by cookjohn · MCP Server · ★ 84
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is sd-skills safe to install? View the security audit →
ScienceDirect Skills for Claude Code English | 中文 English Claude Code skills that let Claude interact with ScienceDirect (Elsevier) through Chrome DevTools MCP. Search papers, browse journals, extract metadata, export citations, download PDFs, and push to Zotero — all from the Claude Code CLI. Prerequisites Claude Code CLI installed Chrome browser (institutional or personal login for PDF download & export) Zotero desktop app (optional, for citation export) Python 3 (optional, for Zotero push script) Skills /sd-navigat
git clone https://github.com/cookjohn/sd-skills.git
git clone https://github.com/cookjohn/sd-skills.git /tmp/sd-skillsTaken from the project's README on GitHub. Check the security audit before running it.
No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
| Stars | 84 |
| Forks | 12 |
| Language | Python |
| Category | MCP Server |
| Quality Score | 66.9583751992364/100 |
| Last Updated | 2026-03-13 |
| Created | 2026-03-02 |
| Platforms | browser, claude-code, mcp, python |
| Est. Tokens | ~15k |
Explore other popular mcp server tools:
sd-skills is ScienceDirect skills for Claude Code — search, browse, export, download academic papers via Chrome DevTools MCP. It is categorized as a MCP Server with 84 GitHub stars.
sd-skills is primarily written in Python.
The README on GitHub (github.com/cookjohn/sd-skills) gives: git clone https://github.com/cookjohn/sd-skills.git , then git clone https://github.com/cookjohn/sd-skills.git /tmp/sd-skills. Usage details are in the same README.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: