Agent skill

Gs Fulltext

by cookjohn in cookjohn/gs-skills

Get full-text access links for a Google Scholar paper - PDF, DOI, Sci-Hub, and publisher links.

MITAuto-check passedResearch & Science

Install Gs Fulltext

skills CLI
$ npx skills add cookjohn/gs-skills --skill gs-fulltext -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install cookjohn/gs-skills gs-fulltext --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/cookjohn/gs-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/gs-fulltext .claude/skills/gs-fulltext && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
gs-fulltext
GitHub stars
524
Token cost
~1.1k tokens
SKILL.md length
253 words
Files
1
Skills in repo
6
Repo updated
First seen
Licence
MIT

At a glance

Get full-text access links for a Google Scholar paper - PDF, DOI, Sci-Hub, and publisher links.

  • Works in 4 steps: Collect links from search results → Resolve additional links (evaluate_script) → Report → …
  • User wants to read
  • SKILL.md covers Arguments, Prerequisites, Steps and Notes
  • Reaches sci-hub.ru and doi.org

What it does

Gs Fulltext is an agent skill from cookjohn/gs-skills. Get full-text access links for a Google Scholar paper - PDF, DOI, Sci-Hub, and publisher links. Use when user wants to read or download a paper's full text.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Research & Science, covering Academic paper search and PDF. The repository describes itself as: Google Scholar skills for Claude Code — search, citation tracking, full-text access, and Zotero export via Chrome DevTools MCP. The licence is MIT.

When your agent uses it

  • User wants to read
  • Download a papers full text

Example prompts

  • “/gs-fulltext”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Collect links from search results
  2. Resolve additional links (evaluate_script)
  3. Report
  4. Open full text (optional)

What it can do on your machine

Read from SKILL.md and the folder at commit df03c99. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are javascript).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • sci-hub.ru
    • doi.org

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Gs Fulltext loads about 1.1k tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 253 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~42
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from cookjohn/gs-skills at commit df03c99, republished under its MIT licence (© cookjohn). 253 words, ~1,050 tokens.

Download SKILL.mdSave it as .claude/skills/gs-fulltext/SKILL.md (or your agent's skills folder).
name
gs-fulltext
description
Get full-text access links for a Google Scholar paper - PDF, DOI, Sci-Hub, and publisher links. Use when user wants to read or download a paper's full text.
argument-hint
[data-cid or result number from previous search]

Google Scholar Full Text Access

Resolve and present all full-text access options for a paper found in Google Scholar search results.

Arguments

$ARGUMENTS can be:

  • A data-cid from a previous search result
  • A result number (e.g., 3) referring to a previous search result

Prerequisites

This skill works best after a previous gs-search or gs-advanced-search call, which already extracts fullTextUrl and href for each result. If those are available, use them directly.

Steps

From the previous search result, extract these fields for the target paper:

  • fullTextUrl: direct PDF/HTML link (from .gs_ggs a)
  • href: link to the paper's publisher page (from .gs_rt a)
  • dataCid: cluster ID

If no previous search context is available, search for the paper first using gs-search.

Navigate to the Google Scholar results page (if not already there), then extract full-text links for the specific paper:

javascript
async () => {
  const cid = "DATA_CID_HERE";

  // Find the result item by data-cid
  const item = document.querySelector(`.gs_r.gs_or.gs_scl[data-cid="${cid}"]`);
  if (!item) return { error: 'not_found', message: 'Paper not found on current page. Try searching again.' };

  const titleEl = item.querySelector('.gs_rt a');
  const title = titleEl?.textContent?.trim() || item.querySelector('.gs_rt')?.textContent?.trim() || '';
  const paperUrl = titleEl?.href || '';

  // Full-text PDF/HTML link (shown on the right side of results)
  const fullTextEl = item.querySelector('.gs_ggs a') || item.querySelector('.gs_or_ggsm a');
  const fullTextUrl = fullTextEl?.href || '';
  const fullTextType = fullTextEl?.querySelector('span.gs_ctg2')?.textContent?.trim() || '';

  // Meta info for context
  const meta = item.querySelector('.gs_a')?.textContent || '';
  const parts = meta.split(' - ');
  const authors = parts[0]?.trim() || '';
  const journalYear = parts[1]?.trim() || '';

  // Try to extract DOI from paper URL
  let doi = '';
  if (paperUrl.includes('doi.org/')) {
    doi = paperUrl.replace(/^https?:\/\/(dx\.)?doi\.org\//, '');
  }

