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

78%

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

82%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 well-structured, highly actionable skill body: copy-paste-ready commands covering all documented use cases, a clear decision-tree entry guide, and bundle scripts that exist and match the documented flags. Minor improvements possible: consolidate the repeated date-range warnings, add explicit result-verification/error-recovery guidance, and either reference or remove the unused citation.bib.

DimensionReasoningScore

Conciseness

The body is efficient and assumes competence — no explanation of what preprints or APIs are — with concrete, trimmable redundancy being the triple repetition of the narrow-date-range warning (frontmatter, "CRITICAL ANTI-PATTERN", "Core Rules"). This fits anchor 4 ('efficient; minor instances that could be trimmed'); it is above anchor 3 because padding is limited and above-trim content is deliberate emphasis, but short of anchor 5's every-token-earns-its-place.

4 / 5

Actionability

Every workflow is given as a copy-paste-ready `uv run scripts/...` command with full flags, and the examples cover the common cases: category browsing, OR-logic keyword filtering with abstracts, author search, and DOI fetch — all verified against the actual scripts' argparse flags. This matches anchor 5 ('fully executable; copy-paste ready; specific examples cover the common cases'), not anchor 4, because there are no missing key details.

5 / 5

Workflow Clarity

The "Search Strategy Guide (Read First)" gives a clear decision tree (DOI → search_by_doi.py; date+category → search_by_dates.py; keywords only → use another skill), and rules for output redirection, pagination, and listing sources are explicit. It fits anchor 4 ('clear sequence with most checkpoints') rather than 5 because there are no explicit verification or error-recovery steps (e.g., what to do with empty results or an invalid category) beyond the scripts' built-in strict validation.

4 / 5

Progressive Disclosure

Good structure with clear sections, and both referenced script paths (scripts/search_by_dates.py, scripts/search_by_doi.py) exist in the bundle with behavior matching the docs. It is not anchor 5 because references/citation.bib is present in the bundle but never referenced or signaled in the body, and the ~35-line category lists are inlined rather than split into a reference file; it is above anchor 3 because what references exist are clearly signaled and one level deep.

4 / 5

Total

17

/

20

Passed

Description

66%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 specific, well-scoped description with strong natural trigger terms (bioRxiv, medRxiv, preprints, DOI) and concrete named actions. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness at 3, and minor coverage gaps such as author filtering.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user mentions bioRxiv, medRxiv, preprints, or wants metadata for a life-science paper by DOI."

Mention the author-filtering capability ("filter by author within a date range") so the 'what' coverage matches the scripts.

Clarify boundaries with sibling literature skills, e.g. "For keyword-only discovery or PDF downloads, use a keyword-capable literature skill instead."

DimensionReasoningScore

Specificity

The description lists several concrete actions — "Browse and filter life sciences, biology, and medical preprints", "fetching paper metadata by DOI", "browsing by date range with category and keyword filters" — which match anchor 4's 'several specific actions; minor gaps'. It falls short of anchor 5 because capabilities like author filtering (supported by the scripts) and output handling are not covered.

4 / 5

Completeness

The 'what' is clearly and concretely stated, but there is no 'Use when...' clause or equivalent explicit trigger guidance — the closing sentence about narrow date ranges is a constraint, not usage triggering. Per the judging guideline, a missing explicit trigger clause caps completeness at 3, and it is not a 2 because the 'what' is far from vague.

3 / 5

Trigger Term Quality

Strong natural keywords users would actually say: "preprints", "bioRxiv", "medRxiv", "DOI", "life sciences", "biology", "medical". A few common variations are missing ("papers", "literature search", "citations", "abstracts"), so it fits anchor 4 ('good keyword coverage; a few natural terms missing') rather than anchor 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

Naming bioRxiv and medRxiv gives it a clear, distinctive niche with low generic-conflict risk, but it sits in a family of closely related literature-search skills (e.g., EuropePMC-based ones) and the description does not delineate when to prefer it — fitting anchor 4's 'mostly distinct; minor overlap risk with closely related skills' rather than anchor 5's minimal conflict risk.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

google-deepmind/science-skills

Path

skills/literature_search_biorxiv/SKILL.md

Reviewed

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.