CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

literature-search-europepmc

Search Europe PMC for scientific literature and download open-access full texts and PDFs. Retrieve full-text XML/plain text by PMCID, get citation lists and bibliography.

Quality

81%

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 highly actionable, well-structured CLI skill reference whose commands, arguments, and workflows are fully executable and include appropriate validation and error-recovery guidance. Its main weaknesses are an orphaned bundle file (references/citation.bib is never referenced) and inline API-reference detail that could live in a separate file.

Suggestions

Reference `references/citation.bib` from the body (e.g., a Sources/Citation section) or remove it, so no bundle file is undiscoverable.

Move the detailed per-command argument lists and the search-syntax quick reference into a references/ file (e.g., API.md), keeping SKILL.md as a lean overview with one example per subcommand.

Deduplicate the OPEN_ACCESS guidance — it appears both in Core Rules and in the note after the search syntax section.

DimensionReasoningScore

Conciseness

The body is a dense, on-point command reference with no explanations of concepts Claude already knows; only minor trimming is needed (the database stats sentence in the intro, and the OPEN_ACCESS note duplicated in Core Rules and again after the search syntax section).

4 / 5

Actionability

Every subcommand has copy-paste-ready `uv run` examples with real DOIs/PMCIDs, complete argument documentation with defaults, output schema descriptions, and jq-based multi-step recipes — all verified to match the actual script CLI.

5 / 5

Workflow Clarity

Common Workflows are clearly sequenced step-by-step, and the body includes explicit validation ("check the pdf downloaded is not empty or corrupted") plus a feedback loop (check `isOpenAccess` and fall back to the abstract on retrieval failure); operations are read-only so the destructive/batch cap does not apply.

5 / 5

Progressive Disclosure

Sections are well organized and the script is clearly referenced throughout, but the bundle's `references/citation.bib` is never mentioned in the body (an orphaned, undiscoverable reference) and roughly 150 lines of per-command argument and search-syntax reference are fully inlined in SKILL.md rather than split out — matching the anchor where content that should be separate is inline.

3 / 5

Total

17

/

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.

A specific, third-person description that concretely covers all the skill's capabilities, but it omits any "Use when..." trigger guidance and is missing common synonyms like "papers", "articles", and "PubMed". These gaps leave it above average yet short of the top anchors on completeness and trigger terms.

Suggestions

Add an explicit trigger clause, e.g. "Use when searching for scientific papers, retrieving open-access full texts or PDFs, or gathering citations/references by DOI, PMID, or PMCID."

Include natural synonyms users would say — "papers", "articles", "PubMed", "abstracts" — alongside "scientific literature" to broaden trigger-term coverage.

Optionally mention the life-siences/biomedical domain explicitly to further reduce overlap with general literature-search skills.

DimensionReasoningScore

Specificity

The description lists four concrete actions — "Search Europe PMC for scientific literature", "download open-access full texts and PDFs", "Retrieve full-text XML/plain text by PMCID", "get citation lists and bibliography" — comprehensively covering every subcommand (search, download_pdf, get_fulltext, get_citations, get_references) with format and ID detail.

5 / 5

Completeness

The "what" is clear and detailed, but there is no "Use when..." clause or equivalent explicit trigger guidance; per the rubric guideline this caps completeness at 3, since "when" is absent rather than merely improvable.

3 / 5

Trigger Term Quality

Good natural keyword coverage ("scientific literature", "full texts", "PDFs", "citations", "bibliography") but common synonyms and variations a user would say — "papers", "articles", "PubMed", "abstracts" — are missing, so it falls short of the comprehensive-synonym anchor.

4 / 5

Distinctiveness Conflict Risk

Naming the specific database "Europe PMC" gives it a clear niche, but generic literature/citation vocabulary could overlap with other search or bibliography skills, so minor overlap risk remains.

4 / 5

Total

16

/

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_europepmc/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.