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

70%

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%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 body is highly actionable with comprehensive executable examples and clear workflow sequences, but it is padded with redundant query examples and lacks validation feedback loops for its batch/database operations. Progressive disclosure is partially undermined by inlining API reference detail that the dedicated reference file already covers.

Suggestions

De-duplicate the variant-associations query: show it once and reference that pattern elsewhere instead of repeating near-identical code in sections 3, 4, Workflow 2, and the integration example.

Add an explicit validation/retry feedback loop for batch and paginated calls (e.g., on non-200 or malformed JSON: inspect the error, back off, and retry before abandoning) to lift workflow clarity above the batch cap.

Move the full endpoint catalogue and response-field tables into references/api_reference.md, keeping only one or two canonical examples inline in SKILL.md, to improve the progressive-disclosure split.

Dimension	Reasoning	Score
Conciseness	Largely domain-specific and useful, but noticeably redundant: the variant-associations query is repeated across sections 3, Example 2, Workflow 2, and the Python Integration Example, and the 10-item 'When to Use' list duplicates the description — content that could be tightened.	3 / 5
Actionability	Fully executable, copy-paste-ready Python covering the common cases with real base URLs, endpoints, parameters, projection/pagination handling, and response-field extraction; the paginated query_gwas_catalog() function is complete.	5 / 5
Workflow Clarity	Five clearly sequenced numbered workflows exist, but for a skill involving batch extraction and database-style operations there are no validate→fix→retry feedback loops; the Python example merely breaks on a non-200 status, so the batch/database cap holds at 3.	3 / 5
Progressive Disclosure	The references/api_reference.md file is real and clearly signaled with usage guidance, but substantial API detail (endpoint list, response fields, query examples) is inlined in the body and overlaps the reference file, so content that could live separately remains inline.	3 / 5
	Total	14 / 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.

The description is specific, action-oriented, and occupies a clear niche with low conflict risk, but it lacks an explicit 'Use when...' trigger clause, capping completeness. Trigger terms are strong but could add a few synonyms.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when querying GWAS Catalog for SNP-trait associations, looking up variants by rs ID, or retrieving summary statistics for genetic epidemiology or polygenic risk scores') to lift completeness.

Include a couple of natural synonyms such as 'variant', 'trait', and 'association' alongside 'SNP' to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Query NHGRI-EBI GWAS Catalog for SNP-trait associations', 'Search variants by rs ID, disease/trait, gene', 'retrieve p-values and summary statistics' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	The 'what' is explicit and concrete, but there is no 'Use when...' clause; the closing 'for genetic epidemiology and polygenic risk scores' only weakly implies when, so per the guideline a missing explicit trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Strong domain keywords a user would naturally say ('SNP-trait associations', 'rs ID', 'p-values', 'summary statistics', 'polygenic risk scores', 'GWAS'), but a few natural synonyms (e.g. 'variant', 'trait', 'association' standalone) are absent.	4 / 5
Distinctiveness Conflict Risk	A highly specialized niche (NHGRI-EBI GWAS Catalog) with distinct triggers (SNP, rs ID, GWAS, polygenic risk scores) means minimal overlap with other skills.	5 / 5
	Total	17 / 20 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: 3a6c3a9

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.