gget

Fast CLI/Python queries to 20+ bioinformatics databases. Use for quick lookups: gene info, BLAST/BLAT, viral sequence downloads, AlphaFold structures, enrichment analysis, OpenTargets, COSMIC, CELLxGENE, and 8cube mouse specificity/expression data. Best for interactive exploration and simple queries. For batch processing or advanced BLAST use biopython; for multi-database Python workflows use bioservices.

Quality

80%

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

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.

A well-organized, actionable overview that points cleanly to one-level-deep references and includes version-pinning guidance. Weakest on workflow clarity, since batch/destructive operations lack an inline validate-fix-retry sequence and the scripts bundle is not surfaced.

Suggestions

Add one inline worked workflow with an explicit validate/recovery checkpoint (e.g., for gget virus downloads: run -> check command_summary.txt -> resume with --baseline/--merge-results on partial failure) so batch operations have a feedback loop in SKILL.md itself.

Make the Resources section reconcile with the body: list common_workflows.md and module_catalog.md there too, and add a scripts/ subsection referencing batch_sequence_analysis.py, enrichment_pipeline.py, and gene_analysis.py so the bundle is discoverable.

Tighten the Overview and Quick Start by removing generic statements like 'Most gget modules work both as command-line tools and as Python functions' that restate what the examples already show.

Dimension	Reasoning	Score
Conciseness	Mostly efficient body focused on gget-specific specifics (install commands, flag tables, best-practice bullets) with only minor over-explanation, e.g. 'Most gget modules work both as command-line tools and as Python functions' could be trimmed.	4 / 5
Actionability	Provides concrete executable commands and flags (uv pip install, --limit, --threads, -mr 20, -r, plot=True, --baseline, --merge-results) with minor gaps since per-module examples live in references rather than inline.	4 / 5
Workflow Clarity	Worked pipelines are delegated to references and the body offers scattered best-practice bullets rather than a sequenced validate-fix-retry flow; for batch operations like viral downloads only partial recovery guidance exists, so the batch-validation cap applies.	3 / 5
Progressive Disclosure	Good one-level-deep structure with real, clearly signaled links to module_catalog.md, module_reference.md, common_workflows.md, and workflows.md; minor gaps as the Resources section omits common_workflows.md and module_catalog.md and never surfaces the scripts/ bundle.	4 / 5
	Total	15 / 20 Passed

Description

92%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.

A strong, specific description with concrete capability enumeration, clear trigger phrasing, and helpful boundary guidance that steers away competing tools. Voice is appropriately third person throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'gene info, BLAST/BLAT, viral sequence downloads, AlphaFold structures, enrichment analysis, OpenTargets, COSMIC, CELLxGENE, and 8cube mouse specificity/expression data' — giving comprehensive coverage rather than vague abstraction.	5 / 5
Completeness	Explicitly answers both 'what' (queries to 20+ bioinformatics databases with enumerated capabilities) and 'when' ('Use for quick lookups', 'Best for interactive exploration and simple queries'), plus negative triggers steering to biopython/bioservices.	5 / 5
Trigger Term Quality	Strong natural keyword coverage (gene info, BLAST, AlphaFold structures, enrichment analysis, COSMIC, CELLxGENE) that bioinformatics users would actually say, though a few common synonyms (e.g., 'protein structure', 'cancer genomics') are absent.	4 / 5
Distinctiveness Conflict Risk	Clear niche (gget bioinformatics CLI) with distinct triggers and explicit boundary guidance ('For batch processing or advanced BLAST use biopython; for multi-database Python workflows use bioservices') minimizing conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/gget/SKILL.md
Commit: b2a92ba

Reviewed: 3 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.