CtrlK
BlogDocsLog inGet started
Tessl Logo

ukb-topmed-phewas-skill

Fetch compact UKB-TOPMed 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 UKB-TOPMed association results for one variant

76

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 tight, fully actionable single-purpose skill body: executable command, concrete input/output contracts verified against the bundled script, and explicit feedback and failure handling. The only flaw is a small amount of repeated max_results guidance across two sections.

DimensionReasoningScore

Conciseness

The body is lean and operational with no concept explanations, but the max_results guidance appears twice ("start with `max_results=10` and only increase it if the first slice is insufficient" and "Increase `max_results` gradually instead of asking for large association dumps in one call"), a minor redundancy that could be trimmed. Fits anchor 4 rather than the every-token-earns-its-place anchor 5.

4 / 5

Actionability

Fully executable guidance: a copy-paste-ready invocation (`echo '{"grch38":"10:112998590-C-T","max_results":10}' | python scripts/ukb_topmed_phewas.py`), four concrete input patterns covering the common cases, an enumerated output field list, and a defined failure format — all consistent with the actual script in the bundle. Matches anchor 5.

5 / 5

Workflow Clarity

A simple, single-purpose lookup skill under 50 lines where the action is unambiguous, so the simple-skill exception applies. Feedback loops are present (increase max_results when truncated, re-run in long conversations) and the failure path is defined via `ok=false` with `error.code`/`error.message`; the operation is read-only so no destructive/batch cap applies.

5 / 5

Progressive Disclosure

Under 50 lines with well-organized sections and no need for external references, which the body states explicitly ("No additional runtime references are required; keep the import package limited to this file and `scripts/ukb_topmed_phewas.py`"). The referenced script path exists in the bundle, so the structure matches the simple-skill anchor 5.

5 / 5

Total

19

/

20

Passed

Description

95%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 strong description: concrete, third-person, with an explicit 'Use when' trigger and comprehensive domain-specific keywords. Its only gap is that the enumerated actions are slightly short of fully comprehensive coverage.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ("fetch compact UKB-TOPMed PheWAS summaries", "accepting rsID, GRCh37, or GRCh38 input", "resolving to the required GRCh38 query"), but coverage is not fully comprehensive — what the summaries contain is only implied via the trigger clause. Fits anchor 4 (several specific actions, minor gaps) rather than 5.

4 / 5

Completeness

Explicitly answers both questions: the first sentence states what the skill does (fetch summaries, accept three input forms, resolve to GRCh38), and "Use when a user wants concise UKB-TOPMed association results for one variant" is a concrete explicit when-clause. Matches the anchor-5 example structure; not 4 because the when-clause is explicit rather than vague.

5 / 5

Trigger Term Quality

Covers the natural vocabulary a user would say for this task — "UKB-TOPMed", "PheWAS", "rsID", "GRCh37", "GRCh38", "variant", "association results" — with both "summaries" and "results" phrasings. No common synonym is obviously missing, matching the comprehensive-coverage anchor.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (single-variant UKB-TOPMed PheWAS lookups) with distinctive trigger terms (UKB-TOPMed, PheWAS, rsID, GRCh37/38); minimal overlap with any other plausible skill. Matches the clear-niche anchor.

5 / 5

Total

19

/

20

Passed

Validation

100%

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
Reviewed

Table of Contents

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.