CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

literature-search-biorxiv

Browse and filter life sciences, biology, and medical preprints from bioRxiv and medRxiv. Supports fetching paper metadata by DOI, and browsing by date range with category and keyword filters. Keyword filtering is local, so date ranges MUST be narrow (1-4 weeks) with a category to prevent timeouts.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/literature_search_biorxiv/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

76%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 highly actionable with copy-paste-ready commands and an unusually good decision guide for choosing the right entry point, including an explicit anti-pattern warning. Its weaknesses are the missing post-run verification step for a batch operation and a redundant triple-stated warning, plus one bundle file (citation.bib) that is never surfaced.

Suggestions

Add a post-run verification step for the batch date-range workflow, e.g. "After parsing results.json, check the result count and treat an empty result as a signal to broaden the date range or category rather than retrying the same query".

Consolidate the three repeated narrow-date-range warnings into one authoritative block to reduce token cost without losing emphasis.

Reference references/citation.bib from the body (or move the category lists into a references file) so all bundle content is discoverable from the overview.

DimensionReasoningScore

Conciseness

The body is lean command-and-flag documentation with no explanations of concepts Claude already knows, but the "narrow date ranges + category" warning is repeated three times (Search Strategy Guide, the CRITICAL ANTI-PATTERN block, and Core Rules) and the category lists run ~55 lines, leaving minor trimming opportunities.

4 / 5

Actionability

Fully executable copy-paste commands are given for every entry point (search_by_dates.py with realistic dates, filters, and output redirection; search_by_doi.py with a concrete DOI), plus complete flag documentation — fully covering the common cases.

5 / 5

Workflow Clarity

The entry-point selection workflow is clear (DOI → search_by_doi.py; date+category → search_by_dates.py; topic-only → do not use this skill), but this is a batch operation (downloading all metadata pages) with no post-run validation/verification step such as checking the parsed result count or handling empty/partial results, which caps workflow clarity at 3 per the rubric.

3 / 5

Progressive Disclosure

Both utility scripts are properly referenced with executable paths, sections are clear, and references are one level deep; however references/citation.bib exists in the bundle but is never referenced from the body, and the ~55-line category lists are inlined where a separate reference file would keep the overview leaner.

4 / 5

Total

16

/

20

Passed

Description

71%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 specific, accurate, and well-scoped to the bioRxiv/medRxiv niche with an honest operational constraint. Its main weakness is the absence of any explicit "Use when..." trigger guidance, and natural trigger phrasings like "search" or "find papers" are underrepresented.

Suggestions

Add an explicit trigger clause such as "Use when the user mentions bioRxiv, medRxiv, preprints, or asks to fetch paper metadata by DOI" to satisfy the when-to-use half of completeness.

Include natural search phrasings users would say — e.g., "search" or "find preprints/papers" — alongside the current platform and filter terminology.

DimensionReasoningScore

Specificity

The description lists multiple concrete, comprehensive actions — "Browse and filter life sciences, biology, and medical preprints", "fetching paper metadata by DOI", "browsing by date range with category and keyword filters" — with no vague filler, matching the comprehensive-coverage anchor.

5 / 5

Completeness

The "what" is clear and concrete, but there is no "Use when..." clause or equivalent explicit trigger guidance — the final sentence about narrow date ranges is an operational constraint, not a when-to-use trigger — which caps completeness at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Strong natural terms users would say ("bioRxiv", "medRxiv", "preprints", "paper metadata by DOI", "date range", "category", "keyword"), but common phrasings like "search", "find papers", or "literature" are missing, so coverage is good rather than comprehensive.

4 / 5

Distinctiveness Conflict Risk

"preprints from bioRxiv and medRxiv" plus DOI metadata fetching carves a clear niche with distinct platform triggers, though sibling literature-search skills (e.g., EuropePMC-based ones) could compete for generic paper-finding requests, giving minor overlap risk.

4 / 5

Total

16

/

20

Passed

Validation

100%

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

google-deepmind/science-skills

Path

skills/literature_search_biorxiv/SKILL.md

Revision

4de6786

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill