Skill Extractor API Guide
Skill Extractor API identifies and extracts skills directly from unstructured text—such as job postings, resumes, learning content, or employee summaries—using Pearson’s Skill Ontology.
It helps you transform raw text into structured skills data, enabling standardized skill tagging, capability mapping, and insight generation.
Who is this API for?
This API is designed for roles focused on strategic workforce, learning, and talent processes, particularly:
- People Strategist
To convert unstructured workforce documents into standardized skills mapped to Pearson’s ontology for talent planning and workforce strategy. - Learning Manager
To extract relevant skills for curriculum design, learning content tagging, and capability-led development pathways. - Talent Recruiter
To automatically identify key skills in resumes or job ads, improving candidate matching and reducing manual skill-tagging effort.
Goals this API helps you achieve
The Skill Extractor API supports foundational skill intelligence and standardization initiatives, including:
- Extract skill terms from text
Convert free-text job descriptions, CVs, and role summaries into structured skill labels. - Map data to Pearson’s ontology
Align extracted skills to a validated taxonomy for consistent analysis across hiring, learning, and workforce planning. - Automate skill tagging at scale
Minimize manual interpretation by automatically surfacing skills, contexts, and confidence levels. - Enable skill-based profiling
Build dynamic worker or role profiles informed by skills directly identified from text sources.
What’s included in the response?
When provided with a block of text, the API returns a list of standardized skills and metadata:
| Field | Description |
|---|---|
| skillName | The identified skill mapped to Pearson’s Skill Ontology |
| skillId | Unique ID from the ontology |
| contextPhrases | Text snippets showing where the skill appeared |
| confidenceLevel | Probability score indicating extraction accuracy |
| rawMatches | Phrases matched from the original text |
| textOffsets | Character positions for highlighting |
In the UI, this appears as highlighted text with an “Extracted Skills” panel showing skill chips and tooltips (e.g., the tooltip for Wireframing with definition + confidence rating).
🔥 Hot Tip:
For the richest and most accurate skill insights, provide longer, more detailed input text. The Skill Extractor performs best when it has plenty of context—such as a full job ad, a multi-paragraph role description, or a resume summary packed with responsibilities and requirements.More text = more context = more complete and precise skill extraction.
Input and Output
Input:
-
Source text (required) — any block of unstructured text
-
Precision level (optional) — e.g., High (default)
Output:
A structured list of extracted skills with:
-
ontology mapping
-
context spans
-
confidence levels
-
highlight-ready text ranges
Real-world applications
This API is used widely in skill-driven workforce and talent ecosystems, such as:
- Recruitment systems
Auto-tag resumes and job ads to improve candidate matching and reduce manual parsing. - Learning & development platforms
Extract skills from course content to build adaptive pathways and skill-based learning recommendations. - Workforce intelligence programs
Transform messy internal documents (role descriptions, CVs, performance summaries) into consistent, ontology-aligned skill datasets. - Talent mobility & career frameworks
Use extracted skills to power internal search, opportunity matching, and personalized development plans.
API Bundle
The Skill Extractor API is part of:
Skill Analysis & Development - Ideal for skill intelligence, automated skill tagging, and building standardized, ontology-aligned skill profiles across the workforce.