biorxiv-database

Efficient database search tool for bioRxiv preprint server. Use this skill when searching for life sciences preprints by keywords, authors, date ranges, or categories, retrieving paper metadata, downloading PDFs, or conducting literature reviews.

1.37x

Quality

88%

Does it follow best practices?

Impact

80%

1.37x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Evaluation results

52%

-4%

Preprint Trend Analysis for a Research Group

Keyword search with category filtering and JSON output

Criteria

Without context

With context

Uses biorxiv_search.py script

60%

70%

Keyword flag used

25%

Category filter applied

90%

Valid category string

100%

Days-back or date range used

100%

Output saved to JSON file

50%

62%

Correct JSON structure parsed

20%

100%

Pandas DataFrame used for analysis

Date field used in analysis

100%

requests dependency installed

Analysis output produced

100%

Does NOT query API directly

100%

96%

48%

Research Collaboration Discovery Tool

Python API usage and author search workflow

Criteria

Without context

With context

Imports BioRxivSearcher

20%

100%

Calls search_by_author()

33%

100%

format_result() called

100%

Results saved to JSON files

100%

include_abstract parameter used

100%

Multiple authors handled

100%

requests dependency installed

25%

50%

Date range specified

62%

100%

Output script runnable

90%

100%

Does NOT reimplement search

100%

Combined results file

100%

92%

21%

Preprint Metadata Collector and Targeted Search Tool

DOI lookup, search field targeting, and result limiting

Criteria

Without context

With context

Uses biorxiv_search.py script

100%

--doi flag used

33%

100%

Full DOI URL accepted

100%

--search-fields flag used

33%

100%

--limit flag used

100%

--verbose flag used

100%

--output flag used

100%

requests dependency installed

DOI output parsed correctly

50%

100%

Shell script or run log produced

100%

Does NOT use full DOI URL as plain DOI without stripping

100%

Repository: K-Dense-AI/claude-scientific-skills
Commit: 71add64

Evaluated: 27 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Preprint Trend Analysis for a Research Group Research Collaboration Discovery Tool Preprint Metadata Collector and Targeted Search Tool

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.