Gs Search

Searches Google Scholar by keyword and scrapes back titles, authors, citation counts, and PDF links when available. Uses Chrome DevTools MCP to navigate and DOM scrape since Google Scholar has no public API. The real value is in the data-cid extraction, which is the cluster ID you need for citation exports and tracking who cited what. Includes CAPTCHA detection that pauses and asks you to solve it manually. Works best when you keep requests spaced out to avoid rate limiting. Pairs with companion skills for pagination, citation tracking, and Zotero export, all built around that data-cid identifier.

skills.sh installs: 447
GitHub stars: 545
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add cookjohn/gs-skills --skill gs-search --agent claude-code

Installs into .claude/skills of the current project.

Files

Google Scholar Basic Search

Search Google Scholar for papers using keyword(s). Returns structured result list via DOM scraping.

Arguments

$ARGUMENTS contains the search keyword(s).

Steps

1. Navigate

Use mcp__chrome-devtools__navigate_page:

url: https://scholar.google.com/scholar?q={URL_ENCODED_KEYWORDS}&hl=en&num=10

2. Extract results (evaluate_script)

Wait for results to load, check for CAPTCHA, then scrape the DOM:

async () => {
  // Wait for results or CAPTCHA
  for (let i = 0; i < 20; i++) {
    if (document.querySelector('#gs_res_ccl') || document.querySelector('#gs_captcha_ccl')) break;
    await new Promise(r => setTimeout(r, 500));
  }

  // CAPTCHA check
  if (document.querySelector('#gs_captcha_ccl') || document.body.innerText.includes('unusual traffic')) {
    return { error: 'captcha', message: 'Google Scholar requires CAPTCHA verification. Please complete it in your browser, then tell me to continue.' };
  }

SKILL.md on GitHub