sketchup-code: Skill for Cursor

Refactor with Validation

Safe workflow for refactoring SketchUp Ruby code: capture baseline → refactor → compare → clean up.

Audit helper (reused in Steps 1 & 3)

Important: Audit only the plugin’s dimensions (same selection + sublayer as clear/run). Do not use model.entities.grep(Sketchup::DimensionLinear) — that includes every linear dimension in the model (other plugins, manual dims) and produces wrong counts (e.g. 158 instead of 49).

def fmt_pt(pt)
  "(#{(pt.x*25.4).round(3)}, #{(pt.y*25.4).round(3)}, #{(pt.z*25.4).round(3)})mm"
end
def fmt_vec(v)
  "(#{v.x.round(6)}, #{v.y.round(6)}, #{v.z.round(6)})"
end

# dims_array: only plugin dimensions (from target_entities + sublayer), not model.entities
def audit_dims(dims_array)
  lines = []
  dims_array.each_with_index do |d, i|
    p1 = d.start[1]
    p2 = d.send(:end)[1]
    ov = d.offset_vector
    dir = Geom::Vector3d.new(p2.x - p1.x, p2.y - p1.y, p2.z - p1.z)
    normal = dir.cross(ov)
    normal.normalize! rescue nil
    lines << [
      "dim #{i}: layer='#{d.layer.name}' text='#{d.text}' 3d_dist=#{(p1.distance(p2)*25.4).round(1)}mm",
      "  p1=#{fmt_pt(p1)}  p2=#{fmt_pt(p2)}",
      "  offset=#{fmt_vec(ov)}",
      "  normal=#{fmt_vec(normal)}"
    ].join("\n")
  end
  lines.join("\n")
end

# Returns the array of DimensionLinear that belong to the plugin (current selection, maten sublayer).
def plugin_dims(model)
  inst = Timmerman::SkeletonDimensions.send(:selected_component_instance, model.selection)
  return [] unless inst
  sublayer = Timmerman::SkeletonDimensions.send(:find_or_create_maten_sublayer, model, inst)
  target = Timmerman::SkeletonDimensions.send(:entities_containing_instance, inst)
  target.grep(Sketchup::DimensionLinear).select { |d| d.layer == sublayer }
end

Per dimension this captures:

• text — displayed measurement (catches wrong values)
• p1 / p2 — exact 3D world-space anchor coordinates in mm (catches wrong corner/beam edge selection)
• 3d_dist — scalar distance as a quick sanity check
• offset — 3D vector positioning the dim line (catches stagger, padding, top-vs-bottom, side-of-beam)
• normal — computed as normalize((p2−p1) × offset); catches orientation flips that wouldn't show in the other fields. DimensionLinear has no built-in normal method, so we derive it.