该 Skill 支持基于关键词的学术论文检索，可以设置发表时间范围与数量 并将论文下载到指定目录，帮助用户快速获取目标领域（如大模型）的最新或代表性研究成果。This skill enables keyword-based academic paper retrieval with optional constraints on time range and result size and download them in the folder.

Search and download related arXiv papers by topic plus date range, or from a seed paper title/id. Use when user asks to crawl related papers, collect arXiv a...

Security Scan

The skill mostly matches its stated purpose (search arXiv and download PDFs) and uses only Python stdlib, but there are a few inconsistencies and an incomplete/truncated source file that warrant caution before installing or running it.

Purpose & Capability

Name/description describe arXiv search + batch PDF download; the included script implements arXiv API queries and PDF downloads using only the Python standard library, which is coherent with the stated purpose.

Instruction Scope

SKILL.md instructs running the script at ./arxiv-related-papers/scripts/download_arxiv.py, but the file manifest places the script at scripts/download_arxiv.py (path mismatch). The SKILL.md claims the output dir is auto-created, but the visible portion of the script does not show directory creation (the file is truncated), so final behavior (including any extra file reads/writes) is unknown. The instructions otherwise limit network calls to arXiv, which is appropriate.

Install Mechanism

No install spec; this is an instruction-only skill with a Python script that uses only the standard library. No third-party packages or downloads are requested.

Credentials

The skill requests no environment variables, credentials, or config paths — consistent with a public arXiv downloader that only performs unauthenticated HTTP requests.

Persistence & Privilege

The skill is not marked always:true and does not request elevated or persistent system-wide privileges. Autonomous invocation is enabled (platform default) but is not combined with other high-risk indicators.

What to consider before installing

This skill appears to do what it says (query arXiv and download PDFs) and uses only Python standard libraries, but take these precautions before installing or running it: - Verify the repository layout: SKILL.md expects ./arxiv-related-papers/scripts/download_arxiv.py but the manifest shows scripts/download_arxiv.py — confirm the correct path or update the invocation. - Inspect the full script (the distributed file appears truncated in the bundle). The truncated tail could contain logic that changes behavior (file system writes, external endpoints, or other actions). Do not run until you have the complete source. - Confirm the script creates the output directory or will not overwrite unintended files. Run in a sandboxed environment or with limited write permissions to the target directory. - The script retries with an unverified SSL context if certificate verification fails; be aware this weakens TLS checks when that code path is taken. - Because it downloads many PDFs, ensure you have permission to write to the target directory and adequate disk space. Given the path mismatch and incomplete source, proceed only after obtaining and reviewing the complete file and correcting the invocation path. If you want, provide the rest of the script and I can re-evaluate with the full content.

arXiv Related Papers Downloader

What this skill does

• Accepts either:
  • topic + time range, or
  • seed paper (arXiv id or title)
• Finds related papers from arXiv API.
• Downloads PDF files into arxiv/.
• Uses filename format: versionDate-title.pdf, where versionDate is vN_YYYYMMDD.

When to use

Use this skill when the user asks to:

• crawl/search related papers by topic;
• find related papers from one article;
• download arXiv PDFs in batch;
• save with a deterministic naming rule.

Required user input

The user must provide one of these modes:

1. Topic mode

   • topic
   • start date (YYYY-MM-DD)
   • end date (YYYY-MM-DD)

2. Seed paper mode

   • seed arXiv id (preferred) or seed title
   • optional start date / end date

Optional:

• max results (default: 20)

Execution steps

1. Confirm missing parameters with the user.
2. Run the script from workspace root:

# Topic mode
python ./arxiv-related-papers/scripts/download_arxiv.py \
  --topic "graph neural network" \
  --start-date 2024-01-01 \
  --end-date 2024-12-31 \
  --max-results 20

# Seed mode by arXiv id
python ./arxiv-related-papers/scripts/download_arxiv.py \
  --seed-id "2401.12345v1" \
  --max-results 20

# Seed mode by title
python ./arxiv-related-papers/scripts/download_arxiv.py \
  --seed-title "Attention Is All You Need" \
  --start-date 2018-01-01 \
  --end-date 2024-12-31 \
  --max-results 20

3. Report back:
   • how many papers were found;
   • how many PDFs were downloaded;
   • the output directory path.

Output location and naming

• Output dir: ./arxiv/ (auto-created if missing)
• File naming rule:
  • v1_20240213-Your_Paper_Title.pdf
  • v3_20231105-Your_Paper_Title.pdf

Notes

• The script only uses Python standard library.
• If a paper has no PDF link or download fails, it is skipped with a warning.
• Existing files are not downloaded again.