refine-model

refine-model is an Exploratory analysis & notebooks skill for AI agents, published by gregmiller00 in the LVTShift repository on GitHub. Skillspace rates refine-model D (68/100) and it passed the safety scan; the rating is based on static analysis only.

Re-runs an existing LVTShift city model with changed parameters — a different split ratio (e.g. 2:1 instead of 4:1), a switch between split-rate and building abatement, a different exemption treatment (which classes are exempt, full vs. partial relief, adding/removing dollar relief or caps), or an expanded levy scope (e.g. add the secondary/bond levy or go full-stack). Use when the user says "refine the model for [city]", "refine-model [city]", "re-run [city] as 2:1", "change [city] to a building abatement", "model [city] with the county levy included", "exempt [X] in [city] instead", or otherwise asks to change one or more modeling choices for a city that is already modeled. Makes the minimal edit to cities/<city>/model.ipynb, re-executes, re-validates, re-runs cross_city, and reports a before/after diff.

Grade

D

Quality

68 / 100

Safety

Passed

GitHub stars

29

Unproven: rated by static analysis only, not yet compared head-to-head.

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.