  // Build access links
  const links = {};

  if (fullTextUrl) {
    links.fullText = fullTextUrl;
    links.fullTextType = fullTextType || (fullTextUrl.endsWith('.pdf') ? '[PDF]' : '[HTML]');
  }

  if (paperUrl) {
    links.publisher = paperUrl;
  }

  if (doi) {
    links.doi = `https://doi.org/${doi}`;
    links.scihub = `https://sci-hub.ru/${doi}`;
  } else if (paperUrl) {
    // Sci-Hub also works with direct URLs
    links.scihub = `https://sci-hub.ru/${paperUrl}`;
  }

  return {
    dataCid: cid,
    title,
    authors,
    journalYear,
    doi,
    fullTextUrl,
    fullTextType,
    paperUrl,
    links
  };
}
Step 3: Report
## Full Text Links — {title}

**Authors:** {authors} | {journalYear}

**Direct Full Text:**
{links.fullText ? "- " + links.fullTextType + " " + links.fullText : "No direct full text link available"}

**Publisher Page:**
{links.publisher ? "- " + links.publisher : "N/A"}

**DOI:**
{links.doi ? "- " + links.doi : "No DOI detected"}

**Sci-Hub:**
{links.scihub ? "- " + links.scihub : "N/A"}
Step 4: Open full text (optional)

If the user wants to read the paper immediately, use mcp__chrome-devtools__new_page to open the preferred link in this priority:

  1. fullTextUrl (direct PDF/HTML, usually free)
  2. DOI link (may require subscription)
  3. Sci-Hub link (fallback)
  4. Publisher page

Notes

  • This skill uses 1-2 tool calls: evaluate_script (if already on results page) or navigate_page + evaluate_script
  • Google Scholar's full-text links (.gs_ggs) are usually free/open-access PDFs
  • DOI may not always be extractable from the paper URL
  • Sci-Hub works with both DOI and direct URL
  • Opening full text in a new tab adds 1 more tool call (new_page)

© cookjohn, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/gs-fulltext of cookjohn/gs-skills.

Open the folder on GitHubat commit df03c99

Compare with similar skills

Gs Fulltext next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Gs Fulltext compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Gs Fulltext this skillcookjohn/gs-skills524—~1.1kAutomated safety check: PassMIT
Summaryalaliqing/claude-paper3441 repos~2kAutomated safety check: NotesMIT
Paper ReadingEdwardxlai/easyread848—~567Automated safety check: PassMIT
Ref Downloaderltczding-gif/ref-downloader139—~5.9kAutomated safety check: PassMIT
Paper Readingsodalone/paper-reading-skill142—~1.3kAutomated safety check: PassNone
Paper ExplainerZJU-REAL/Easel3.2k—~1.4kAutomated safety check: PassApache-2.0

Similar skills

  • Summary

    alaliqing/claude-paper

    Use this for a quick summary of a research paper's core ideas and key points.

    344 GitHub starsUsed in 1 repo~2k tokens
    Research & ScienceAuto-check: notes
  • Paper Reading

    Edwardxlai/easyread

    论文共读:用 EasyRead(E:\CursorProject\easyread)这个本地工具读论文。用户给一篇 PDF 或 arXiv 编号时,导入文献库、翻译成中文(后台引擎或对话里的 agent 亲自译);之后边读边讨论,agent 读用户在页面上的笔记和提问,把回答、解释、原文核对提示追加到对应段落旁。用于…

    848 GitHub stars~567 tokensUpdated yesterday
    Research & ScienceAuto-check passed
  • Ref Downloader

    ltczding-gif/ref-downloader

    A skill your agent uses when the user asks to batch-download academic PDFs with ref-downloader — either ALL references of one paper (Mode A: DOI or PDF input), OR a custom batch of papers (Mode B…

    139 GitHub stars~5.9k tokensUpdated 4 mo ago
    Research & ScienceAuto-check passed
  • Paper Reading

    sodalone/paper-reading-skill

    系统阅读、解释和批判性分析单篇 arXiv AI / 机器人论文,并生成一份主线清楚、核心内容不缺失、审稿证据可追溯的自包含 Markdown 报告。适用于 arXiv 链接、ID 或其 PDF 的精读、方法/理论/系统讲解、完整 Claim 审查、实验/证明/协议/代码证据核对、相关文献定位和复现或验证判断;默认执行完整精读,仅在用户明确要求速读时缩减覆盖范围。当前流水线不支持无法解析出…

