ncbi-entrez-skill

Submit compact NCBI Entrez E-Utilities requests for PubMed, Gene, Protein, Nucleotide, PMC metadata, and GEO metadata workflows. Use when a user wants concise Entrez search, fetch, summary, or link results; save raw JSON or XML only on request.

Quality

100%

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

100%Weight 40%Scale 1-3

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

A tight, highly actionable skill body: concrete executable examples, clear input/output/execution contract, and well-signaled one-level-deep reference separation for GEO. It assumes Claude's intelligence and avoids redundant explanation.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: it never explains what NCBI, Entrez, or a PMID is, and every section (operating rules, execution behavior, input/output) earns its tokens.	3 / 3
Actionability	Provides concrete JSON payloads with real endpoint/param values and an executable bash one-liner piping input to the script, matching the copy-paste-ready anchor rather than the pseudocode level 2.	3 / 3
Workflow Clarity	The single action (read JSON from stdin, run the script, return output) is unambiguous via the Input, Execution, and Output sections; the read-only query nature means no destructive-operation validation checkpoint is required.	3 / 3
Progressive Disclosure	GEO detail is split one level deep into the real `references/geo.md` (verified to exist) and clearly signaled ("load only when the user is specifically asking about GEO"), with `scripts/ncbi_entrez.py` also present as referenced.	3 / 3
	Total	12 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 precise, third-person description that names concrete actions and databases, supplies natural trigger terms, and gives an explicit 'Use when' clause covering both what and when. It is concise without padding and clearly distinct from sibling NCBI skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("search, fetch, summary, or link results") across named databases (PubMed, Gene, Protein, Nucleotide, PMC, GEO), matching the 'Lists multiple specific concrete actions' anchor rather than the partial level 2.	3 / 3
Completeness	Explicitly states what it does ("Submit compact NCBI Entrez E-Utilities requests...") and when to use it via a clear "Use when a user wants..." clause, satisfying both what and when.	3 / 3
Trigger Term Quality	Natural user-facing terms like "PubMed", "Gene", "Protein", and "Entrez search, fetch, summary, or link results" give good coverage of what a user would actually say; not merely technical jargon.	3 / 3
Distinctiveness Conflict Risk	The "NCBI Entrez E-Utilities" framing with specific databases forms a clear niche unlikely to trigger competing skills; it scopes GEO/PMC to metadata rather than their dedicated workflows.	3 / 3
	Total	12 / 12 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/ncbi-entrez-skill/SKILL.md
Commit: 11c74d6

Reviewed: 17 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.