gget

Fast CLI/Python queries to 20+ bioinformatics databases. Use for quick lookups: gene info, BLAST searches, AlphaFold structures, enrichment analysis. Best for interactive exploration, simple queries. For batch processing or advanced BLAST use biopython; for multi-database Python workflows use bioservices.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

65%

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 executable examples per module, but it is token-heavy: parameter detail duplicated in module_reference.md lives inline, and workflows lack validation checkpoints. Disclosure would improve by leaning on the reference files and surfacing the orphaned scripts.

Suggestions

Move the per-module parameter lists into module_reference.md and replace them in the body with one-line summaries plus a link, reducing duplication and token cost (improves conciseness and progressive_disclosure).

Add validation/feedback checkpoints to the workflows — e.g. after `gget.search`, check that results are non-empty before calling `gget.info(gene_ids[:5])`, and retry/adjust on failure (improves workflow_clarity).

Reference the scripts/ files (batch_sequence_analysis.py, enrichment_pipeline.py, gene_analysis.py) from the relevant workflows or a scripts section so the bundle is discoverable rather than orphaned (improves progressive_disclosure).

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept padding, but the ~600-line inline per-module parameter catalog duplicates module_reference.md; not a 3 because that bulk does not earn its place when a reference file already exists.	2 / 3
Actionability	Every module ships concrete, executable bash and Python snippets (e.g. `gget search -s human gaba gamma-aminobutyric` and `gget.info([...], pdb=True)`) that are copy-paste ready, matching the score-3 anchor.	3 / 3
Workflow Clarity	Six workflows give numbered sequences, but none include validation checkpoints or error-recovery feedback loops (e.g. confirm search returned hits before slicing `ensembl_id`), so it sits at the score-2 anchor rather than 3.	2 / 3
Progressive Disclosure	references/ files are cleanly signaled and one level deep, but the inline per-module parameter tables replicate module_reference.md (the score-2 "200 lines of API reference that could be in a separate file" pattern), and the scripts/ files are never referenced from the body.	2 / 3
	Total	9 / 12 Passed

Description

100%

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, concise description: it states concrete capabilities, gives explicit trigger guidance, and differentiates itself from adjacent skills. Uses third-person voice throughout with no first/second-person phrasing.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — "gene info, BLAST searches, AlphaFold structures, enrichment analysis" — naming both domain and capabilities, matching the score-3 anchor.	3 / 3
Completeness	Explicitly answers both what ("Fast CLI/Python queries to 20+ bioinformatics databases") and when ("Use for quick lookups: ..."), with an explicit "Use for..." trigger clause.	3 / 3
Trigger Term Quality	Uses natural terms a bioinformatics user would actually say ("gene info", "BLAST searches", "AlphaFold structures", "enrichment analysis", "batch processing"); not below 3 because coverage is broad and jargon-free.	3 / 3
Distinctiveness Conflict Risk	Carves a clear niche and explicitly contrasts with biopython (batch/advanced BLAST) and bioservices (multi-database Python workflows), so it is unlikely to trigger for the wrong skill.	3 / 3
	Total	12 / 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 (871 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/biology/gget/SKILL.md
Commit: 52845c3

Reviewed: about 11 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.