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

93%

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 1-5

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

An exemplary lean skill body: dense operational rules, copy-paste-ready input examples, a clear input/output/error contract, and a well-signaled one-level-deep reference to geo.md that was verified to exist and contain real GEO query patterns. Nothing scored below the top anchor on any dimension.

Dimension	Reasoning	Score
Conciseness	Every line is operational and imperative — endpoint values, parameter defaults, rendering rules, and boundaries with sibling skills — with zero explanation of concepts Claude already knows; nothing reads as padding.	5 / 5
Actionability	Fully executable: four copy-paste JSON payloads covering the common endpoint patterns, an executable bash example, explicit required/optional input fields, and a concrete success/failure output contract including error.code/error.message.	5 / 5
Workflow Clarity	This is a simple single-task skill and the single action (construct a JSON object, pipe it to scripts/ncbi_entrez.py, summarize the compact output) is unambiguous, with defined failure behavior and no destructive or batch operations requiring validation checkpoints.	5 / 5
Progressive Disclosure	The body is a lean overview that conditionally loads references/geo.md only for GEO queries (verified: the file exists, is real content, and is one level deep), delegates the executable surface to scripts/ncbi_entrez.py, and explicitly keeps the import package minimal.	5 / 5
	Total	20 / 20 Passed

Description

83%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 strong, concrete, third-person description with an explicit and specific 'Use when' trigger clause. It enumerates databases and endpoint actions precisely; the only weaknesses are a few missing natural synonyms and mild overlap risk with sibling NCBI skills whose territory it partially names.

Dimension	Reasoning	Score
Specificity	Names the domain ('NCBI Entrez E-Utilities') and several concrete actions ('search, fetch, summary, or link results', 'save raw JSON or XML') across six named databases, but coverage has a minor gap (e.g., the einfo endpoint and elink-to-other-dbs behavior are not mentioned).	4 / 5
Completeness	Explicitly answers both: the 'what' ('Submit compact NCBI Entrez E-Utilities requests for PubMed, Gene, Protein, Nucleotide, PMC metadata, and GEO metadata workflows') and a concrete 'when' ('Use when a user wants concise Entrez search, fetch, summary, or link results'), plus an explicit output behavior ('save raw JSON or XML only on request').	5 / 5
Trigger Term Quality	Good natural keyword coverage ('PubMed', 'Entrez', 'NCBI', 'GEO', 'Gene', 'Protein', 'Nucleotide'), but a few natural synonyms users would say are missing (e.g., 'abstracts', 'citations', 'PMID', 'literature search').	4 / 5
Distinctiveness Conflict Risk	The Entrez E-Utilities niche is clear and mostly distinct, but 'PMC metadata' invites overlap with a dedicated ncbi-pmc-skill and 'GEO metadata' with a standalone GEO skill; the description does not itself delineate those boundaries.	4 / 5
	Total	17 / 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/ncbi-entrez-skill/SKILL.md
Commit: 5fd93af

Reviewed: 10 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.