Skewness is a measure of the tendency for the distribution of a variable's values to lack symmetry or to be more spread out on one side than the other. Positive skewness indicates that values located to the right of the mean are more spread out than are values located to the left of the mean. Negative skewness indicates the opposite.
As an example, think of the distribution of incomes. This distribution is positively skewed because some relatively high values are not offset by correspondingly low values.
At least three nonmissing values are required for computing skewness. In addition, skewness cannot be computed if the standard deviation is 0.