Stats
Actions
Tags
From baywright
Baywright workflow verb (invoke as /baywright:bw-next): advance to the next workflow stage, but gate-check the current one first — it refuses to advance past a stage whose evidence isn't recorded. Trigger on: /baywright:bw-next, "next step in the workflow", "advance the model", "what do I do next with baywright".
How this skill is triggered — by the user, by Claude, or both
Slash command
/baywright:bw-nextThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Move the workflow forward one stage, fail-closed.
Move the workflow forward one stage, fail-closed.
baywright-ledger.md. Find the current stage: the first stage not yet done in the
sequence formulation -> priors -> computation -> calibration -> criticism -> comparison ->
reporting.done with empty evidence is not done. If the evidence isn't
there, do not advance — name what's missing and finish it (route to the stage's skill).done with a one-line evidence note, then
route to the next stage's skill: model-formulation, priors-and-prior-predictive,
computation-and-diagnostics, reparameterization (if the sampler is fighting the geometry),
calibration, model-criticism, model-comparison, reporting. For the calibration stage use
/baywright:bw-gate; for criticism use /baywright:bw-criticize.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.