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

62%

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 ./skills/bio/geo-database/SKILL.md

Quality

Content

42%

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

Highly actionable with abundant executable code, but the skill is far too verbose, explains concepts Claude already knows, lacks validation checkpoints on batch operations, and references a non-existent bundle file. It needs aggressive trimming and a real references/ split to earn top scores.

Suggestions

Trim concept glossaries Claude already knows (SOFT/MINiML/MIAME definitions, accession-type counts) and de-duplicate repeated GEOparse import/get_GEO boilerplate across sections.

Add explicit validation checkpoints to batch and FTP workflows (e.g. verify downloaded file integrity, confirm expected record counts before proceeding, retry-on-error feedback loops).

Either create the referenced references/geo_reference.md and move the deep API/format details there, or remove the dangling reference; split the monolithic body so SKILL.md stays a lean overview.

Dimension	Reasoning	Score
Conciseness	At ~810 lines the body is verbose and padded: it glosses concepts Claude already knows (SOFT, MINiML, Series Matrix, MIAME compliance, expression value types), repeats GEOparse imports and get_GEO calls across sections, and includes a self-promotional K-Dense Web section, matching the verbose/padded anchor.	1 / 3
Actionability	Provides fully executable, copy-paste-ready Python (GEOparse, Biopython Entrez, ftplib), concrete shell commands (uv pip install, wget), and specific worked examples throughout.	3 / 3
Workflow Clarity	Capabilities are numbered and organized with error handling in batch routines, but batch downloads, FTP retrieval, and batch E-utilities lack explicit validation/verification checkpoints, capping workflow clarity at 2 per the batch-operations guideline.	2 / 3
Progressive Disclosure	The body is a monolithic wall of text with everything inline, and the one signaled reference — 'references/geo_reference.md' — points to a references/ directory that does not exist, so the structure is both monolithic and broken.	1 / 3
	Total	7 / 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.

A specific, third-person description with strong trigger terms and a clear niche, but it lacks an explicit 'Use when...' clause so the use-trigger guidance is only implied. Adding an explicit trigger clause would raise completeness to the top level.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when searching for or downloading GEO gene-expression datasets, or when the user mentions GSE/GSM/GPL accessions, RNA-seq, or microarray data.'

Consider adding common natural phrasings users might say such as 'gene expression datasets' or 'GEO accessions' to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Access NCBI GEO', 'Search/download microarray and RNA-seq datasets (GSE, GSM, GPL)', 'retrieve SOFT/Matrix files' — matching the multiple-specific-actions anchor.	3 / 3
Completeness	The 'what' is explicit, but 'when' is only implied via the purpose clause 'for transcriptomics and expression analysis' with no 'Use when...' trigger guidance, so completeness is capped at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	Good coverage of natural domain terms a researcher would say — 'gene expression', 'RNA-seq', 'microarray', 'GSE', 'GSM', 'GPL', 'transcriptomics' — rather than internal jargon.	3 / 3
Distinctiveness Conflict Risk	Clear niche (NCBI GEO gene-expression data) with distinct identifiers (GSE/GSM/GPL, SOFT/Matrix) that are unlikely to trigger the wrong skill.	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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/bio/geo-database/SKILL.md
Commit: df37802

Reviewed: about 2 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.