    142 GitHub stars~1.3k tokensUpdated 2 mo ago
    Research & ScienceAuto-check passed
  • Paper Explainer

    ZJU-REAL/Easel

    科研论文解读:解析 arXiv/PDF 的公式与图表,提炼问题、贡献、方法、关键图和结论,再产出 B站/视频号解读视频或知乎/公众号图文。

    3.2k GitHub stars~1.4k tokensUpdated yesterday
    Research & ScienceAuto-check passed
  • Paper Reading

    voidful/academic-skills

    太奶讀論文 — 一位百歲阿嬤用繁體中文、生活比喻和動漫梗,帶你讀懂學術論文。當使用者提供論文 PDF、arXiv 連結、或貼上論文文字,並想理解論文內容時,一定要使用此技能。觸發詞包括:讀論文、解釋論文、看不懂、幫我理解這篇、這篇在說什麼、paper reading、explain this paper。適用於任何學術論文的直觀導讀。

    133 GitHub stars~1.4k tokensUpdated 6 mo ago
    Research & ScienceAuto-check passed

More from cookjohn/gs-skills

  • Gs Advanced Search

    cookjohn/gs-skills

    Perform advanced Google Scholar search with filters - author, journal, date range, exact phrase, title-only.

    524 GitHub stars~1.2k tokensUpdated 6 mo ago
    Auto-check passed
  • Gs Cited By

    cookjohn/gs-skills

    Find papers that cite a given Google Scholar paper. An agent skill from cookjohn/gs-skills.

    524 GitHub stars~935 tokensUpdated 6 mo ago
    Auto-check passed
  • Gs Export

    cookjohn/gs-skills

    Export Google Scholar paper(s) to Zotero via BibTeX. An agent skill from cookjohn/gs-skills.

    524 GitHub stars~1.2k tokensUpdated 6 mo ago
    Auto-check passed
  • Gs Navigate Pages

    cookjohn/gs-skills

    Navigate Google Scholar search result pages. An agent skill from cookjohn/gs-skills.

    524 GitHub stars~901 tokensUpdated 6 mo ago
    Auto-check passed
  • Gs Search

    cookjohn/gs-skills

    Search Google Scholar for academic papers by keywords. An agent skill from cookjohn/gs-skills.

    524 GitHub stars~1k tokensUpdated 6 mo ago
    Auto-check passed

Questions about Gs Fulltext

What does Gs Fulltext do?

Get full-text access links for a Google Scholar paper - PDF, DOI, Sci-Hub, and publisher links. Gs Fulltext is an agent skill from cookjohn/gs-skills. Get full-text access links for a Google Scholar paper - PDF, DOI, Sci-Hub, and publisher links.

When should I use Gs Fulltext?

Gs Fulltext fits situations like: user wants to read; download a papers full text.

How do I install Gs Fulltext in Claude Code?

Run `npx skills add cookjohn/gs-skills --skill gs-fulltext -a claude-code`. Or copy the skill folder (skills/gs-fulltext in cookjohn/gs-skills) into .claude/skills/gs-fulltext in your project. Claude Code loads it when a task matches its description.

How do I install Gs Fulltext in Codex?

Run `npx skills add cookjohn/gs-skills --skill gs-fulltext -a codex`. Or copy the skill folder (skills/gs-fulltext in cookjohn/gs-skills) into .agents/skills/gs-fulltext in your project. Codex loads it when a task matches its description.

Can I use Gs Fulltext in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cookjohn/gs-skills --skill gs-fulltext -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gs-fulltext, .gemini/skills/gs-fulltext, .github/skills/gs-fulltext and .opencode/skills/gs-fulltext in your project.

What does Gs Fulltext need to run?

SKILL.md names no scripts, command-line tools or credentials: Gs Fulltext is instructions for the agent only.

Does Gs Fulltext access the network?

SKILL.md names 2 domains. In commands or code: sci-hub.ru and doi.org; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Gs Fulltext safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Gs Fulltext use?

Gs Fulltext is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Gs Fulltext use?

About 1.1k tokens (SKILL.md is roughly 4.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Gs Fulltext?

Skills that share tags, products or a category with Gs Fulltext: Summary (alaliqing/claude-paper, 344 stars), Paper Reading (Edwardxlai/easyread, 848 stars), Ref Downloader (ltczding-gif/ref-downloader, 139 stars) and Paper Reading (sodalone/paper-reading-skill, 142 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Gs Fulltext?

cookjohn (a GitHub user) maintains it in cookjohn/gs-skills, which has 524 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on March 13, 2026.

Source: cookjohn/gs-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.