Cnki Navigate Pages logo

Cnki Navigate Pages

Community
cookjohn
cnki-navigate-pages

Navigate CNKI search result pages (next/previous/specific page) or change sort order. Use when user wants to see more results or change sorting.

Overview

Publishercookjohn
Repositorycnki-skills
Skill namecnki-navigate-pages
Stars
984
Forks
84
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by cookjohn on GitHub. Read the source before you install it.

Installation

Install the Cnki Navigate Pages AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/cookjohn/cnki-skills/tree/master/skills/cnki-navigate-pages
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/cookjohn/cnki-skills.git /tmp/cnki-skills
mkdir -p .claude/skills
cp -r /tmp/cnki-skills/skills/cnki-navigate-pages .claude/skills/cnki-navigate-pages
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cnki Navigate Pages in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Cnki Navigate Pages on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Cnki Navigate Pages is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

CNKI Results Pagination and Sorting

All operations use a single async evaluate_script — no snapshot or wait_for needed.

Arguments

$ARGUMENTS should be one of:

  • next / previous / page N — pagination
  • sort by date / sort by citations / sort by downloads / sort by relevance / sort by comprehensive — sorting

Pagination (single evaluate_script)

Replace ACTION_HERE with "next", "previous", or "page 3":

javascript
async () => {
  const cap = document.querySelector('#tcaptcha_transform_dy');
  if (cap && cap.getBoundingClientRect().top >= 0) return { error: 'captcha' };

  const action = "ACTION_HERE";
  const pageLinks = document.querySelectorAll('.pages a');
  const prevMark = document.querySelector('.countPageMark')?.innerText;

  if (action === 'next') {
    const next = Array.from(pageLinks).find(a => a.innerText.trim() === '下一页');
    if (!next) return { error: 'no_next_page' };
    next.click();
  } else if (action === 'previous') {
    const prev = Array.from(pageLinks).find(a => a.innerText.trim() === '上一页');
    if (!prev) return { error: 'no_previous_page' };
    prev.click();
  } else {
    const num = action.replace(/\D/g, '');
    const target = Array.from(pageLinks).find(a => a.innerText.trim() === num);
    if (!target) return { error: 'page_not_found', available: Array.from(pageLinks).map(a => a.innerText.trim()) };
    target.click();
  }

  // Wait for page change
  await new Promise((r, j) => {
    let n = 0;
    const c = () => {
      const mark = document.querySelector('.countPageMark')?.innerText;
      if (mark && mark !== prevMark) r();
      else if (++n > 30) j('timeout');
      else setTimeout(c, 500);
    };
    setTimeout(c, 1000);
  });

  const cap2 = document.querySelector('#tcaptcha_transform_dy');
  if (cap2 && cap2.getBoundingClientRect().top >= 0) return { error: 'captcha' };

  return {
    action,
    total: document.querySelector('.pagerTitleCell')?.innerText?.match(/([\d,]+)/)?.[1] || '0',
    page: document.querySelector('.countPageMark')?.innerText || '?',
    url: location.href
  };
}

Sorting (single evaluate_script)

Replace SORT_HERE with "relevance", "date", "citations", "downloads", or "comprehensive":

javascript
async () => {
  const cap = document.querySelector('#tcaptcha_transform_dy');
  if (cap && cap.getBoundingClientRect().top >= 0) return { error: 'captcha' };

  const sortBy = "SORT_HERE";
  const idMap = {
    'relevance': 'FFD', 'date': 'PT',
    'citations': 'CF', 'downloads': 'DFR', 'comprehensive': 'ZH'
  };

  const liId = idMap[sortBy];
  if (!liId) return { error: 'invalid_sort', valid: Object.keys(idMap) };

  const li = document.querySelector('#orderList li#' + liId);
  if (!li) return { error: 'sort_option_not_found' };

  const prevMark = document.querySelector('.countPageMark')?.innerText;
  li.click();

  // Wait for results to refresh (page resets to 1)
  await new Promise((r, j) => {
    let n = 0;
    const c = () => {
      const mark = document.querySelector('.countPageMark')?.innerText;
      if (mark && mark !== prevMark) r();
      else if (++n > 30) j('timeout');
      else setTimeout(c, 500);
    };
    setTimeout(c, 1000);
  });

  return {
    sortBy,
    total: document.querySelector('.pagerTitleCell')?.innerText?.match(/([\d,]+)/)?.[1] || '0',
    page: document.querySelector('.countPageMark')?.innerText || '?',
    activeLi: document.querySelector('#orderList li.cur')?.innerText?.trim(),
    url: location.href
  };
}

Output

Navigated to page {page}. Total {total} results. Results now sorted by {sortBy}.

Tool calls: 1 (evaluate_script only)

Verified selectors

ElementSelectorNotes
Page links.pages anumbers + 上一页/下一页
Current page.pages a.cur
Next pagetext 下一页, class pagesnums
Page counter.countPageMarktext "1/300"
Sort container#sortList (.order-group)
Sort options#orderList liclick to sort
相关度li#FFDdata-sort="FFD"
发表时间li#PTdata-sort="PT"
被引li#CFdata-sort="CF"
下载li#DFRdata-sort="DFR"
综合li#ZHdata-sort="ZH"
Active sort#orderList li.curhas class cur

Captcha detection

Check #tcaptcha_transform_dy element's getBoundingClientRect().top >= 0. Only active when top >= 0 (visible). Pre-loaded SDK sits at top: -1000000px.

Frequently asked questions

What does the Cnki Navigate Pages AI skill do?

Navigate CNKI search result pages (next/previous/specific page) or change sort order. Use when user wants to see more results or change sorting.

Why use Cnki Navigate Pages on TypingMind?

Because you install it once and use it with any model. Cnki Navigate Pages is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Cnki Navigate Pages in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/cookjohn/cnki-skills/tree/master/skills/cnki-navigate-pages. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Cnki Navigate Pages?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Cnki Navigate Pages?

As many as you like. As long as a model supports skills, you can use Cnki Navigate Pages with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Cnki Navigate Pages AI skill free?

It is published on GitHub by cookjohn. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