finngen-phewas-skill

Fetch compact FinnGen PheWAS summaries for single variants by accepting rsID, GRCh37, or GRCh38 input and resolving to the required GRCh38 query. Use when a user wants concise FinnGen association results for one variant

Quality

93%

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

86%Weight 40%Scale 1-3

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

A tight, actionable SKILL.md body with an executable command, exact I/O field contracts, and clean section organization suited to a single-purpose skill. It could be tightened by removing the overlap between Operating rules and Execution behavior and by adding an explicit re-run/checkpoint note for the failure path.

Suggestions

De-duplicate the max_results guidance between 'Operating rules' and 'Execution behavior' so the advice lives in one place and saves tokens.

Add an explicit validation checkpoint for the failure path (e.g., on ok=false, inspect error.code, re-run with adjusted input or report the error to the user) rather than only describing the error shape.

Consider folding the 'Execution behavior' bullets into 'Output' or 'Operating rules' to reduce section count and redundancy in a sub-50-line skill.

Dimension	Reasoning	Score
Conciseness	Lean with no concept-explaining fluff and every section earns its place, but the 'Operating rules' and 'Execution behavior' sections overlap on max_results advice (start with 10, increase gradually). Mostly efficient with minor redundancy, so just below the score-3 'every token earns its place' anchor and above score 2.	2.5 / 3
Actionability	Provides a fully executable command ('echo '{...}' \| python scripts/finngen_phewas.py'), concrete JSON input patterns, and exact output/input field lists — copy-paste ready. Matches the score-3 anchor; not score 2 because the guidance is complete and executable rather than pseudocode.	3 / 3
Workflow Clarity	The single-action flow is unambiguous and success/failure outputs plus truncation status are clearly surfaced, but there is no explicit validation/verification checkpoint or re-run-on-error loop beyond returning error.code. Above the score-2 'steps listed but validation gaps' anchor due to clear sequencing and failure surfacing, but below score 3 because a checkpoint for the failure path is only implicit.	2.5 / 3
Progressive Disclosure	Under ~40 lines, well-organized into clear sections (Operating rules, Execution behavior, Input, Output, Execution, References), with the body's reference to scripts/finngen_phewas.py verified as a real bundle file and no nested references. Per the simple-skills scoring note, this satisfies the score-3 anchor; not score 2 because organization is clean with no inline bloat.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 that states concrete capabilities, covers the natural variant-input terms, and includes an explicit activation trigger. It cleanly answers both what the skill does and when to use it, with low conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Fetch compact FinnGen PheWAS summaries for single variants', 'accepting rsID, GRCh37, or GRCh38 input', and 'resolving to the required GRCh38 query'. Matches the score-3 anchor of multiple specific concrete actions; not score 2 because the actions are comprehensive rather than partial.	3 / 3
Completeness	Explicitly answers both what ('Fetch...summaries...resolving to...GRCh38 query') and when ('Use when a user wants concise FinnGen association results for one variant'). Matches the score-3 anchor with an explicit 'Use when' trigger; not score 2 because the when-clause is explicit, not implied.	3 / 3
Trigger Term Quality	Natural domain terms a user would say are present — 'FinnGen PheWAS', 'rsID', 'GRCh37, or GRCh38', and 'FinnGen association results'. Good coverage of the common input forms; not score 2 because it captures the realistic user phrasings rather than only jargon.	3 / 3
Distinctiveness Conflict Risk	A clear, narrow niche (single-variant FinnGen PheWAS) with distinct triggers unlikely to activate for unrelated skills. Matches the score-3 anchor of a clear niche with distinct triggers; not score 2 because it would not realistically overlap with other skills.	3 / 3
	Total	12 / 12 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: openai/plugins
Path: plugins/life-science-research/skills/finngen-phewas-skill/SKILL.md
Commit: 11c74d6

Reviewed: 17 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.