Sd Advanced Search logo

Sd Advanced Search

Community
cookjohn
sd-advanced-search

Advanced search on ScienceDirect with filters like author, journal, year, title, keywords. Use when the user wants filtered academic paper search.

Overview

Publishercookjohn
Repositorysd-skills
Skill namesd-advanced-search
Stars
88
Forks
12
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 Sd Advanced Search 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/sd-skills/tree/master/skills/sd-advanced-search
  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/sd-skills.git /tmp/sd-skills
mkdir -p .claude/skills
cp -r /tmp/sd-skills/skills/sd-advanced-search .claude/skills/sd-advanced-search
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Sd Advanced Search 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 Sd Advanced Search 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 Sd Advanced Search 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.

ScienceDirect Advanced Search

Perform a filtered search on ScienceDirect by constructing URL parameters directly.

URL Parameter Reference

Build the search URL as {BASE_URL}/search?{params}&show=25 using these parameters:

ParamFieldExample
qsAll fields (keywords)machine learning
takTitle, abstract or keywordsneural network
titleTitle onlytransformer
authorsAuthor name(s)Hinton
pubJournal or book titleNature
dateYear or year range2023 or 2020-2025
volumeVolume number(s)5 or 7-11
issueIssue number(s)1 or 1-3
pagePage number(s)55 or 1-9
docIdISSN or ISBN0957-4174
affiliationsAuthor affiliationMIT
referencesCited referencesSmith 2020

Multiple parameters can be combined. For example:

{BASE_URL}/search?tak=deep+learning&authors=LeCun&date=2020-2025&show=25

Steps

Step 1: Parse user intent

From $ARGUMENTS, identify which fields the user wants to filter on. Map natural language to URL parameters:

  • "by author X" → authors=X
  • "in journal Y" → pub=Y
  • "from 2020 to 2025" / "since 2020" → date=2020-2025
  • "about topic Z" → tak=Z or qs=Z
  • "titled ..." → title=...

Step 2: Navigate

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

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

Step 3: Check access

  • If the page shows "Are you a robot" or captcha: auto-click the Cloudflare Turnstile checkbox using the procedure below. If auto-click fails after 2 attempts, tell the user "请在浏览器中完成验证后告知我。"
  • If the URL no longer contains sciencedirect or search after navigation, the user may have been redirected to a login/authentication page. Tell the user: "页面被重定向,请在浏览器中完成登录或认证后告知我。" Then wait.
Cloudflare Turnstile auto-click procedure

When a captcha page is detected (title "请稍候…" or body contains "Are you a robot"):

  1. Wait for the Turnstile iframe to load — use evaluate_script to poll for #captcha-box (up to 8s).
  2. Take a snapshot — use take_snapshot to get the a11y tree. The checkbox is inside a cross-origin iframe but Chrome DevTools MCP can see it:
    Iframe "包含 Cloudflare 安全质询的小组件"
      checkbox "确认您是真人"   ← target uid
  3. Click the checkbox — use click(uid) on the checkbox element.
  4. Wait and verify — wait 3-5s, then check if document.contentType changed or the page URL changed (indicating success). If still on captcha, retry once or fall back to asking the user.

Step 4: Extract results

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

javascript
async () => {
  // Wait for results to load (up to 10s)
  for (let i = 0; i < 20; i++) {
    if (document.querySelector('li.ResultItem') || document.querySelector('.search-body-results-text')) break;
    await new Promise(r => setTimeout(r, 500));
  }

  const items = document.querySelectorAll('li.ResultItem');
  const papers = [];

  for (let i = 0; i < items.length; i++) {
    const item = items[i];
    const titleLink = item.querySelector('a.result-list-title-link');
    const journal = item.querySelector('a.subtype-srctitle-link');
    const dateSpans = item.querySelectorAll('.srctitle-date-fields > span');
    const date = dateSpans.length > 1 ? dateSpans[dateSpans.length - 1].textContent.trim() : '';
    const authors = [...item.querySelectorAll('.Authors .author')].map(a => a.textContent.trim());
    const doi = item.getAttribute('data-doi');
    const pii = titleLink?.href?.match(/pii\/(\w+)/)?.[1] || '';
    const articleType = item.querySelector('.article-type')?.textContent?.trim() || '';
    const isOpenAccess = !!item.querySelector('.access-label');

    papers.push({
      rank: i + 1,
      title: titleLink?.textContent?.trim() || '',
      pii, doi: doi || '',
      journal: journal?.textContent?.trim() || '',
      date, authors, articleType, openAccess: isOpenAccess,
    });
  }

  const totalText = document.querySelector('.search-body-results-text')?.textContent?.trim() || '';
  const pageInfo = document.querySelector('.Pagination li:first-child')?.textContent?.trim() || '';
  return { papers, totalResults: totalText, pageInfo };
}

Step 5: Present results

Same format as sd-search. Additionally, show the applied filters at the top:

Search filters: author={X}, journal={Y}, year={Z}
Found {totalResults}. {pageInfo}

1. {title} ...

Notes

  • URL parameter approach avoids form filling, keeping operations to 2 tool calls.
  • All parameters are optional and combinable.
  • If the user provides a very specific query (e.g., DOI or PII), consider using sd-paper-detail instead.

Frequently asked questions

What does the Sd Advanced Search AI skill do?

Advanced search on ScienceDirect with filters like author, journal, year, title, keywords. Use when the user wants filtered academic paper search.

Why use Sd Advanced Search on TypingMind?

Because you install it once and use it with any model. Sd Advanced Search 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 Sd Advanced Search in TypingMind?

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

Which AI models can use Sd Advanced Search?

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 Sd Advanced Search?

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

Is the Sd Advanced Search 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 👇