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

65%

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

Quality

Content

61%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 skill is highly actionable with broad executable examples and a genuine one-level-deep reference, but it is verbose and its batch/FTP workflows lack the validation checkpoints the rubric requires. Tightening duplicated code and adding explicit validation steps would raise both conciseness and workflow clarity.

Suggestions

Add explicit validation/verification checkpoints to batch and FTP workflows (e.g. verify downloaded files exist and are non-empty before processing; confirm rate-limit sleeps succeed).

Trim duplicated install snippets and repeated GEOparse.get_GEO boilerplate, and move the full DE-analysis/clustering/meta-analysis code into references/geo_reference.md.

Cut the 'Key Concepts' explanations of MIAME/SOFT/MINiML to one-line definitions, since Claude already knows these formats.

Dimension	Reasoning	Score
Conciseness	The ~800-line body is mostly actionable code rather than prose padding, but it is noticeably verbose: repeated GEOparse.get_GEO calls, duplicated install snippets, and 'Key Concepts' blocks explaining MIAME/SOFT/MINiML that Claude largely already knows.	3 / 5
Actionability	Extensive copy-paste-ready Python covers search, retrieval, FTP download, QC, differential expression, clustering, and batch processing, with only minor gaps (placeholder GSM IDs, unverified pivot_samples/VALUE assumptions).	4 / 5
Workflow Clarity	Capabilities are loosely sequenced but lack explicit validation checkpoints, and batch/bulk operations (batch_download_geo, batch_fetch_geo_metadata, FTP bulk wget -r) run without validate-then-proceed feedback loops, which caps workflow_clarity at 3 per the rubric.	3 / 5
Progressive Disclosure	Clear overview with a real, well-signaled one-level-deep reference (references/geo_reference.md) whose stated topics match the file's actual sections, though large analysis code blocks (DE analysis, clustering, meta-analysis) are inlined rather than split into the reference.	4 / 5
	Total	14 / 20 Passed

Description

70%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 trigger-term coverage, but it omits an explicit 'Use when...' trigger clause, leaving the activation conditions only weakly implied. Adding a concrete 'Use when...' sentence would lift completeness and distinctiveness further.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when searching for gene expression datasets, downloading GEO data, or analyzing transcriptomics datasets.'

Include a couple of natural user synonyms (e.g. 'GEO datasets', 'omics data', '.soft files') to broaden trigger-term coverage.

Mention downstream analysis actions (QC, normalization, differential expression) so the capability list matches what the body actually covers.

Dimension	Reasoning	Score
Specificity	Names the domain plus several concrete actions ('Search/download microarray and RNA-seq datasets', 'retrieve SOFT/Matrix files') with explicit accession types (GSE, GSM, GPL), though coverage of analysis/QC tasks is absent.	4 / 5
Completeness	Has a clear 'what' (access/search/download/retrieve) but only a weakly implied 'when' via the trailing 'for transcriptomics and expression analysis'; no explicit 'Use when...' trigger clause, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Includes natural terms like 'gene expression', 'microarray', 'RNA-seq', 'transcriptomics', 'expression analysis', and accession codes, but misses common synonyms a user might say such as 'GEO datasets' or 'omics data'.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (NCBI GEO gene-expression data) with distinct accession codes (GSE/GSM/GPL) and SOFT/Matrix formats, giving minimal overlap risk with other skills.	5 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (813 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning

	Total	14 / 16 Passed

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/geo-database/SKILL.md
Commit: d5ae560

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.