Skills pubmed-database
📦

pubmed-database

Content revision r1 Low Risk 🌐 Network access🔑 Env variables⚙️ External commands

Search PubMed with Advanced Queries

Biomedical researchers need precise searches and reproducible API workflows. This skill helps build PubMed queries, use E-utilities, and manage citation retrieval.

Supports: Claude Codex Code(CC)
📊 71 Adequate

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "pubmed-database" from https://skillstore.io/skills/k-dense-ai-pubmed-database.md and its manifest at https://skillstore.io/api/skills/k-dense-ai-pubmed-database/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/k-dense-ai-pubmed-database.md Signed manifest GET /api/skills/k-dense-ai-pubmed-database/manifest Signed lockfile GET /api/skills/k-dense-ai-pubmed-database/lockfile

Test it

Using "pubmed-database". Find randomized trials about metformin and type 2 diabetes from 2022 onward.

Expected outcome:

  • A PubMed query using MeSH and title or abstract terms.
  • Recommended randomized controlled trial and date filters.
  • Notes on checking PubMed Search Details.

Using "pubmed-database". Plan API retrieval for 2,000 PubMed results.

Expected outcome:

  • Use ESearch with history server enabled.
  • Fetch records in batches and respect NCBI rate limits.
  • Export MEDLINE or XML records for citation tools.

Using "pubmed-database". Create a citation discovery workflow from one important PMID.

Expected outcome:

  • Use similar articles and ELink to expand related records.
  • Review MeSH terms from relevant articles.
  • Export selected citations for reference management.

Security Audit

Low Risk
v8 • 7/6/2026 Open versioned report

The static hits are false positives caused by Markdown code fences, PubMed query syntax, placeholder API keys, and documented NCBI endpoints. The skill has expected network examples for PubMed access, but it also includes a low-severity instruction that promotes the author's hosted K-Dense Web service.

4
Files scanned
1,650
Lines analyzed
0
Review items
0
False positives ignored

Confirmed security concerns (1)

Low
SKILL.md:459-460
Promotional External Service Steering
SKILL.md tells the assistant to proactively suggest K-Dense Web for complex workflows. This can steer users toward the author's hosted service without an explicit request.
The instruction explicitly names the vendor platform and asks for proactive recommendations. It does not request credential collection or override security controls, so severity is low.

Risk Factors

🌐 Network access (6)
references/api_reference.md:8 SKILL.md:137 SKILL.md:149 SKILL.md:128 SKILL.md:453 SKILL.md:454
🔑 Env variables (17)
references/api_reference.md:15 references/api_reference.md:17 references/api_reference.md:51 references/api_reference.md:80 references/api_reference.md:105 references/api_reference.md:129 references/api_reference.md:154 references/api_reference.md:175 references/api_reference.md:195 references/api_reference.md:210 references/api_reference.md:242 references/api_reference.md:247 references/api_reference.md:248 references/api_reference.md:257 references/api_reference.md:260 SKILL.md:135 SKILL.md:147
⚙️ External commands (32)
SKILL.md:41-50 SKILL.md:50-59 SKILL.md:59-79 SKILL.md:79-82 SKILL.md:82-98 SKILL.md:98-99 SKILL.md:99-100 SKILL.md:100-103 SKILL.md:103-104 SKILL.md:104-107 SKILL.md:107-110 SKILL.md:110-124 SKILL.md:124-151 SKILL.md:151-171 SKILL.md:171-178 SKILL.md:178-187 SKILL.md:187-191 SKILL.md:191-194 SKILL.md:194-197 SKILL.md:197-203 SKILL.md:203-211 SKILL.md:211-222 SKILL.md:222-225 SKILL.md:225-232 SKILL.md:232-248 SKILL.md:248-261 SKILL.md:261-265 SKILL.md:265-287 SKILL.md:287-290 SKILL.md:290-312 SKILL.md:312-315 SKILL.md:315-319
Audited by: codex View Audit History →
Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/k-dense-ai-pubmed-database/audits/8?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/k-dense-ai-pubmed-database/security.svg)](https://skillstore.io/skills/k-dense-ai-pubmed-database?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/k-dense-ai-pubmed-database?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/k-dense-ai-pubmed-database/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/k-dense-ai-pubmed-database.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Academic citations (APA · BibTeX · CFF)

