Conciseness

At ~37 lines the body is lean and assumes Claude's competence, with no padding or explanation of concepts Claude already knows; every section earns its place.

Actionability

Provides a concrete, copy-paste-ready bash invocation plus three specific JSON input patterns and exact param names (df, ef, sf, q, offset, count), not vague description.

Workflow Clarity

A simple single-task skill with an unambiguous input/stdin/output contract and explicit guidance to page via offset; per the simple-skills note, the single action is clear enough to score 3, and no destructive/batch operation requires validation checkpoints.

Progressive Disclosure

Under 50 lines with well-organized sections and a single referenced script (scripts/ncbi_gene_clinicaltables.py) that exists in the bundle; per the simple-skills note this warrants a 3 without further external references.

Specificity

Names multiple concrete actions — "human gene lookup, pagination, and field selection" — tied to a specific endpoint, matching the multi-action anchor rather than the single-domain score-2 example.

Completeness

Explicitly answers both what ("Submit compact Clinical Tables NCBI Gene requests for ... lookup, pagination, and field selection") and when ("Use when a user wants concise autocomplete-style human gene search results").

Trigger Term Quality

Natural terms a user would say are present ("human gene search results", "autocomplete-style", "NCBI Gene"), giving good coverage rather than just technical jargon.

Distinctiveness Conflict Risk

The Clinical Tables autocomplete niche is distinct from general Entrez Gene records, with trigger language unlikely to fire for unrelated skills.