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.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/biorxiv-database/SKILL.md

Quality

Content

61%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A thorough, actionable skill body with extensive executable examples and a clear one-level reference, weakened by verbosity in non-skill-specific sections and by batch/multi-step workflows that lack validation checkpoints.

Suggestions

Trim the pandas 'Programmatic Integration' walkthrough, the verbose expected test-output block, and the K-Dense Web promo section to restore conciseness and keep only bioRxiv-specific guidance.

Add validation feedback loops to the batch PDF download and literature-review workflows — e.g., confirm each download succeeded and retry on failure, and check result_count before processing results — so workflow_clarity can clear the batch cap.

Fix the executable examples: the 'Author Tracking' loop places a 'python ...' shell command inside a Python for-loop with an un-interpolated '{author}' placeholder; replace with a real subprocess or Python-API call.

Dimension	Reasoning	Score
Conciseness	The body is ~480 lines and mostly efficient in its core examples, but includes unnecessary padding Claude doesn't need: a pandas DataFrame integration walkthrough, a verbose expected test-output block, and a self-promotional K-Dense Web section — fitting 'mostly efficient but could be tightened'.	3 / 5
Actionability	Provides concrete, copy-paste-ready CLI commands with full flags and Python API examples with real method signatures across the common cases; minor gaps such as a 'python ...' invocation inside a Python for-loop and an un-interpolated '{author}' shell placeholder keep it below 5.	4 / 5
Workflow Clarity	The Literature Review Workflow is a clear numbered sequence but has no validation checkpoints, and the batch PDF download loop lacks any verify/retry step — a batch operation without validation triggers the cap at 3.	3 / 5
Progressive Disclosure	Clear overview with a well-signaled one-level-deep reference to references/api_reference.md (verified to exist), good section structure, and most content appropriately placed; minor gaps from inlining the full category list and output schema rather than splitting them out.	4 / 5
	Total	14 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that clearly states both what the skill does and when to use it, with concrete capabilities and a distinct bioRxiv niche. The only gap is a lack of file-extension/synonym triggers like '.pdf' and 'doi'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'searching ... by keywords, authors, date ranges, or categories, retrieving paper metadata, downloading PDFs, or conducting literature reviews' — with comprehensive coverage matching the anchor for listing several specific concrete actions.	5 / 5
Completeness	Explicitly answers both 'what' ('Efficient database search tool for bioRxiv preprint server') and 'when' ('Use this skill when searching ...') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Strong natural terms ('bioRxiv preprint', 'life sciences preprints', 'PDFs', 'literature reviews', 'keywords/authors') but missing file extensions and synonyms like '.pdf' and 'doi' that would warrant a 5.	4 / 5
Distinctiveness Conflict Risk	'bioRxiv preprint server' names a clear niche with distinct triggers and minimal overlap risk with other skills, matching the anchor for a clear niche with distinct triggers.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: googolme/run0204
Path: scientific-skills/biorxiv-database/SKILL.md
Commit: 4902409

Reviewed: 6 hours ago

Table of Contents

Discovery Implementation Validation

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.