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

71%

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

68%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.

The body is highly actionable with comprehensive executable examples and a well-signaled reference file, but it is verbose for a context-window skill and lacks explicit validation checkpoints in its batch/download workflows.

Suggestions

Trim the overview and 'Key Concepts' sections that re-explain GEO/SOFT/MIAME concepts Claude already knows, and move the full differential-expression and batch-processing code into the reference file.

Add explicit validation checkpoints to the batch-download and batch-processing workflows (e.g. verify downloaded files exist and are non-empty, confirm parsed expression matrices have expected shape before analysis).

Restructure the capability catalog as a short 'how to do common tasks' sequenced workflow so the primary path is clear rather than presented as parallel sections.

Dimension	Reasoning	Score
Conciseness	The ~800-line body is mostly concrete code but includes unnecessary explanation Claude already knows (the GEO overview, 'Key Concepts' defining SOFT/MINiML/MIAME/Series Matrix, and generic 'Common Use Cases'); could be tightened, so it sits at the midpoint rather than 4.	3 / 5
Actionability	Provides extensive copy-paste-ready, executable code across GEOparse, Entrez E-utilities, FTP downloads, and differential expression analysis covering the common cases; fully actionable.	5 / 5
Workflow Clarity	Content is organized as a capability catalog (sections 1-7) rather than a sequenced workflow, and the batch-processing and download operations lack explicit validation checkpoints, which caps workflow clarity at 3 per the batch-operation rule.	3 / 5
Progressive Disclosure	A single one-level-deep reference (references/geo_reference.md) is clearly signaled with a description of what it covers; structure is good, though a fair amount of inline content (full analysis/batch code) could live in the reference, keeping it just below 5.	4 / 5
	Total	15 / 20 Passed

Description

75%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.

The description is specific and distinctive with strong concrete actions and trigger keywords, but it lacks an explicit 'Use when...' clause, which caps completeness at 3.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when searching for or downloading gene expression datasets, querying GSE/GSM/GPL accessions, or retrieving SOFT/Matrix files from GEO.'

Include a few more natural trigger phrases and file extensions a user might actually say (e.g. 'GEO database', '.soft', '.matrix', 'series matrix').

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'Search/download microarray and RNA-seq datasets (GSE, GSM, GPL), retrieve SOFT/Matrix files' — with comprehensive coverage of the skill's operations; not below 5 because coverage is broad and concrete, not above because 5 is the top anchor.	5 / 5
Completeness	Has a clear 'what' but no explicit 'Use when...' trigger clause; 'for transcriptomics and expression analysis' only weakly implies when, so per the missing-trigger-guidance cap completeness cannot exceed 3.	3 / 5
Trigger Term Quality	Good keyword coverage including synonyms and accession types ('gene expression', 'genomics data', 'microarray', 'RNA-seq', 'SOFT/Matrix', 'transcriptomics', 'GSE/GSM/GPL'); a few natural terms a user might say (e.g. 'GEO database', '.soft' file extensions) are missing, so it is not a 5.	4 / 5
Distinctiveness Conflict Risk	Clear niche with distinct triggers — 'NCBI GEO', 'GSE/GSM/GPL' accessions, 'SOFT/Matrix files' — making conflict with other skills minimal.	5 / 5
	Total	17 / 20 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: 3a6c3a9

Reviewed: 1 day 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.