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 ieee-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/ieee-paper-detail)<a href="https://agentmods.dev/skills/yuanyuanma03/academic-research-skills/ieee-paper-detail"><img src="https://agentmods.dev/badge/skills/yuanyuanma03/academic-research-skills/ieee-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/ieee-paper-detail"><img src="https://agentmods.dev/badge/skills/yuanyuanma03/academic-research-skills/ieee-paper-detail.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00041 | $0.01846 |
| Opus 5 | $0.00020 | $0.00923 |
| Sonnet 5 | $0.00008 | $0.00369 |
| Haiku 4.5 | $0.00004 | $0.00185 |
Grade A, and why
ieee-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 13d ago.
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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IEEE Xplore Paper Detail Extraction
Extract complete metadata from an IEEE Xplore article page.
Steps
Step 1: Navigate to article
Determine the article URL from $ARGUMENTS:
- If an article number is given (e.g.
8876906): URL is{BASE_URL}/document/{ARNUMBER}/ - If a full URL is given: use that URL directly
- If a DOI is given: URL is
https://doi.org/{DOI}(will redirect to IEEE Xplore)
Use navigate_page with initScript:
navigate_page({
url: "{article_url}",
initScript: "Object.defineProperty(navigator, 'webdriver', {get: () => undefined})"
})
If the article is already open in the current tab, skip navigation and go directly to Step 3.
Step 2: Check access
After navigation, verify:
- If the page shows a captcha or bot challenge: tell the user "请在浏览器中完成验证后告知我。"
- If the page URL no longer points to IEEE Xplore, the user may need to log in. 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。"
Step 3: Extract metadata
Use evaluate_script with built-in waiting. Do NOT use wait_for.
async () => {
// Wait for article content to load (up to 15s)
for (let i = 0; i < 30; i++) {
if (document.querySelector('.document-title') || document.querySelector('h1[class*="title"]')) break;
await new Promise(r => setTimeout(r, 500));
}
const result = {};
// Title
result.title = document.querySelector('.document-title span')?.textContent?.trim() ||
document.querySelector('h1[class*="title"]')?.textContent?.trim() || '';
// Authors
result.authors = [...document.querySelectorAll('.authors-info a[href*="/author/"]')]
.map(a => a.textContent.trim()).filter(Boolean);
// Abstract
result.abstract = document.querySelector('.abstract-text div[xplmathjax]')?.textContent?.trim() ||
document.querySelector('.abstract-text')?.textContent?.trim() || '';
// DOI
const doiLink = document.querySelector('a[href*="doi.org"]');
result.doi = doiLink?.textContent?.trim() || '';
// Publication info
result.publication = document.querySelector('.stats-document-abstract-publishedIn a')?.textContent?.trim() || '';
// Meta info (Published in, Date, DOI, Publisher, Conference Location, etc.)
const metaItems = document.querySelectorAll('.abstract-desktop-div .u-pb-1');
result.metaInfo = [...metaItems].map(el => el.textContent.trim().replace(/\s+/g, ' ')).filter(Boolean);
// Keywords - multiple fallback strategies (keywords section may need scrolling to load)
// Strategy 1: keywords module links
let kwLinks = document.querySelectorAll('.stats-keywords-module a');
result.keywords = [...kwLinks].map(a => a.textContent.trim()).filter(Boolean);
// Strategy 2: keyword list items
if (result.keywords.length === 0) {
const kwItems = document.querySelectorAll('.doc-keywords-list-theme li a, .doc-keywords-list li a');
result.keywords = [...kwItems].map(a => a.textContent.trim()).filter(Boolean);
}
// Strategy 3: extract from the plain text citation (keywords field inside citation text)
if (result.keywords.length === 0) {
const kwMatch = document.body.innerText.match(/keywords:\s*\{([^}]+)\}/i);
if (kwMatch) {
result.keywords = kwMatch[1].split(';').map(k => k.trim()).filter(Boolean);
}
}
// Strategy 4: meta tag
if (result.keywords.length === 0) {
const kwMeta = document.querySelector('meta[name="keywords"]');
if (kwMeta) {
result.keywords = kwMeta.content.split(',').map(k => k.trim()).filter(Boolean);
}
}
// PDF link
const pdfLink = document.querySelector('a[href*="stamp/stamp.jsp"]');
result.pdfUrl = pdfLink?.href || '';
// Article number from URL
result.arnumber = window.location.pathname.match(/\/document\/(\d+)/)?.[1] || '';
// Cited by count — use multiple strategies
const citeMetric = [...document.querySelectorAll('.document-banner-metric')].find(el => el.textContent.includes('Cites'));
result.citedBy = citeMetric?.querySelector('.document-banner-metric-count')?.textContent?.trim() || '';
// Fallback: regex from button text like "70Cites inPapers"
if (!result.citedBy) {
const citeBtn = [...document.querySelectorAll('button')].find(b => b.textContent.includes('Cites'));
const citeMatch = citeBtn?.textContent?.match(/(\d+)\s*Cites/);
result.citedBy = citeMatch ? citeMatch[1] : '';
}
// Full text views
const viewMetric = [...document.querySelectorAll('.document-banner-metric')].find(el => el.textContent.includes('Views'));
result.fullTextViews = viewMetric?.querySelector('.document-banner-metric-count')?.textContent?.trim() || '';
if (!result.fullTextViews) {
const viewBtn = [...document.querySelectorAll('button, .document-banner-metric')].find(b => b.textContent.includes('Views'));
const viewMatch = viewBtn?.textContent?.match(/(\d[\d,]*)\s*Full/);
result.fullTextViews = viewMatch ? viewMatch[1] : '';
}
// Section headings (article structure / TOC)
result.sections = [...document.querySelectorAll('.document-toc a, h2')]
.map(el => el.textContent.trim())
.filter(t => t && !t.includes('Abstract') && t.length < 100)
.slice(0, 20);
// References count
const refSection = document.querySelector('#references');
const refItems = document.querySelectorAll('.reference-container, [class*="reference-item"]');
result.referenceCount = refItems.length;
return result;
}
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.
- 13d ago First seen · 194 lines · 41 tokens per session scan A 568ba470c6c0
ieee-paper-detail is a skill published in the GitHub repository YuanyuanMa03/academic-research-skills (63 stars, last pushed 22d ago), licensed MIT. It adds 41 tokens to every session and 1,846 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other skills, from other repositories
cnki-exp-search-automation
A browser-based automation tool for CNKI, the China National Knowledge Infrastructure research database, that runs advanced literature searches and collects result lists and abstracts.
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…
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…