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 pm-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/pm-paper-detail)<a href="https://agentmods.dev/skills/yuanyuanma03/academic-research-skills/pm-paper-detail"><img src="https://agentmods.dev/badge/skills/yuanyuanma03/academic-research-skills/pm-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/pm-paper-detail"><img src="https://agentmods.dev/badge/skills/yuanyuanma03/academic-research-skills/pm-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 | $0.00050 | $0.01512 |
| Opus 5.5 | $0.00020 | $0.00605 |
| Sonnet 5.5 | $0.00010 | $0.00302 |
| Haiku 4.5 | $0.00005 | $0.00151 |
Grade A, and why
pm-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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PubMed Paper Detail
Extract complete metadata from a PubMed paper using NCBI E-utilities efetch API (XML format).
Arguments
$ARGUMENTS is a PMID (PubMed ID, an integer like 35641793).
Steps
1. Navigate to the paper page
Use mcp__chrome-devtools__navigate_page:
- url:
https://pubmed.ncbi.nlm.nih.gov/{PMID}/
This shows the paper detail page to the user in the browser.
2. Extract full metadata via E-utilities (evaluate_script)
Replace PMID_HERE with the actual PMID from $ARGUMENTS:
async () => {
const pmid = "PMID_HERE";
// efetch XML for full record (abstract, MeSH, authors with affiliations)
const fetchResp = await fetch(
`https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=pubmed&id=${pmid}&retmode=xml`
);
const xml = await fetchResp.text();
const doc = new DOMParser().parseFromString(xml, 'text/xml');
// Title
const title = doc.querySelector('ArticleTitle')?.textContent || '';
// Abstract (may have labeled sections like BACKGROUND, METHODS, etc.)
const abstractParts = Array.from(doc.querySelectorAll('AbstractText')).map(el => {
const label = el.getAttribute('Label');
return label ? `**${label}**: ${el.textContent}` : el.textContent;
});
const abstract = abstractParts.join('\n\n') || '';
// Authors with affiliations
const authors = Array.from(doc.querySelectorAll('Author')).map(a => {
const lastName = a.querySelector('LastName')?.textContent || '';
const foreName = a.querySelector('ForeName')?.textContent || '';
const initials = a.querySelector('Initials')?.textContent || '';
const affiliations = Array.from(a.querySelectorAll('AffiliationInfo Affiliation'))
.map(af => af.textContent);
return {
name: foreName ? `${lastName} ${foreName}` : `${lastName} ${initials}`,
nameAbbr: `${lastName} ${initials}`,
affiliations
};
});
// MeSH terms
const meshTerms = Array.from(doc.querySelectorAll('MeshHeading')).map(mh => {
const descriptor = mh.querySelector('DescriptorName')?.textContent || '';
const majorTopic = mh.querySelector('DescriptorName')?.getAttribute('MajorTopicYN') === 'Y';
const qualifiers = Array.from(mh.querySelectorAll('QualifierName')).map(q => ({
name: q.textContent,
major: q.getAttribute('MajorTopicYN') === 'Y'
}));
return { descriptor, majorTopic, qualifiers };
});
// Keywords
const keywords = Array.from(doc.querySelectorAll('Keyword')).map(k => k.textContent);
// Publication types
const pubTypes = Array.from(doc.querySelectorAll('PublicationType')).map(p => p.textContent);
// Grant/funding
const grants = Array.from(doc.querySelectorAll('Grant')).map(g => ({
id: g.querySelector('GrantID')?.textContent || '',
agency: g.querySelector('Agency')?.textContent || '',
country: g.querySelector('Country')?.textContent || ''
}));
// IDs
const doi = doc.querySelector('ArticleId[IdType="doi"]')?.textContent || '';
const pmcid = doc.querySelector('ArticleId[IdType="pmc"]')?.textContent || '';
// Journal info
const journal = doc.querySelector('Journal Title')?.textContent
|| doc.querySelector('Title')?.textContent || '';
const journalAbbr = doc.querySelector('ISOAbbreviation')?.textContent || '';
const issn = doc.querySelector('ISSN')?.textContent || '';
const volume = doc.querySelector('Volume')?.textContent || '';
const issue = doc.querySelector('Issue')?.textContent || '';
const pages = doc.querySelector('MedlinePgn')?.textContent || '';
// Publication date
const pubDateEl = doc.querySelector('PubDate');
const year = pubDateEl?.querySelector('Year')?.textContent || '';
const month = pubDateEl?.querySelector('Month')?.textContent || '';
const day = pubDateEl?.querySelector('Day')?.textContent || '';
const medlineDate = pubDateEl?.querySelector('MedlineDate')?.textContent || '';
const pubDate = medlineDate || [year, month, day].filter(Boolean).join(' ');
// Language
const language = doc.querySelector('Language')?.textContent || '';
return {
pmid, title, abstract, authors,
meshTerms, keywords, pubTypes, grants,
doi, pmcid, journal, journalAbbr, issn,
volume, issue, pages, pubDate, language
};
}
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 · 159 lines · 50 tokens per session scan A e6b69c3972e3
pm-paper-detail is a skill published in the GitHub repository YuanyuanMa03/academic-research-skills (75 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 1,512 once invoked, about $0.0002 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
paper2poster-poster
Use when the user wants to turn an academic paper into a conference poster, poster outline, poster copy deck, poster layout brief, poster.yaml style draft, or Paper2Poster-ready generation package. Trigger for paper-to-poster requests involving PDF papers, arXiv links, manuscripts, PPTX posters, conference…
manuscript-optimizer
Use when auditing, restructuring, or revising a research manuscript whose scientific question, claim hierarchy, evidence chain, section logic, figures, terminology, or prose may be unclear or out of sync. Apply before sentence-level polishing, especially for whole drafts, major revisions, resubmissions, overclaiming…
review-article-architecture
Use when writing, restructuring, or auditing a Review, survey, or Perspective rather than a research article, especially a commissioned one written across many sessions. Covers the governing plan document, drift detection, single-definition thesis and field judgements, section-owns-figure allocation, display-item…
write-scientific-manuscript
Diagnose and repair the clarity and logic of manuscript prose, journal-agnostic. Use when a passage is technically correct but hard to follow: buried topic sentences, missing logical bridges, ambiguous referents, abstract noun chains, overloaded sentences, incomplete comparisons with no stated dataset or metric or…
paper-reviewer
Referee-side skill for Nature Portfolio manuscripts: write a referee report, inventory every ask and sub-ask in received comments, grade drafted replies, and test reply readability. Check methodology, statistics, reporting, reproducibility and data/code availability. Preserve referee wording, numbering and order…
figure-planner
Use when designing, restructuring, or auditing manuscript figures and you need to define one main claim per figure, assign panel roles, align legends with the text, or decide what belongs in main figures versus supplement.