Agent skill

Web of Science Search

by cookjohn in cookjohn/wos-skills

Searches Web of Science by topic, author, title, DOI or advanced query from a logged-in browser page, with database, edition and sort options.

No licenceAuto-check passedResearch & Science

Install Web of Science Search

skills CLI
$ npx skills add cookjohn/wos-skills --skill wos-search -a claude-code

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

GitHub CLI
$ gh skill install cookjohn/wos-skills wos-search --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/wos-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/wos-search .claude/skills/wos-search && 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
wos-search
GitHub stars
123
Token cost
~2k tokens
SKILL.md length
519 words
Files
1
Skills in repo
6
Repo updated
First seen
Licence
None found

At a glance

Searches Web of Science by topic, author, title, DOI or advanced query from a logged-in browser page, with database, edition and sort options.

  • Works in 3 steps: Build API Request Body → Execute API Call via evaluate_script → Present Results
  • Finding highly cited papers on a topic in Web of Science
  • SKILL.md covers Important: Browser Prerequisite, Language Guidance, Parameter Reference and Steps, plus 1 more section
  • Reaches webofscience.com

What it does

The skill calls the Web of Science internal API with a single evaluate_script call from the browser, so no page navigation is needed. The browser has to be open on a webofscience.com page and logged in. Queries are built as rows of field and text pairs joined with AND, OR or NOT, covering topic, title, author, DOI, journal, year, affiliation, abstract, funding and country.

You can pick the database, such as the Core Collection, all databases, MEDLINE, preprints or SciELO, limit the Core Collection to the SCI, SSCI or conference editions, and sort by relevance, citations, date or usage. The record count defaults to 10 and tops out at 50. Because SCI and SSCI mostly index English-language work, Chinese keywords are translated into English and the translation is reported back to you.

When your agent uses it

  • Finding highly cited papers on a topic in Web of Science
  • Looking up a paper by DOI, title or author in the Core Collection
  • Restricting a search to SCI, SSCI or conference proceedings editions

Example prompts

  • “Search Web of Science for the most cited papers on value co-creation.”
  • “Find papers by the author Smith about graph neural networks in SCI and SSCI, newest first.”
  • “Look up the Core Collection record for the paper titled Attention Is All You Need.”

Requirements

  • A browser logged in to webofscience.com
  • Chrome DevTools MCP

Workflow steps

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

  1. Build API Request Body
  2. Execute API Call via evaluate_script
  3. Present Results

What it can do on your machine

Read from SKILL.md and the folder at commit 268b139. 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 json and 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:

    • webofscience.com

    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

Web of Science Search loads about 2k tokens when it runs. Until then it costs about 32 tokens; SKILL.md has 519 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~32
When it runs · the whole SKILL.md, loaded when a task matches
~2k

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 519 words (~1,994 tokens).

“Search Web of Science via internal API. Supports edition filtering, sorting, and multiple databases — all in a single evaluate_script call.”

— opening of SKILL.md by cookjohn
name
wos-search
argument-hint
[search keywords] [--edition SCI/SSCI/...] [--sort citations/date/relevance] [--db woscc|alldb|...]
user-invocable
true
disable-model-invocation
false

Read the full SKILL.md on GitHub

Files

Just SKILL.md in skills/wos-search of cookjohn/wos-skills.

Open the folder on GitHubat commit 268b139

Compare with similar skills

Web of Science Search 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.

Web of Science Search compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Web of Science Search this skillcookjohn/wos-skills123—~2kAutomated safety check: PassNone
Literature Reviewneflibata-feng/MyArxiv-Agent12620 repos~5.9kAutomated safety check: NotesMIT
Preprint Search on bioRxivLigphiDonk/Oh-my--paper73812 repos~3.7kAutomated safety check: PassMIT
Systematic Literature Review Builderbytedance/deer-flow84k2 repos~4.3kAutomated safety check: PassMIT
Paper Research on arXivXiaomiMiMo/MiMo-Code14k—~1.5kAutomated safety check: PassMIT
Literature Review AgentAr9av/PaperOrchestra6771 repos~5.2kAutomated safety check: PassCustom licence

Similar skills

  • Literature Review

    neflibata-feng/MyArxiv-Agent

    Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.).

    126 GitHub starsUsed in 20 repos~5.9k tokens
    Research & ScienceAuto-check: notes
  • Preprint Search on bioRxiv

    LigphiDonk/Oh-my--paper

    Searches bioRxiv life sciences preprints by keyword, author, date range or category with a Python script, returning JSON metadata and optional PDF downloads.

