geo-search-api

Search for gene expression DataSets and Profiles in the NCBI GEO database. Use this skill when the user wants to find microarray, RNA-seq, or other genomic data by keywords, organism, author, or specific fields.

Quality

81%

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

75%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 skill with a real executable script and genuine reference file, clear workflow and validation rules, and appropriate progressive disclosure. The main weakness is redundancy across several generic process sections that pads token use.

Suggestions

Consolidate the overlapping 'When to Use', 'Key Features', 'Example Usage', 'Implementation Details', 'Required Inputs', and 'Recommended Workflow' sections, which repeat the same validate-then-execute-then-review guidance; keep one concrete workflow and remove the generic restatements to improve conciseness.

Add an explicit feedback loop to the workflow (e.g., on API error or empty results, adjust filters using references/query_fields.json and re-run) to raise workflow clarity toward a 5.

Trim the generic 'Output Contract' and 'Validation and Safety Rules' boilerplate to the GEO-specific points (e.g., output name geo_search_api_result.md, NCBI rate-limit/credential handling) so every line earns its place.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete usage examples, but the 'Key Features', 'Example Usage', 'Implementation Details', 'Required Inputs', and 'Recommended Workflow' sections restate the same generic scope/validate/produce guidance several times, adding padding that could be tightened, which fits the 3 anchor better than the lean 4.	3 / 5
Actionability	Provides fully executable, copy-paste-ready commands (python scripts/search_geo.py with concrete --filters and --limit examples), a real script with documented arguments, and a real reference file, matching the 5 anchor for copy-paste-ready coverage of common cases.	5 / 5
Workflow Clarity	Clear sequenced steps ('Recommended Workflow', 'Quick Validation', 'Validation and Safety Rules', 'Failure Handling') with validation before execution and early-stop on missing inputs; it is a read-only search rather than destructive/batch work, and the only minor gap is no explicit re-validate-after-error feedback loop, sitting at 4 just below the 5 anchor.	4 / 5
Progressive Disclosure	Good structure with a SKILL.md overview pointing one level deep to real bundle files (scripts/search_geo.py and references/query_fields.json), both of which exist and are clearly signaled via links; minor organization gaps (some redundant inline guidance that could be trimmed) keep it just below the 5 anchor.	4 / 5
	Total	16 / 20 Passed

Description

87%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 description: third-person voice, concrete capabilities, and an explicit 'Use when...' clause with natural trigger terms. It is specific and well-distinguished from other skills.

Dimension	Reasoning	Score
Specificity	States the concrete action ('Search for gene expression DataSets and Profiles in the NCBI GEO database') plus the filterable dimensions (keywords, organism, author, fields), giving several specific actions with only minor coverage gaps, which sits just below the comprehensive 5 anchor.	4 / 5
Completeness	It explicitly answers both 'what' ('Search for gene expression DataSets and Profiles in the NCBI GEO database') and 'when' ('Use this skill when the user wants to find microarray, RNA-seq, or other genomic data by keywords, organism, author, or specific fields') with concrete trigger phrases, matching the 5 anchor.	5 / 5
Trigger Term Quality	Natural terms a researcher would actually say are present ('microarray', 'RNA-seq', 'genomic data', 'organism', 'author'), with good keyword coverage but a few synonyms/extensions missing, fitting the 4 rather than the 5 anchor.	4 / 5
Distinctiveness Conflict Risk	The niche is clearly bounded to NCBI GEO gene-expression search with distinct triggers (DataSets, Profiles, microarray, RNA-seq), making overlap with other skills minimal, matching the 5 anchor rather than the mostly-distinct 4.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Evidence Insight/geo-search-api/SKILL.md
Commit: 63c61d3

Reviewed: 9 hours 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.