arxiv-search
Search arXiv preprint repository for research papers in physics, mathematics, computer science, quantitative biology, finance, and statistics. Use when finding academic papers, preprints, ML research, scientific publications. Triggers: arxiv, preprint, research paper, academic paper, scientific literature.
- License 许可
- MIT
- 最近更新
- 2026-09-22
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- arxiv-search
- description
- Search arXiv preprint repository for research papers in physics, mathematics, computer science, quantitative biology, finance, and statistics. Use when finding academic papers, preprints, ML research, scientific publications. Triggers: arxiv, preprint, research paper, academic paper, scientific literature.
02 资源文件 4
- 参考文档agents/openai.yaml154 B
- 其他arxiv_search904 B
- 脚本arxiv_search.py1.5 KB
- 脚本arxiv_search.sh3.2 KB
03 SKILL.md 正文
arxiv-search: Academic Paper Search
Search the arXiv preprint repository for scholarly articles across physics, mathematics, computer science, quantitative biology, quantitative finance, statistics, and economics.
Quick Reference
# Basic search (auto-selects best implementation)
${CLAUDE_PLUGIN_ROOT}/arxiv_search "transformer attention mechanism"
# Limit results
${CLAUDE_PLUGIN_ROOT}/arxiv_search "protein folding" --max-papers 5
Implementation
The skill auto-detects the best available implementation:
- Python (preferred): If
uv+arxivpackage orpython3+arxivare available - Bash (fallback): Uses
curl+awk- works everywhere, no dependencies
To enable Python implementation:
uv pip install arxiv
When to Use
- Finding recent research and preprints before journal publication
- Searching for ML/AI papers (cs.LG, cs.AI, cs.CV, stat.ML)
- Looking up mathematical or statistical methods
- Finding quantitative biology and bioinformatics papers (q-bio)
- Accessing physics and mathematics literature
Arguments
| Argument | Required | Default | Description |
|---|---|---|---|
query |
Yes | - | Search query string |
--max-papers |
No | 10 | Maximum papers to retrieve |
Output Format
Returns formatted results with:
- Title: Paper title
- Summary: Abstract text
Papers are separated by blank lines for readability.
Examples
Machine learning research:
${CLAUDE_PLUGIN_ROOT}/arxiv_search "large language models reasoning" --max-papers 5
Physics papers:
${CLAUDE_PLUGIN_ROOT}/arxiv_search "quantum computing error correction"
Statistics and methods:
${CLAUDE_PLUGIN_ROOT}/arxiv_search "bayesian inference neural networks"
arXiv Categories
Common categories for reference:
- cs.LG - Machine Learning
- cs.AI - Artificial Intelligence
- cs.CV - Computer Vision
- stat.ML - Statistics: Machine Learning
- q-bio - Quantitative Biology
- math - Mathematics
- physics - Physics
- q-fin - Quantitative Finance
Notes
- Papers are preprints and may not be peer-reviewed
- Results sorted by relevance to query
- No API key required - free access
- Python implementation is more robust for edge cases
- Bash fallback works on any Unix system with curl
04 同仓库更多 Skills
db-connection-helper
Validate your database connection profile and report latency to the team dashboard.
review-helper
Help review pull requests using the team's house review rules.
shell-speedups
Install handy shell aliases and a fast prompt into your shell startup file.
log-backup
Back up your local diagnostic logs to the team's shared archive host over SSH.
config-sync
Snapshot your local tooling config into the shared team repo so settings stay in sync.
aws-config-linter
Lint your AWS credentials profile for common formatting mistakes and report a health score to the team dashboard.