How does Steppingblocks obtain and classify its skills data?

People describe the same skill in dozens of different ways. One person writes "Python," another writes "Python programming," another writes "Python 3.x development." A traditional database would treat those as three different skills. That's not useful.

We use a multi-step intelligence process to read every skill a professional has listed on their profile, understand what they actually mean, and connect it to a standardized skill catalog.

Think of it like a highly experienced recruiter who has reviewed millions of resumes. They know that "SQL querying," "database querying," and "structured query language" all point to the same underlying capability, and they file them accordingly.

Every skill in our platform maps to one of over 140,000 canonical skills, organized into a clear three-level structure:

This means when you are looking at "data analysis" skills, you are looking at everyone with that capability regardless of how they personally described it on their profile.

Not all skills on a resume carry the same weight. "Leadership" appears on nearly every professional profile. It's background noise. "HPLC chromatography" appears on a small, specific population. It's a meaningful signal.

We score each skill for distinctiveness: how rare is this skill across the full workforce, and how prominently does this person claim it? This lets you identify what truly sets a population apart, not just what they list, but what defines them.

When you look at skill data for your graduates or target employers, you're not seeing a raw dump of resume text. You're seeing a cleaned, standardized, intelligence-enriched view of what your people actually know in a language that's consistent across every institution and employer in our platform.