geo-database

Access NCBI GEO for gene expression/genomics data. Search/download microarray and RNA-seq datasets (GSE, GSM, GPL), retrieve SOFT/Matrix files, for transcriptomics and expression analysis.

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/databases/geo-database/SKILL.md

Quality

Content

65%

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

The body is rich with executable, actionable code but is overly verbose for a SKILL.md, repeating imports and explaining domain concepts Claude already knows. Workflow sequencing lacks explicit validation checkpoints and most detail lives inline rather than in the provided reference.

Suggestions

Move advanced material (E-utilities API specs, differential-expression and meta-analysis pipelines) into references/geo_reference.md and replace the inline blocks with brief pointers, keeping SKILL.md a lean overview.

Add explicit validation checkpoints to batch/download workflows (e.g. verify file integrity or sample counts before proceeding, with a fix-and-retry loop) to lift workflow clarity.

Remove repetitive re-imports and boilerplate (re-downloading the same GSE in every section) by defining shared helpers once, and cut the Overview/Key Concepts explanations of what GEO and MIAME are.

Dimension	Reasoning	Score
Conciseness	The ~815-line body explains concepts Claude already knows (the Overview on what GEO is, Key Concepts defining SOFT/MINiML/MIAME) and repeats boilerplate re-imports of GEOparse across nearly every code block; it is mostly useful but could be tightened.	2 / 3
Actionability	Provides numerous complete, executable Python functions (search, fetch, download, differential expression, meta-analysis) that are copy-paste ready with real imports and parameters.	3 / 3
Workflow Clarity	Capabilities are organized into numbered sections, but there is no end-to-end sequenced workflow with validation checkpoints; batch and destructive operations (batch_download_geo, FTP downloads) rely on try/except without explicit verify-then-proceed feedback loops, capping the score at 2.	2 / 3
Progressive Disclosure	A real one-level-deep reference (references/geo_reference.md) is clearly signaled with a dedicated section, but the bulk of detailed material (E-utilities API, analysis pipelines, meta-analysis) remains inline in SKILL.md rather than being split out, so organization is only partially achieved.	2 / 3
	Total	9 / 12 Passed

Description

82%

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, well-triggered, and distinctive, but it omits an explicit 'Use when...' clause, so it does not fully answer when Claude should invoke the skill. Adding an explicit trigger phrase would raise completeness to a top score.

Suggestions

Append an explicit trigger clause, e.g. "Use when searching for gene expression datasets, retrieving GEO accessions (GSE/GSM/GPL), or downloading SOFT/Matrix files for transcriptomics analysis."

Keep the natural user-facing terms (RNA-seq, microarray, gene expression) prominently near the start to strengthen trigger matching.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("Search/download microarray and RNA-seq datasets", "retrieve SOFT/Matrix files") rather than vague language.	3 / 3
Completeness	Clearly states what the skill does but lacks an explicit "Use when..." trigger clause; the trailing "for transcriptomics and expression analysis" only implies when, so completeness is capped at 2 per the guidelines.	2 / 3
Trigger Term Quality	Includes natural terms users would say (gene expression, RNA-seq, microarray, transcriptomics) alongside the GEO domain name.	3 / 3
Distinctiveness Conflict Risk	Scoped specifically to NCBI GEO gene-expression data with distinct accessions (GSE/GSM/GPL), making conflict with other skills unlikely.	3 / 3
	Total	11 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (815 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/databases/geo-database/SKILL.md
Commit: 52845c3

Reviewed: about 10 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.