A standardized, open-source skills taxonomy for AI-powered hiring that goes beyond keyword matching to understand skill relationships and transferability
Traditional ATS systems treat skills as raw text strings, leading to systematic errors:
A structured, machine-readable taxonomy that enables intelligent skill matching and inference.
Example: Job requires "React" and "TypeScript"
Candidate CV lists: "Next.js, JavaScript, Vue.js"
❌ REJECTED - Missing "React" and "TypeScript" keywords
Inference: "Next.js" → implies React, Node.js, JavaScript
"JavaScript" + modern frameworks → likely TypeScript capable
✓ MATCHED - Skills inferred through transferability
Complete taxonomy structure, usage examples, and integration guide
105 skills with 430+ aliases in machine-readable JSON format
Sample code for normalization, inference, and matching
How to add skills, report issues, and submit improvements
CC BY 4.0 - Free to share, adapt, and use commercially with attribution
Version history and taxonomy evolution
Build intelligent skill matching that goes beyond keyword search. Reduce false negatives and improve candidate quality.
Integration guideStandardize skill representation across products. Enable better analytics and benchmarking with normalized data.
API documentationUse as a reference dataset for skill taxonomy research. Build upon for academic work. Contribute improvements back.
Citation formatUpload a CV and job description to see how our skills taxonomy enables intelligent matching beyond keyword search.