菜单
学术论文 PDF 下载。支持 8 个数据源：Elsevier、Springer Nature、IEEE Xplore、 arXiv、Unpaywall、Semantic Scholar、PubMed Central、知网(CNKI)。 自动根据 DOI 前缀路由到对应数据源，未知 DOI 自动尝试 Unpaywall → Semantic Scholar。
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/ShZhao27208/Aut_Sci_Write --skill sci-download命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Read an academic paper end to end and extract professional research insights, figures, metadata, and critique. Use this skill whenever the user shares a scientific paper, review paper, survey paper, systematic review, meta-analysis, scoping review, arXiv link, DOI, PDF, or pasted paper text and asks to read, summarize, analyze, extract, digest, review, critique, or explain it. For original research papers, produce a modified Heilmeier analysis. For review literature, produce a field-map extraction covering scope, taxonomy, evidence quality, consensus, controversies, gaps, and future directions. Do NOT use this skill for non-academic articles, blog posts, or news.
Extracts figures and sub-figures from academic PDF papers. Supports Fig/Figure, Scheme, Chart, Supplementary Figure, Extended Data Figure (Nature), and Chinese equivalents (图/方案/示意图/附图/补充图). Sub-figure label recognition supports (a)/(A)/a)/(i)/(1)/a. formats. High-quality PNG output at configurable DPI. Use when user asks to "extract figure", "截取文献图片", "提取子图", "get figure from paper", "Scheme", "方案图", "补充图", "Supplementary Figure", or "Extended Data".
Generate academic presentation-style HTML slide decks and browser reports from PDFs, structured text, Markdown, paper summaries, outlines, or research notes. Use whenever the user wants to convert a scientific paper PDF directly into an interactive HTML report, clickable web presentation, shareable browser deck, or PPT-like HTML output with figures, structured insights, section pages, and offline deck-directory output. In the Aut_Sci_Write suite, choose this skill when the user wants HTML/web output; choose sci-ppt when they explicitly need a .pptx file.
基于 SOC 职业分类
正在显示 SKILL.md
| name | sci-download |
| description | 学术论文 PDF 下载。支持 8 个数据源：Elsevier、Springer Nature、IEEE Xplore、 arXiv、Unpaywall、Semantic Scholar、PubMed Central、知网(CNKI)。 自动根据 DOI 前缀路由到对应数据源，未知 DOI 自动尝试 Unpaywall → Semantic Scholar。 |
| author | Shuo Zhao |
| license | MIT |
| copyright | © 2026 Shuo Zhao. All rights reserved. |
| triggers | ["下载论文","下载文献","download paper","download PDF","DOI",10.1016,10.1038,10.1007,10.1109,"arXiv download","ScienceDirect","Elsevier","Springer","IEEE","Unpaywall","PubMed Central","PMC","知网","CNKI"] |
Academic paper PDF download tool with intelligent DOI routing across 8 sources.
| Source | Type | Auth | Coverage |
|---|---|---|---|
| Elsevier/ScienceDirect | API | API Key | Elsevier journals |
| Springer Nature | API | API Key | Springer/Nature OA |
| IEEE Xplore | API | API Key | IEEE/IET |
| arXiv | Direct | None | Physics/CS/Math preprints |
| Unpaywall | API | Email only | Any DOI → OA version |
| Semantic Scholar | API | None | Cross-source OA aggregation |
| PubMed Central | Direct | None | Biomedical OA |
| CNKI (知网) | FSSO/WebVPN | University account | Chinese journals/theses |
The CLI automatically selects the source based on identifier format:
10.1016/... → Elsevier
10.1038/... → Springer Nature
10.1007/... → Springer Nature
10.1109/... → IEEE Xplore
2301.07041 → arXiv
PMC1234567 → PubMed Central
12345678 → PubMed (PMID)
中文关键词 → CNKI
Other DOI → Unpaywall → Semantic Scholar (waterfall)
Main script: ./sci_download.py
# Auto-route by DOI prefix
python skills/sci-download/sci_download.py "10.1038/s41586-023-06600-9"
# Download arXiv paper (auto-detected)
python skills/sci-download/sci_download.py "2301.07041"
# Force a specific source
python skills/sci-download/sci_download.py "10.1021/acs.nanolett.3c00123" --source unpaywall
# Search papers (requires --source)
python skills/sci-download/sci_download.py --search "perovskite solar cells" --source semantic_scholar --limit 5
# Search arXiv
python skills/sci-download/sci_download.py --search "large language model" --source arxiv --limit 5
# Show config and API key status
python skills/sci-download/sci_download.py --status
# Custom output directory
python skills/sci-download/sci_download.py "2301.07041" --output-dir ./papers
API keys are stored in the unified ~/.aut_sci_write/.env (auto-created on first use).
Non-secret settings (school, output_dir, proxy) are in ~/.aut_sci_write/sci-download/config.json.
Edit ~/.aut_sci_write/.env directly or use the config helper:
cd skills/sci-download
python -c "from config import update_config; update_config('elsevier_api_key', 'YOUR_KEY')"
python -c "from config import update_config; update_config('springer_api_key', 'YOUR_KEY')"
python -c "from config import update_config; update_config('ieee_api_key', 'YOUR_KEY')"
python -c "from config import update_config; update_config('unpaywall_email', 'you@email.com')"
| Service | URL | Notes |
|---|---|---|
| Elsevier | https://dev.elsevier.com/ | Free, Article Retrieval API |
| Springer | https://dev.springernature.com/ | Free, OA only |
| IEEE | https://developer.ieee.org/ | Free tier |
| Unpaywall | N/A | Just provide email |
python skills/sci-download/cnki_download.py set-mode fsso
python skills/sci-download/cnki_download.py status
# Login at https://fsso.cnki.net → export cookies → save to ~/.aut_sci_write/webvpn_cookies.json
requests, pycryptodome, beautifulsoup4
Aut_Sci_Write — Autonomous Scientific Writer