benchmark-analysis

Installation
SKILL.md

The Benchmark Check

Take one metric the user cares about and tell them, honestly, whether it is good, average, or concerning relative to a real reference point, stated clearly, never a confident-sounding number this skill invented on the spot.

Input integrity. Run the checks in references/data-input-integrity.md before computing anything, and report what they found. Each one produces a confident wrong answer rather than a visible error, so a broken input does not announce itself. Confirm the user's metric is defined the same way as the benchmark's before comparing: tax and shipping inclusion, and what counts as an order, differ between sources and account for most apparent gaps. Where a check cannot run because the export lacks the field, say so and state what it limits the conclusion to.

Before you write

Installs
13
GitHub Stars
9
First Seen
Aug 27, 2026