scientific-pkg-gget

gget CLI and Python workflow for quick genomic database queries, sequence lookup, BLAST-style searches, enrichment checks, and reproducible bioinformatics evidence logs. Use when a task needs quick bioinformatics lookup across genomic reference databases with the gget CLI or Python package.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/scientific-pkg-gget/SKILL.md

Quality

Content

82%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 strong, lean single-file skill body: executable CLI and Python examples throughout, a sensible small-query-first workflow with a review checklist, and clean section structure. The only real upside is offloading per-module detail to a references/ file and making workflow checkpoints more explicit.

Suggestions

Move per-module detail (the 'Common Modules' list) into a references/modules.md file and keep one-line summaries inline, shortening SKILL.md.

Make the small-query-first checkpoint an explicit validate step, e.g. 'If the small query errors or returns nothing, check the module docs before retrying'.

Dimension	Reasoning	Score
Conciseness	The body is lean with no explanations of concepts Claude already knows (no 'what is BLAST' padding) and every section carries actionable content, but a few spots ('Before relying on an older environment...', 'Do not assume every module supports...') could be tightened further, matching 'efficient; minor instances of over-explanation'.	4 / 5
Actionability	Fully executable, copy-paste-ready commands cover the common cases: `gget search -s human brca1 dna repair -o brca1-search.json`, `gget info ENSG00000012048 -o brca1-info.json`, `gget seq ENSG00000012048 -o brca1-seq.fa`, `gget blast "MEEPQ..." -l 10`, plus runnable Python (`gget.search(["BRCA1"], species="human")`), matching the anchor for copy-paste ready examples across common cases.	5 / 5
Workflow Clarity	The numbered 'Common workflow' (identify species/assembly -> check docs -> run a small query first -> save with explicit filename -> record metadata) plus the closing 'Review Checklist' give a clear sequence with checkpoints; it stops short of 5 because checkpoints are partly implicit rather than explicit validate-fix-retry loops. The destructive/batch cap does not apply since queries are read-only lookups.	4 / 5
Progressive Disclosure	A single-file, well-sectioned skill (When to Use / Installation / Basic Patterns / Common Modules / Quick Examples / Reproducibility Log / Review Checklist / References) with clearly signaled external links; at ~160 lines the under-50-line exception doesn't apply and per-module details could be offloaded to a reference file, so 'good structure; minor organization gaps' fits.	4 / 5
	Total	17 / 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.

A solid description that names the tool, lists five concrete capabilities, and includes an explicit use-when clause. Its main gaps are missing common trigger synonyms (Ensembl, gene, FASTA) and a when-clause that echoes the what rather than adding distinct trigger phrases.

Suggestions

Add concrete trigger phrases to the when-clause, e.g. 'Use when the user mentions genes, Ensembl IDs, BLAST, fetching sequences or FASTA, or genomic database lookups'.

Include widely-used domain keywords such as 'Ensembl', 'reference genome', and 'gene metadata' so the description surfaces on those queries.

Mention one or two more capabilities from the body (e.g. protein-structure or reference-genome retrieval) to close the coverage gap.

Dimension	Reasoning	Score
Specificity	Lists five concrete actions ('genomic database queries, sequence lookup, BLAST-style searches, enrichment checks, and reproducible bioinformatics evidence logs'), matching the 'several specific actions; minor gaps' anchor rather than 5 because protein-structure, reference-genome download, and ID-metadata lookups are not mentioned.	4 / 5
Completeness	Both a concrete 'what' and an explicit 'Use when a task needs quick bioinformatics lookup...' clause are present; it falls short of 5 because the when-clause largely restates the what instead of adding concrete user-mention trigger phrases.	4 / 5
Trigger Term Quality	Includes natural terms users would say ('BLAST', 'sequence lookup', 'enrichment', 'bioinformatics', 'gget CLI'), but common synonyms like 'Ensembl', 'gene', 'FASTA', or 'reference genome' are missing, which fits 'good keyword coverage; a few natural terms missing'.	4 / 5
Distinctiveness Conflict Risk	The gget-specific niche and tool-specific triggers make it mostly distinct with minimal conflict risk, but the broad 'bioinformatics' phrasing leaves minor overlap with other bioinformatics tool skills.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: skills/scientific-pkg-gget/SKILL.md
Commit: c70874f

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.