Stats
Actions
Tags
From baywright
Baywright workflow verb (invoke as /baywright:bw-criticize): run a posterior-predictive model criticism pass — try to break the model with test quantities, check identifiability and prior sensitivity — and record what you found in the Model Ledger. Trigger on: /baywright:bw-criticize, "criticize my model", "run posterior predictive checks", "can my model reproduce the data".
How this skill is triggered — by the user, by Claude, or both
Slash command
/baywright:bw-criticizeThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Run model criticism (see `model-criticism`) and record the findings.
Run model criticism (see model-criticism) and record the findings.
criticism stage to done with the test
quantities used and the verdict; log any misfit either as addressed or as a stated limitation.model-formulation to expand the
model — say so plainly and re-enter the sequence.Drive your live session; consult the current documentation for your tool's posterior-predictive sampling and check helpers.
npx claudepluginhub 3shn/baywrightGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.