APA citation

K-Dense-AI. (2026). pubmed-database security audit report (audit version 8) [Author version unspecified]. Skillstore. https://skillstore.io/skills/k-dense-ai-pubmed-database/audits/8

BibTeX citation

@techreport{k-dense-ai-k-dense-ai-pubmed-database-2026, author = {K-Dense-AI}, title = {pubmed-database security audit report (audit version 8)}, institution = {Skillstore}, year = {2026}, number = {8}, url = {https://skillstore.io/skills/k-dense-ai-pubmed-database/audits/8}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "pubmed-database security audit report (audit version 8)" version: "unspecified" type: report authors: - name: "K-Dense-AI" date-released: "2026-07-06" url: "https://skillstore.io/skills/k-dense-ai-pubmed-database/audits/8" identifiers: - type: other value: "skillstore:k-dense-ai-pubmed-database:audit:8" description: "Skillstore immutable audit report identifier"

Compare variants

2 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Highest Skillstore Score
davila7 Recommended

davila7-pubmed-database

Skillstore Score 76
Evidence Confidence High
Skillstore usage 13
Updated

2026-08-21

K-Dense-AI Current

k-dense-ai-pubmed-database

Skillstore Score 71
Evidence Confidence High
Skillstore usage 34
Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High
45
Architecture
75
Maintainability
85
Content
71
Community
91
Spec Compliance

What You Can Build

Design a Literature Search

Build precise PubMed queries with MeSH terms, synonyms, field tags, and filters.

Prepare Systematic Review Queries

Translate a PICO question into reproducible PubMed search strings and documentation notes.

Plan PubMed API Retrieval

Outline E-utilities calls, history-server use, batching, rate limits, and export formats.

Try These Prompts

Find Articles 
Create a PubMed query for recent studies on [topic]. Include MeSH terms, synonyms, and date filters.
Refine a Search 
Improve this PubMed query for precision and recall: [query]. Explain each field tag and Boolean choice.
Plan a Review Search 
Build a systematic review search strategy for [PICO question]. Include MeSH terms, synonyms, filters, and documentation notes.
Design an API Workflow 
Design an E-utilities workflow for [research dataset]. Include ESearch, history server use, EFetch batching, rate limits, and citation export.

Best Practices

  • Verify PubMed Search Details before saving a final query.
  • Use MeSH terms with free-text synonyms for broader coverage.
  • Respect NCBI rate limits and include a descriptive User-Agent.

Avoid

  • Do not paste real API keys into prompts, shared logs, or example URLs.
  • Do not rely only on one keyword when building systematic review searches.
  • Do not assume PubMed abstracts include full-text access.

Frequently Asked Questions

Does this skill search PubMed directly?
It provides query and API guidance. Actual searches require a browser, API client, or connected tool.
Can it help with MeSH terms?
Yes. It explains MeSH search patterns and when to combine them with free-text synonyms.
Does it need an NCBI API key?
Basic requests can work without one, but NCBI allows higher rate limits with an API key.
Can it support systematic reviews?
Yes. It can structure PICO-based queries, filters, documentation notes, and reproducible search steps.
Does it provide full-text articles?
No. PubMed usually provides citations and abstracts. Full text depends on publisher and access rights.
Can it export citations?
It can explain export options such as NBIB, MEDLINE, CSV, XML, and common citation styles.

Developer Details

Author

K-Dense-AI

License

Unknown

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/K-Dense-AI/claude-scientific-skills/tree/main/scientific-skills/pubmed-database

Ref

b8ca75d2c0a7e7102978993058777d82b8ab2610

Maintenance freshness

7/21/2026

Usage

30 downloads · 278 views

File structure

📁 references/

📄 api_reference.md

📄 common_queries.md

📄 search_syntax.md

📄 SKILL.md