    738 GitHub starsUsed in 12 repos~3.7k tokens
    Research & ScienceAuto-check passed
  • Searches arXiv across many papers on one topic, extracts each paper's methodology and findings in parallel, and synthesizes a cited literature review.

    84k GitHub starsUsed in 2 repos~4.3k tokens
    Research & ScienceAuto-check passed
  • Paper Research on arXiv

    XiaomiMiMo/MiMo-Code

    Searches arXiv, fetches metadata, generates BibTeX, downloads PDFs and finds citations and related papers using a bundled Python script.

    14k GitHub stars~1.5k tokensUpdated yesterday
    Research & ScienceAuto-check passed
  • Literature Review Agent

    Ar9av/PaperOrchestra

    Step 3 of the PaperOrchestra pipeline (arXiv:2604.05018). An agent skill from Ar9av/PaperOrchestra.

    677 GitHub starsUsed in 1 repo~5.2k tokens
    Research & ScienceAuto-check passed
  • Conference Paper Recommender

    juliye2025/evil-read-arxiv

    Searches DBLP for papers from top conferences such as CVPR, ICLR and NeurIPS, adds Semantic Scholar data, scores them and writes a yearly Obsidian note.

    1.7k GitHub stars~2.5k tokensUpdated 25 days ago
    Research & ScienceAuto-check passed

More from cookjohn/wos-skills

  • Web of Science Export

    cookjohn/wos-skills

    Exports Web of Science records into Zotero directly, or to RIS, BibTeX, Excel and plain-text files through the site's export menu.

    123 GitHub stars~1k tokensUpdated 7 mo ago
    Auto-check passed
  • Walks a Web of Science full-record page through to the publisher's site to locate and download the paper's PDF, or reports why it could not.

    123 GitHub stars~1.4k tokensUpdated 7 mo ago
    Auto-check passed
  • WoS Results Page Navigation

    cookjohn/wos-skills

    Jumps to a given page of Web of Science search results, or loads more results from the previous search, by changing the results URL or re-running the search API.

    123 GitHub stars~751 tokensUpdated 7 mo ago
    Auto-check passed
  • Web of Science Paper Details

    cookjohn/wos-skills

    Fetches the full record for a paper from Web of Science by its WoS accession number or URL and presents the metadata as a structured summary.

    123 GitHub stars~2.2k tokensUpdated 7 mo ago
    Auto-check passed
  • Web of Science Result Parser

    cookjohn/wos-skills

    Parse search results from the current WoS results page or API response. Internal skill used by other skills.

    123 GitHub stars~763 tokensUpdated 7 mo ago
    Auto-check passed

Works with

Questions about Web of Science Search

What does Web of Science Search do?

Searches Web of Science by topic, author, title, DOI or advanced query from a logged-in browser page, with database, edition and sort options. The skill calls the Web of Science internal API with a single evaluate_script call from the browser, so no page navigation is needed.com page and logged in.

When should I use Web of Science Search?

Web of Science Search fits situations like: finding highly cited papers on a topic in Web of Science; looking up a paper by DOI, title or author in the Core Collection; restricting a search to SCI, SSCI or conference proceedings editions.

How do I install Web of Science Search in Claude Code?

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

How do I install Web of Science Search in Codex?

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

Can I use Web of Science Search 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/wos-skills --skill wos-search -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/wos-search, .gemini/skills/wos-search, .github/skills/wos-search and .opencode/skills/wos-search in your project.

What does Web of Science Search need to run?

SKILL.md names no scripts, command-line tools or credentials: Web of Science Search is instructions for the agent only. Our summary lists: A browser logged in to webofscience.com; Chrome DevTools MCP.

Does Web of Science Search access the network?

SKILL.md names 1 domain. In commands or code: webofscience.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Web of Science Search 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 Web of Science Search use?

No licence was found for Web of Science Search or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Web of Science Search use?

About 2k tokens (SKILL.md is roughly 8k 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 Web of Science Search?

Skills that share tags, products or a category with Web of Science Search: Literature Review (neflibata-feng/MyArxiv-Agent, 126 stars), Preprint Search on bioRxiv (LigphiDonk/Oh-my--paper, 738 stars), Systematic Literature Review Builder (bytedance/deer-flow, 84k stars) and Paper Research on arXiv (XiaomiMiMo/MiMo-Code, 14k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Web of Science Search?

cookjohn (a GitHub user) maintains it in cookjohn/wos-skills, which has 123 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on March 13, 2026.

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