Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add YuanyuanMa03/academic-research-skills --skill wos-paper-detailgit clone --depth 1 https://github.com/YuanyuanMa03/academic-research-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/yuanyuanma03/academic-research-skills/wos-paper-detail)<a href="https://agentmods.dev/skills/yuanyuanma03/academic-research-skills/wos-paper-detail"><img src="https://agentmods.dev/badge/skills/yuanyuanma03/academic-research-skills/wos-paper-detail/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/yuanyuanma03/academic-research-skills/wos-paper-detail"><img src="https://agentmods.dev/badge/skills/yuanyuanma03/academic-research-skills/wos-paper-detail.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00028 | $0.02516 |
| Opus 5.5 | $0.00011 | $0.01006 |
| Sonnet 5.5 | $0.00006 | $0.00503 |
| Haiku 4.5 | $0.00003 | $0.00252 |
Grade A, and why
wos-paper-detail scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WoS Paper Detail
Navigate to a WoS full record page and extract comprehensive paper metadata.
Steps
Step 1: Parse Input
Accept either:
- WoS Accession Number:
WOS:000779183600001 - Full URL:
https://www.webofscience.com/wos/woscc/full-record/WOS:000779183600001
Extract the WoS ID if a full URL is provided.
Step 2: Navigate
navigate_page({
url: "{BASE_URL}/wos/woscc/full-record/{WOS_ID}",
initScript: "Object.defineProperty(navigator, 'webdriver', {get: () => undefined})"
})
Step 3: Extract Full Record Data
async () => {
// Wait for full record to load
for (let i = 0; i < 30; i++) {
if (document.querySelector('[data-ta="FullRTa-fullRecordtitle-0"]')) break;
await new Promise(r => setTimeout(r, 500));
}
await new Promise(r => setTimeout(r, 1500));
// Check access
if (document.body.innerText.includes('Sign in') && !document.querySelector('[data-ta="FullRTa-fullRecordtitle-0"]')) {
return { status: 'login_required' };
}
// Helper: get value for a labeled field (h3 label -> parent's non-h3 children)
const getField = (label) => {
const h3 = [...document.querySelectorAll('h3')].find(h => h.textContent.trim() === label);
if (!h3) return '';
const parent = h3.parentElement;
const valueEls = [...parent.children].filter(el => el.tagName !== 'H3');
return valueEls.map(s => s.textContent?.trim()).join(' ').substring(0, 300) || '';
};
// Title
const title = document.querySelector('[data-ta="FullRTa-fullRecordtitle-0"]')?.textContent?.trim() || '';
// Authors
const authors = [...document.querySelectorAll('[data-ta^="SumAuthTa-DisplayName-author-en"]')]
.map(a => a.textContent?.trim());
// Abstract
const abstract = document.querySelector('div.abstract--instance')?.textContent?.trim() || '';
// Source/Journal - extract only journal name from the JCR sidenav component
let source = '';
const sourceSpan = document.querySelector('h3[data-ta="FullRTa-sourceLabel"]')?.parentElement?.querySelector('span.section-label-data');
if (sourceSpan) {
// The span contains app-jcr-sidenav with journal name + popup. Get first text content before "arrow_back"
const fullText = sourceSpan.textContent?.trim() || '';
source = fullText.split('arrow_back')[0].trim();
}
if (!source) {
source = document.querySelector('.summary-source-title-link')?.firstChild?.textContent?.trim() || '';
}
// DOI - try link first, fall back to h3 label extraction
const doiEl = document.querySelector('a[href*="doi.org"]');
const doi = doiEl?.textContent?.trim() || doiEl?.href?.replace(/.*doi\.org\//, '') || getField('DOI');
// Metadata fields
const volume = getField('Volume');
const issue = getField('Issue');
const pages = getField('Page');
const published = getField('Published');
const earlyAccess = getField('Early Access');
const docType = getField('Document Type');
const language = getField('Language');
const accessionNumber = getField('Accession Number');
const issn = getField('ISSN');
const eissn = getField('eISSN');
// Keywords - use parentElement.querySelectorAll('a') to get ALL keyword links
const getKeywords = (label) => {
const h3 = [...document.querySelectorAll('h3')].find(h => h.textContent.trim() === label);
if (!h3) return [];
return [...h3.parentElement.querySelectorAll('a')].map(a => a.textContent?.trim()).filter(Boolean);
};
const authorKeywords = getKeywords('Author Keywords');
