Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
cookjohn avatar

Sd Navigate Pages

  • 14 installs
  • 51 repo stars
  • Updated March 13, 2026
  • cookjohn/sd-skills

Navigates ScienceDirect search result pages, changes sort order, and adjusts results per page.

About

Handles pagination and sorting on ScienceDirect search results. A developer uses it to page through results or reorder them.

  • Navigates next, prev, and page-N results
  • Changes sort order and results per page

Sd Navigate Pages by the numbers

  • 14 all-time installs (skills.sh)
  • Ranked #1,417 of 2,715 Automation & Workflows skills by installs in the Skillselion catalog
  • Data as of Jul 29, 2026 (Skillselion catalog sync)
npx skills add https://github.com/cookjohn/sd-skills --skill sd-navigate-pages

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs14
repo stars51
Last updatedMarch 13, 2026
Repositorycookjohn/sd-skills

What it does

Navigates ScienceDirect search result pages, changes sort order, and adjusts results per page.

Files

SKILL.mdMarkdownGitHub ↗

ScienceDirect Pagination & Sorting

Navigate between result pages, change sorting, or adjust results per page.

How pagination works

ScienceDirect uses URL parameters for pagination:

  • offset — starting result index (0-based). Default is 0 (page 1).
  • show — results per page. Options: 25, 50, 100.
  • sortBy — sort order. date for newest first; omit for relevance.

Page calculation: page Noffset = (N - 1) * show

Steps

Step 1: Determine current state

Use evaluate_script to read the current URL and pagination info:

() => {
  const url = new URL(window.location.href);
  const params = Object.fromEntries(url.searchParams);
  const pageInfo = document.querySelector('.Pagination li:first-child')?.textContent?.trim() || '';
  const totalText = document.querySelector('.search-body-results-text')?.textContent?.trim() || '';
  return { params, pageInfo, totalText, currentUrl: window.location.href };
}

Step 2: Build target URL

Based on $ARGUMENTS, modify the URL parameters:

User intentAction
"next" / "下一页"offset += show
"prev" / "上一页"offset -= show (min 0)
"page 3" / "第3页"offset = (3-1) * show
"sort by date" / "按日期排序"add sortBy=date
"sort by relevance" / "按相关性排序"remove sortBy
"show 100" / "每页100条"set show=100, reset offset=0

Step 3: Navigate and extract

Use navigate_page to the new URL. Always include `initScript` to prevent bot detection:

initScript: "Object.defineProperty(navigator, 'webdriver', {get: () => undefined})"

Then extract results using evaluate_script with built-in waiting (same as sd-search). Do NOT use wait_for — it returns oversized snapshots.

Notes

  • Always preserve existing query parameters (qs, tak, authors, etc.) when modifying pagination/sort.
  • When changing show, reset offset to 0 to avoid out-of-range pages.
  • Maximum 2-3 tool calls per operation.

Related skills

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.