gwas-database

Query NHGRI-EBI GWAS Catalog for SNP-trait associations. Search variants by rs ID, disease/trait, gene, retrieve p-values and summary statistics, for genetic epidemiology and polygenic risk scores.

Quality

73%

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/gwas-database/SKILL.md

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable with executable, copy-paste-ready code, but undermined by verbosity (re-explaining known concepts) and weak validation checkpoints in its workflows, plus underuse of the bundled reference file. Trimming the overview and moving API/field detail into api_reference.md would lift conciseness and progressive disclosure.

Suggestions

Move the per-endpoint examples, response-field reference, and pagination detail into references/api_reference.md, keeping SKILL.md to a concise overview plus one or two quick-start examples.

Add explicit validation/checkpoint steps to the workflows (e.g., 'if response.status_code != 200: retry with backoff, then stop' and 'verify the DataFrame is non-empty before analyzing') to satisfy the feedback-loop requirement for batch/data operations.

Cut the Overview paragraph and the external-database lists that restate what Claude already knows about GWAS Catalog, Ensembl, dbSNP, and gnomAD.

Dimension	Reasoning	Score
Conciseness	The body is efficient in its code but padded with concepts Claude already knows (the Overview defining the GWAS Catalog, what summary statistics are, and lists of Ensembl/dbSNP/gnomAD), so it is mostly efficient with some unnecessary explanation that could be tightened — the level-2 anchor.	2 / 3
Actionability	Provides multiple complete, executable Python examples with real base URLs, endpoints, params, pagination, and a pandas-returning helper plus a wget command — copy-paste ready, matching the score-3 anchor rather than pseudocode at level 2.	3 / 3
Workflow Clarity	Five workflows give clear sequences, but validation checkpoints and error/retry feedback loops are missing or implicit across the API and batch data-extraction workflows; per the guidelines, missing validation in batch/data operations caps this at 2.	2 / 3
Progressive Disclosure	A one-level-deep reference (references/api_reference.md) is signaled and exists, but the detailed endpoint specs, examples, and field reference that should live in it are largely inline in a ~590-line SKILL.md, fitting the level-2 'content that should be separate is inline' anchor.	2 / 3
	Total	9 / 12 Passed

Description

82%

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 good natural trigger terms and a clear niche, weakened only by the absence of an explicit 'Use when...' trigger clause. Adding a when-to-use sentence would raise completeness to full marks.

Suggestions

Append a 'Use when...' clause naming natural trigger scenarios (e.g., 'Use when the user asks about GWAS hits, SNP-trait associations, rs ID lookups, or polygenic risk scores') to satisfy the completeness 'when' requirement.

Add common user phrasings like 'GWAS', 'genome-wide association', or 'genetic variants for a disease' to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'Query NHGRI-EBI GWAS Catalog', 'Search variants by rs ID, disease/trait, gene', 'retrieve p-values and summary statistics' — matching the score-3 anchor rather than the domain-plus-some-actions level 2.	3 / 3
Completeness	Explicitly answers 'what' with concrete actions but lacks any 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	Covers natural terms a genetics user would actually say — 'GWAS Catalog', 'SNP-trait associations', 'rs ID', 'disease/trait', 'p-values', 'summary statistics', 'polygenic risk scores' — giving good coverage across variations rather than the partial level-2 set.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (NHGRI-EBI GWAS Catalog, SNP-trait associations, polygenic risk scores) with distinct triggers unlikely to fire for unrelated skills, matching the score-3 anchor.	3 / 3
	Total	11 / 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 (608 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/gwas-database/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.