Conciseness

Lean and token-efficient: a brief intro, a minimal executable snippet, a dense dataset table, and short guidance bullets, with no padding or explanation of concepts Claude already knows.

Actionability

Provides copy-paste-ready executable code (`cp.load_data("did")`) plus a complete table of every dataset key with use-case and description, covering all common cases.

Workflow Clarity

A simple single-purpose skill whose single action (load a dataset by key) is unambiguous; no destructive or batch operation is present, so the simple-skill exception applies.

Progressive Disclosure

Under 50 lines, self-contained with well-organized sections (Usage, Available Datasets, Guidance) and one-level references to sibling skills; no nested bundle references to manage.

Specificity

Names the domain (CausalPy example datasets) and several concrete use contexts ('demos, tutorials, tests, and quick causal-analysis prototypes'), though the core action is essentially a single verb ('Load').

Completeness

Explicitly states what it does ('Load built-in CausalPy example datasets...') and when to use it ('Use when the user needs sample data or asks which demo datasets are available').

Trigger Term Quality

Includes natural phrases users would say — 'sample data', 'demo datasets', 'which demo datasets are available' — with good but not exhaustive synonym coverage.

Distinctiveness Conflict Risk

Targets a clear niche (CausalPy's built-in datasets) with distinct triggers, making conflict with other skills unlikely.