const keywordsPlus = getKeywords('Keywords Plus');
// Categories
const researchAreas = getField('Research Areas');
const wosCategories = getField('Web of Science Categories');
// Citations - full record page uses FullRRPTa selectors, NOT stat-number selectors
const citedLinks = [...document.querySelectorAll('a[data-ta*="times-cited-count-link"]')];
// WOSCC link text is "992 In Web of Science Core Collection" - extract leading number
const extractNum = (text) => (text?.match(/^[\d,]+/) || ['0'])[0];
const wosccCited = extractNum(citedLinks.find(a => a.getAttribute('data-ta')?.includes('-WOSCC'))?.textContent?.trim());
const alldbCited = extractNum(citedLinks.find(a => a.getAttribute('data-ta')?.includes('-ALLDB'))?.textContent?.trim());
const mainCited = extractNum(citedLinks.find(a => /^\d/.test(a.textContent?.trim()))?.textContent?.trim());
const citedCount = wosccCited || mainCited || '0';
// References
const refsCount = document.querySelector('a[data-ta*="refCountLink"]')?.textContent?.trim() || '0';
// JIF - extract from JCR popup/sidenav text content
let jif = '', jifYear = '', jifFiveYear = '', jcrQuartile = '';
const jcrPopup = document.querySelector('[class*="journal-content"], app-jcr-sidenav');
if (jcrPopup) {
const jcrText = jcrPopup.textContent || '';
// Pattern: "Journal Impact Factor ™20242.8Five Year3.4"
const jifMatch = jcrText.match(/Impact Factor\s*(?:™|TM)?\s*(\d{4})\s*([\d.]+)/);
if (jifMatch) { jifYear = jifMatch[1]; jif = jifMatch[2]; }
const fyMatch = jcrText.match(/Five Year\s*([\d.]+)/);
if (fyMatch) jifFiveYear = fyMatch[1];
// Quartile: "159/316 Q3" pattern in JCR summary
const qMatch = jcrText.match(/\d+\/\d+\s*(Q[1-4])/);
if (qMatch) jcrQuartile = qMatch[1];
}
// Full text links
const ftLinks = [...document.querySelectorAll('a[data-ta^="FRLinkTa"]')].map(a => ({
text: a.textContent?.trim()?.replace(/open_in_new/g, '').trim(),
href: a.href
})).filter(l => l.text);
return {
status: 'ok',
title, authors, abstract, source, doi,
volume, issue, pages, published, earlyAccess,
docType, language, accessionNumber, issn, eissn,
authorKeywords, keywordsPlus,
researchAreas, wosCategories,
citedCount, alldbCited, refsCount,
jif, jifYear, jifFiveYear, jcrQuartile,
ftLinks
};
}
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 224 lines · 28 tokens per session scan A 65897c814be7
wos-paper-detail is a skill published in the GitHub repository YuanyuanMa03/academic-research-skills (75 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 2,516 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-29.
Other skills, from other repositories
agent-platform-tuning
Agent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using Agent Platform infrastructure. Don't use for model training outside Agent Platform, model deployment to endpoints (use agent-platform-deploy), or managing serving endpoints (use agent-platform-endpoint-management).
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
gke-alert-configuration
Configures alerting policies in Terraform for Google Kubernetes Engine (GKE) clusters, workloads, and services using PromQL and Google Cloud Managed Service for Prometheus. Use when writing, analyzing, validating, or deploying Terraform alerting policies to monitor GKE service latency, traffic, error rates using…
secops-detection-engineering
Author, validate, test, and deploy YARA-L 2.0 detection rules and evaluate end-to-end detection coverage gaps in Google SecOps. Use when writing new detection rules, tuning existing rules, validating syntax, testing logic against historical telemetry, or evaluating detection coverage against threat intelligence blogs…
application-design-center-design-deploy
Processes GCP infrastructure design and deployment workflows within Application Design Center (ADC). Use when: - Designing GCP infrastructure with Terraform. - Validating local HCL. - Performing best-practice plan scans. - Importing templates to Application Design Center (ADC). - Deploying templates. - Troubleshooting…
cloud-run-basics
Manages Cloud Run services, jobs, and worker pools. Use when you need to deploy applications responding to HTTP requests (services), run event-triggered or scheduled tasks (jobs), or handle always-on pull-based background processing (worker pools).