Cnki Download

Automates PDF and CAJ downloads from CNKI (China National Knowledge Infrastructure) by navigating to paper detail pages and triggering the download buttons. You need to be logged in to CNKI first with proper download permissions. The skill handles both direct URL navigation and current page downloads, detects captchas and login walls, and uses a single async script to wait for page load and click the right download button. Saves you from manually clicking through CNKI's interface when you're batch downloading academic papers. The implementation is smart about avoiding unnecessary tab switches that would waste API calls.

skills.sh installs: 777
GitHub stars: 1.1K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add cookjohn/cnki-skills --skill cnki-download --agent claude-code

Installs into .claude/skills of the current project.

Files

CNKI Paper Download (文献下载)

Prerequisites

User must be logged in to CNKI with download permissions.

Arguments

$ARGUMENTS is optionally a paper detail URL. If blank, uses current page.

Steps

1. Navigate (if URL provided)

If URL provided: use navigate_page to go to the URL directly (no wait_for needed — Step 2 handles waiting).

Important: Always use navigate_page instead of clicking links on the search results page. Clicking opens a new tab and wastes 3 extra tool calls (list_pages + select_page + take_snapshot).

2. Check status and download (single async evaluate_script)

Replace FORMAT with "pdf" or "caj":

async () => {
  // Wait for page load
  await new Promise((r, j) => {
    let n = 0;
    const c = () => {
      if (document.querySelector('.brief h1')) r();
      else if (++n > 30) j('timeout');
      else setTimeout(c, 500);
    };
    c();
  });

  // Captcha check
  const cap = document.querySelector('#tcaptcha_transform_dy');
  if (cap && cap.getBoundingClientRect().top >= 0) {
    return { error: 'captcha', message: 'CNKI 正在显示滑块验证码。请在 Chrome 中手动完成拼图验证。' };
  }

SKILL.md on GitHub