Skip to content
Back to search

sd-skills

ScienceDirect skills for Claude Code — search, browse, export, download academic papers via Chrome DevTools MCP

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/cookjohn--sd-skills/badge.svg)](/listings/cookjohn--sd-skills)

HTML

<a href="/listings/cookjohn--sd-skills"><img src="/api/listings/cookjohn--sd-skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

1. Install Chrome DevTools MCP server

claude mcp add chrome-devtools -- npx -y chrome-devtools-mcp@latest

2. Install ScienceDirect skills

git clone https://github.com/cookjohn/sd-skills.git
cd sd-skills
cp -r skills/ agents/ .claude/

Or add to an existing project:

git clone https://github.com/cookjohn/sd-skills.git /tmp/sd-skills
cp -r /tmp/sd-skills/skills/ your-project/.claude/skills/
cp -r /tmp/sd-skills/agents/ your-project/.claude/agents/

3. Configure anti-detection (recommended)

Add to your `.claude.json` to prevent Cloudflare captcha loops on PDF downloads:

{
  "mcpServers": {
    "chrome-devtools": {
      "command": "npx",
      "args": [
        "-y",
        "chrome-devtools-mcp@latest",
        "--ignoreDefaultChromeArg=--enable-automation",
        "--ignoreDefaultChromeArg=--disable-infobars",
        "--chromeArg=--disable-blink-features=AutomationControlled"
      ]
    }
  }
}

