CtrlK
BlogDocsLog inGet started
Tessl Logo

pubmed-database

Direct REST API access to PubMed. Advanced Boolean/MeSH queries, E-utilities API, batch processing, citation management. For Python workflows, prefer biopython (Bio.Entrez). Use this for direct HTTP/REST work or custom API implementations.

80

1.16x
Quality

78%

Does it follow best practices?

Impact

72%

1.16x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/pubmed-database/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

85%

10%

PubMed Literature Monitor: Automated Abstract Extraction Tool

Programmatic PubMed data extraction with Python

Criteria
Without context
With context

Uses Bio.Entrez

0%

0%

ESearch usage

87%

100%

EFetch usage

87%

100%

History server for large sets

100%

100%

Batched retrieval

100%

100%

Rate limit compliance

100%

100%

User-Agent or email header

0%

100%

Local caching

100%

100%

Retry / exponential backoff

100%

100%

README with install instructions

100%

100%

80%

4%

Systematic Review Search Protocol: Hypertension Drug Therapy in Elderly Patients

Advanced PubMed search query construction and field tags

Criteria
Without context
With context

PICO framework used

100%

100%

MeSH [mh] tag

90%

100%

MeSH subheading

0%

0%

Drug substance [nm] tag

0%

0%

[tiab] tag usage

100%

100%

Publication type [pt] filter

100%

100%

Date range [dp] syntax

87%

100%

Free full text filter

75%

100%

Synonyms with OR

100%

100%

Boolean AND grouping

100%

100%

Language filter

100%

100%

Elderly population term

100%

100%

53%

16%

Reference Library Cleanup: Batch Citation Lookup and Export

Citation matching, export formats, and batch operations

Criteria
Without context
With context

ECitMatch endpoint used

0%

0%

Pipe-delimited citation format

0%

0%

ELink for related articles

86%

66%

EPost for batch UID upload

0%

0%

.nbib export format

0%

100%

Batch export API format

66%

100%

User-Agent or email identification

100%

100%

Output files present

100%

100%

Repository
K-Dense-AI/claude-scientific-skills
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.