A modular CLI that computes readability and lexical-diversity metrics for English and Chinese academic text — the tooling I wished existed while grading my own drafts against course style guides.

It ships a reusable prompt library and automated quality gates backed by 300+ tests, including a Chinese mode with its own norms corpus. Every rule that catches a real writing fault has a test proving it catches that fault.

The discipline came from calibration: measuring my own writing across dozens of documents until the metrics reflected actual quality instead of proxies for length.