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.

1.02x

Quality

66%

Does it follow best practices?

Impact

80%

1.02x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/geo-database/SKILL.md

Quality

Discovery

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.

This is a strong, domain-specific skill description with excellent specificity and trigger term coverage for bioinformatics users. The main weakness is the lack of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. The technical terminology is appropriate for the target audience.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about gene expression data, GEO datasets, downloading transcriptomics data, or mentions GSE/GSM/GPL accession numbers.'

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'Search/download microarray and RNA-seq datasets', 'retrieve SOFT/Matrix files', with specific identifiers (GSE, GSM, GPL) and clear use cases (transcriptomics, expression analysis).	3 / 3
Completeness	Clearly answers 'what' (access GEO, search/download datasets, retrieve files) but lacks an explicit 'Use when...' clause. The 'when' is only implied through the listed capabilities rather than explicitly stated.	2 / 3
Trigger Term Quality	Excellent coverage of natural terms users would say: 'NCBI GEO', 'gene expression', 'genomics', 'microarray', 'RNA-seq', 'GSE', 'GSM', 'GPL', 'SOFT', 'Matrix files', 'transcriptomics'. These are domain-specific but exactly what bioinformatics users would search for.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with specific domain (NCBI GEO), specific data types (GSE, GSM, GPL, SOFT/Matrix), and specific analysis types (transcriptomics, expression analysis). Unlikely to conflict with other skills due to specialized bioinformatics focus.	3 / 3
	Total	11 / 12 Passed

Implementation

50%

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

This skill provides highly actionable, executable code for GEO database access but suffers from severe verbosity. It explains concepts Claude already knows (database organization, what expression data is) and includes extensive inline content that should be in reference files. The lack of validation checkpoints in workflows involving batch downloads is a notable gap.

Suggestions

Reduce the 'Understanding GEO Data Organization' section to a brief table of accession types (GSE, GSM, GPL, GDS) without explanatory prose - Claude knows what databases and samples are

Move the detailed analysis code (QC, differential expression, clustering) to a separate ANALYSIS.md reference file, keeping only a brief example in the main skill

Add explicit validation steps to batch processing workflows: verify download success, check file integrity, validate parsed data before proceeding

Remove the 'Overview' and 'When to Use This Skill' sections entirely - these add no actionable value and waste tokens

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at 600+ lines, explaining concepts Claude already knows (what GEO is, what PDFs are equivalent explanations about data organization), includes extensive background information, and repeats similar patterns multiple times. The 'Understanding GEO Data Organization' section explains basic database concepts unnecessarily.	1 / 3
Actionability	The skill provides fully executable, copy-paste ready Python code throughout. Examples are complete with imports, function definitions, and realistic usage patterns. Code covers searching, downloading, parsing, and analyzing GEO data comprehensively.	3 / 3
Workflow Clarity	While multi-step processes are present (search -> fetch -> analyze), there are no explicit validation checkpoints or error recovery feedback loops. The batch processing section lacks verification steps to confirm downloads succeeded before proceeding to analysis.	2 / 3
Progressive Disclosure	The skill mentions 'references/geo_reference.md' for detailed documentation, which is good, but the main file itself is monolithic with extensive inline content that could be split. The 600+ lines of detailed code examples and analysis patterns should be in separate reference files.	2 / 3
	Total	8 / 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 — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (814 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning

	Total	9 / 11 Passed

Repository: K-Dense-AI/claude-scientific-skills
Commit: 71add64

Reviewed: 7 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.