hugging Face and related arXiv pages or APIs.
  • Requests may return 404 when a paper has not yet been indexed on Hugging Face.
  • Write operations require HF_TOKEN, specific permissions, and accurate paper or user identifiers.
  • The source does not document a test suite, rate limits, or required runtime versions.

How do you install this skill?

Copy or symlink skills/huggingface-papers/ from the repository's skills/ directory into a Codex-supported .agents/skills location, such as $REPO_ROOT/.agents/skills or $HOME/.agents/skills. The README does not provide a separate installation command for this individual skill.

How do you use this skill?

After installation, use a prompt such as: “Use the Hugging Face papers skill to summarize https://huggingface.co/papers/2602.08025” or “Analyze arXiv paper 2602.08025.” Public paper-page reads require no authentication. Authorship claims, indexing, and link updates require HF_TOKEN and the relevant permissions.

How does this skill compare with similar options?

The documented fallbacks are the regular Hugging Face paper page and the arXiv abstract page or PDF. The source does not identify other comparable skills or products.

FAQ

Do I need a Hugging Face token to read papers?
The source states that public paper pages require no authentication. The Daily Papers example uses HF_TOKEN, and write endpoints require authorization.
What does a 404 mean?
It generally means the paper is not indexed on Hugging Face paper pages yet. Verify the arXiv ID, including any version suffix.
Does this skill automatically fetch every paper?
No. It works with papers provided or found through the documented endpoints and depends on Hugging Face indexing. If an arXiv HTML version is unavailable, it falls back to the Hugging Face page HTML.
Does using it cost money?
The source does not specify pricing, quotas, or API billing.

More skills from this repository

All from huggingface/skills

Writing & Content

Hugging Face Paper Publisher

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

Data & Analysis

Hugging Face Dataset Explorer

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

Dev & Engineering

Hugging Face ZeroGPU Builder

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

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.

Dev & Engineering

Hugging Face Hub CLI Skill

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

Data & Analysis

Hugging Face Model Finder

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

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 API Tool Builder

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

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

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.

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.

Dev & Engineering

Hugging Face MCP Assistant

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

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