ncbi-datasets-skill

Submit compact NCBI Datasets v2 requests for assembly, genome, taxonomy, and related metadata endpoints. Use when a user wants concise NCBI Datasets summaries; save raw JSON or text only on request.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%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, actionable skill body that gives Claude everything needed to run the script correctly with no concept padding. The only blemish is one duplicated preference rule across two sections.

Suggestions

Consolidate the duplicate targeting guidance: keep a single 'Prefer targeted endpoint calls over broad unfiltered pulls' statement rather than restating it in both Operating rules and Execution behavior.

Consider merging Operating rules and Execution behavior, which overlap in guidance about targeted calls and raw-vs-summary output, to further tighten the body.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence without explaining NCBI or JSON, but 'Prefer targeted metadata paths instead of broad unfiltered pulls' and 'Prefer targeted endpoint calls instead of broad unfiltered dumps' are near-duplicate guidance that could be consolidated.	2 / 3
Actionability	It provides explicit REST path values, named optional fields, three concrete payload patterns, and a copy-paste-ready bash invocation against the real scripts/ncbi_datasets.py.	3 / 3
Workflow Clarity	This is a single-action skill whose invocation is unambiguous (echo JSON \| python script), with Input/Output contracts and a documented failure path; per the simple-skill note an unambiguous single action scores 3.	3 / 3
Progressive Disclosure	The body is under 50 lines and organized into clearly labeled sections, with the only bundle file (scripts/ncbi_datasets.py) referenced one level deep and confirmed to exist.	3 / 3
	Total	11 / 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.

The description is specific, uses third person, includes natural trigger terms, and explicitly answers both what the skill does and when to use it. It is clearly distinct from other skills.

Dimension	Reasoning	Score
Specificity	'Submit compact NCBI Datasets v2 requests for assembly, genome, taxonomy, and related metadata endpoints' lists multiple concrete endpoint actions, matching the multi-action anchor; voice is third person.	3 / 3
Completeness	It states what the skill does (submit compact requests across named endpoints) and when to use it via an explicit 'Use when a user wants concise NCBI Datasets summaries' clause.	3 / 3
Trigger Term Quality	Natural user-facing terms (NCBI Datasets, assembly, genome, taxonomy, summaries) appear with good coverage of how a user would phrase the request.	3 / 3
Distinctiveness Conflict Risk	The NCBI Datasets v2 niche is specific and trigger-scoped, making it unlikely to fire for unrelated skills.	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-datasets-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.