4. Launch Claude Code

claude

Skills and agent are picked up automatically. Try `/sd-search deep learning` to verify.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 212 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # ScienceDirect Skills for Claude Code
  2. [English](#english) | [中文](#中文)
  3. | WeChat Official Account (公众号) | WeChat Group (微信群) | Discord |
  4. |:---:|:---:|:---:|
  5. | <img src="qrcode_for_gh_a1c14419b847_258.jpg" width="200"> | <img src="0320.jpg" width="200"> | [Join Discord](https://discord.gg/tGd5vTDASg) |
  6. | 未来论文实验室 | 扫码加入交流群 | English & Chinese |
  7. ---
  8. <a id="english"></a>
  9. ## English
  10. [Claude Code](https://docs.anthropic.com/en/docs/claude-code) skills that let Claude interact with [ScienceDirect (Elsevier)](https://www.sciencedirect.com) through Chrome DevTools MCP.
  11. Search papers, browse journals, extract metadata, export citations, download PDFs, and push to Zotero — all from the Claude Code CLI.
  12. ### Prerequisites
  13. - [Claude Code](https://docs.anthropic.com/en/docs/claude-code) CLI installed
  14. - Chrome browser (institutional or personal login for PDF download & export)
  15. - [Zotero](https://www.zotero.org/) desktop app (optional, for citation export)
  16. - Python 3 (optional, for Zotero push script)
  17. ### Skills
  18. | Skill | Description | Invocation |
  19. |-------|-------------|------------|
  20. | `sd-search` | Keyword search with structured result extraction | `/sd-search machine learning` |
  21. | `sd-advanced-search` | Filtered search: author, journal, year, title, keywords | `/sd-advanced-search author: Smith year: 2024 deep learning` |
  22. | `sd-parse-results` | Re-parse an existing search results page | _(internal)_ |
  23. | `sd-navigate-pages` | Pagination, sort order, results-per-page | `/sd-navigate-pages next` |
  24. | `sd-paper-detail` | Extract full article metadata (abstract, authors, DOI, etc.) | `/sd-paper-detail S0957417426005245` |
  25. | `sd-journal-browse` | Browse journal info, impact factor, issues, articles | `/sd-journal-browse Nature Energy` |
  26. | `sd-download` | Download article PDFs to local disk | `/sd-download S0957417426005245` |
  27. | `sd-export` | Export citations as RIS/BibTeX/text, push to Zotero | `/sd-export S0957417426005245 format: zotero` |
  28. ### Agent
  29. **`sd-researcher`** — orchestrates all 8 skills. Handles Cloudflare captcha detection (auto-clicks or pauses for manual resolution), and supports multi-step workflows like "search → detail → export to Zotero → download PDF".
  30. ### Installation
  31. #### 1. Install Chrome DevTools MCP server
  32. ```bash
  33. claude mcp add chrome-devtools -- npx -y chrome-devtools-mcp@latest
  34. ```
  35. #### 2. Install ScienceDirect skills
  36. ```bash
  37. git clone https://github.com/cookjohn/sd-skills.git
  38. cd sd-skills
  39. cp -r skills/ agents/ .claude/
  40. ```
  41. Or add to an existing project:
  42. ```bash
  43. git clone https://github.com/cookjohn/sd-skills.git /tmp/sd-skills
  44. cp -r /tmp/sd-skills/skills/ your-project/.claude/skills/
  45. cp -r /tmp/sd-skills/agents/ your-project/.claude/agents/
  46. ```
  47. #### 3. Configure anti-detection (recommended)
  48. Add to your `.claude.json` to prevent Cloudflare captcha loops on PDF downloads:
  49. ```json
  50. {
  51. "mcpServers": {
  52. "chrome-devtools": {
  53. "command": "npx",
  54. "args": [
  55. "-y",
  56. "chrome-devtools-mcp@latest",
  57. "--ignoreDefaultChromeArg=--enable-automation",
  58. "--ignoreDefaultChromeArg=--disable-infobars",
  59. "--chromeArg=--disable-blink-features=AutomationControlled"
  60. ]
  61. }
  62. }
  63. }
  64. ```
  65. #### 4. Launch Claude Code
  66. ```bash
  67. claude
  68. ```
  69. Skills and agent are picked up automatically. Try `/sd-search deep learning` to verify.
  70. ### Project Structure
  71. ```
  72. skills/
  73. ├── sd-search/SKILL.md # Basic keyword search
  74. ├── sd-advanced-search/SKILL.md # Filtered search (author, journal, year, etc.)
  75. ├── sd-parse-results/SKILL.md # Parse existing results page
  76. ├── sd-navigate-pages/SKILL.md # Pagination & sorting
  77. ├── sd-paper-detail/SKILL.md # Paper metadata extraction
  78. ├── sd-journal-browse/SKILL.md # Journal info & issue browsing
  79. ├── sd-download/SKILL.md # PDF download with Cloudflare handling
  80. └── sd-export/ # Citation export & Zotero
  81. ├── SKILL.md
  82. └── scripts/
  83. └── push_to_zotero.py # Zotero Connector API client
  84. agents/
  85. └── sd-researcher.md # Agent: orchestrates all skills
  86. ```
  87. ---
  88. <a id="中文"></a>
  89. ## 中文
  90. | 公众号 | 微信交流群 | Discord |
  91. |:---:|:---:|:---:|
  92. | <img src="qrcode_for_gh_a1c14419b847_258.jpg" width="200"> | <img src="0320.jpg" width="200"> | [加入 Discord](https://discord.gg/tGd5vTDASg) |
  93. | 未来论文实验室 | 扫码加入交流群 | 中英文交流 |
  94. 让 [Claude Code](https://docs.anthropic.com/en/docs/claude-code) 通过 Chrome DevTools MCP 操作 [ScienceDirect (Elsevier)](https://www.sciencedirect.com) 的技能集。
  95. 支持论文检索、期刊浏览、元数据提取、引用导出、PDF 下载、推送到 Zotero 等功能,全部在 Claude Code 命令行中完成。
  96. ### 前置要求
  97. - 已安装 [Claude Code](https://docs.anthropic.com/en/docs/claude-code) CLI
  98. - Chrome 浏览器(下载和导出需机构或个人账号登录)
  99. - [Zotero](https://www.zotero.org/) 桌面端(可选,用于引用导出)
  100. - Python 3(可选,用于 Zotero 推送脚本)
  101. ### 技能列表
  102. | 技能 | 功能 | 调用方式 |
  103. |------|------|----------|
  104. | `sd-search` | 关键词检索,返回结构化结果 | `/sd-search machine learning` |
  105. | `sd-advanced-search` | 高级检索:作者、期刊、年份、标题、关键词 | `/sd-advanced-search author: Smith year: 2024 deep learning` |
  106. | `sd-parse-results` | 重新解析当前搜索结果页 | _(内部调用)_ |
  107. | `sd-navigate-pages` | 翻页、排序、每页显示数量 | `/sd-navigate-pages next` |
  108. | `sd-paper-detail` | 提取论文完整元数据(摘要、作者、DOI 等) | `/sd-paper-detail S0957417426005245` |
  109. | `sd-journal-browse` | 浏览期刊信息、影响因子、期次、文章列表 | `/sd-journal-browse Nature Energy` |
  110. | `sd-download` | 下载论文 PDF 到本地 | `/sd-download S0957417426005245` |
  111. | `sd-export` | 导出引用为 RIS/BibTeX/纯文本,推送到 Zotero | `/sd-export S0957417426005245 format: zotero` |
  112. ### 智能体
  113. **`sd-researcher`** — 统一调度全部 8 个技能。自动处理 Cloudflare 验证码(自动点击或暂停等待用户手动完成),支持"检索 → 详情 → 导出到 Zotero → 下载 PDF"等复合工作流。
  114. ### 安装方法
  115. #### 1. 安装 Chrome DevTools MCP 服务器
  116. ```bash
  117. claude mcp add chrome-devtools -- npx -y chrome-devtools-mcp@latest
  118. ```
  119. #### 2. 安装 ScienceDirect 技能
  120. ```bash
  121. git clone https://github.com/cookjohn/sd-skills.git
  122. cd sd-skills
  123. cp -r skills/ agents/ .claude/
  124. ```
  125. 添加到已有项目:
  126. ```bash
  127. git clone https://github.com/cookjohn/sd-skills.git /tmp/sd-skills
  128. cp -r /tmp/sd-skills/skills/ your-project/.claude/skills/
  129. cp -r /tmp/sd-skills/agents/ your-project/.claude/agents/
  130. ```
  131. #### 3. Configure anti-detection(推荐)
  132. 在 `.claude.json` 中添加以下配置,优化 PDF 下载体验:
  133. ```json
  134. {
  135. "mcpServers": {
  136. "chrome-devtools": {
  137. "command": "npx",
  138. "args": [
  139. "-y",
  140. "chrome-devtools-mcp@latest",
  141. "--ignoreDefaultChromeArg=--enable-automation",
  142. "--ignoreDefaultChromeArg=--disable-infobars",
  143. "--chromeArg=--disable-blink-features=AutomationControlled"
  144. ]
  145. }
  146. }
  147. }
  148. ```
  149. #### 4. 启动 Claude Code
  150. ```bash
  151. claude
  152. ```
  153. 技能和智能体会自动加载。输入 `/sd-search deep learning` 验证是否正常。
  154. ---
  155. ## License
  156. MIT

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.