This paper introduces a refined general definition of a skeleton that is ba
sed on a penalized-distance function and cannot create any of the degenerat
e cases of the earlier CEASAR and TEASAR algorithms. Additionally, we provi
de an algorithm that finds the skeleton accurately and rapidly. Our solutio
n is fully automatic, which frees the user from having to engage in manual
data preprocessing. We present the accurate skeletons computed on a number
of test datasets. The algorithm is very efficient as demonstrated by the ru
nning times which were all below seven minutes.