biorxiv-skill

Submit compact bioRxiv and medRxiv API requests for details, publication-linkage, and DOI lookups. Use when a user wants concise preprint metadata summaries

Quality

83%

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

Quality

Content

92%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.

The body is a lean, highly actionable single-purpose skill: a copy-paste-ready execution command, concrete example payloads, and an explicit success/error contract that matches the bundled script. Its only flaw is minor redundancy — a repeated guidance phrase and a duplicated example payload — which slightly dents token efficiency.

Suggestions

Deduplicate the example JSON payload: keep the concrete examples in the Input section and reference them from Execution instead of repeating one verbatim.

Merge the overlapping guidance about not pasting large collections into chat into a single operating rule covering both page size and save_raw.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes Claude's competence, and explains nothing it already knows, matching the 'efficient; minor instances of over-explanation' anchor. Not 5 because the 'pasting long collections into chat' guidance is repeated across two bullets and the full example JSON payload is duplicated between the Input and Execution sections.	4 / 5
Actionability	The 'echo ... \| python scripts/rest_request.py' command is copy-paste ready, three concrete example payloads cover the common cases (date-range details, DOI details, pubs), and the documented interface matches the actual script. This matches the 'fully executable; copy-paste ready' anchor.	5 / 5
Workflow Clarity	This is a single-task skill with an unambiguous action (pipe a JSON config to the script and summarize the output), so the simple-skill exception applies and clarity earns a 5. Error feedback is explicit ('Failure returns ok=false with error.code and error.message') and operations are read-only, so no destructive/batch validation cap applies.	5 / 5
Progressive Disclosure	The body is under 50 lines with well-organized sections and no need for external references, satisfying the rubric's simple-skill guideline for a top score. The single referenced file, scripts/rest_request.py, exists and matches the documented interface, and the References section explicitly bounds the bundle.	5 / 5
	Total	19 / 20 Passed

Description

75%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.

The description is concise, specific, and answers both 'what' and 'when' with natural trigger terms in third person. Its main weaknesses are a 'when' clause that covers only one of the three stated capabilities and keyword coverage missing common synonyms like 'manuscript' or 'preprint server'.

Suggestions

Broaden the 'Use when' clause to cover all stated capabilities, e.g., 'Use when a user wants preprint metadata, publication linkage, or DOI lookups on bioRxiv or medRxiv'.

Add common natural trigger variations such as 'preprint server', 'manuscript', or 'paper details' to improve trigger-term coverage.

Clarify what 'details' requests return (e.g., 'fetch preprint metadata by date range or DOI') to make the capability set more concrete.

Dimension	Reasoning	Score
Specificity	Names the domain ('bioRxiv and medRxiv API') and several concrete actions ('details, publication-linkage, and DOI lookups'), matching the 'several specific actions; minor gaps' anchor. Falls short of 5 because coverage is not comprehensive (e.g., date-range retrieval and what 'details' returns are unstated).	4 / 5
Completeness	Has a clear 'what' ('Submit compact bioRxiv and medRxiv API requests for details, publication-linkage, and DOI lookups') and an explicit 'when' ('Use when a user wants concise preprint metadata summaries'). Not 5 because the 'when' clause covers only metadata summaries and omits the DOI-lookup and publication-linkage trigger scenarios; the explicit 'Use when' clause rules out the cap of 3.	4 / 5
Trigger Term Quality	Includes natural terms users would say — 'bioRxiv', 'medRxiv', 'preprint', 'metadata', 'DOI' — giving good keyword coverage per the anchor. Not 5 because common variations like 'manuscript', 'paper', or 'preprint server' are missing.	4 / 5
Distinctiveness Conflict Risk	'bioRxiv and medRxiv API' is a clear niche with distinct triggers, but generic phrasing like 'API requests' and 'DOI lookups' leaves minor overlap risk with a generic REST-client or DOI/Crossref skill. This fits the 'mostly distinct; minor overlap risk' anchor rather than the fully distinct anchor 5.	4 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: openai/plugins
Path: plugins/life-science-research/skills/biorxiv-skill/SKILL.md
Commit: 5fd93af

Reviewed: 2 days 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.