Skills Normalizer - Map Free-Text Skills to a Taxonomy

What does Skills Normalizer do?

Skills Normalizer maps free-text skills to a taxonomy of 11,000+ skills. Send a skill, a list or a whole skills section, and get for each skill found:

• a stable ID (excel, react…) to store and filter on,
• the canonical name, in the output language you choose,
• its type: hard skill, software, certification, soft skill or language,
• its families and domains (e.g. Frontend development → Software Development),
• a broader skill to widen a search (Excel → Microsoft Office),
• the mention in your text it was found in.

Parts of the text that match no skill are listed in unresolved, with likely families, so nothing is guessed.

It is powered by the HireLayer skills API. Processing runs in the EU.

Why use it?

• Clean skill data: "MS Excel", "excel avancé" and "Microsoft Excel" become one skill.
• Better search and matching: filter candidates or jobs by skill ID, family or domain.
• Labour market analytics: count skills across job ads or profiles without spelling noise.

How to use it

1. Click Try for free.
2. Enter one text per line (up to 5,000 characters each).
3. Choose the output language and click Start.

Input

{
  "texts": ["React, TypeScript, Node.js, AWS, Excel, project management, fluent Spanish"],
  "language": "en"
}

Output

One dataset item per text:

{
  "input_text": "React, TypeScript, Excel, fluent Spanish, project management",
  "status": "success",
  "language": "en",
  "skills": [
    {
      "id": "react",
      "name": "React",
      "type": "software",
      "mention": "React",
      "families": [{ "id": "frontend_development", "name": "Frontend development", "domain_id": "software_development" }],
      "domains": [{ "id": "software_development", "name": "Software Development" }],
      "broader": null
    }
  ],
  "unresolved": [],
  "taxonomy_version": "v1"
}

Pricing

$0.05 per text, whatever the number of skills it contains. A text that cannot be processed is not charged.

Use it from code

curl -X POST "https://api.apify.com/v2/acts/hirelayer~skills-normalizer/run-sync-get-dataset-items?token=YOUR_APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"texts": ["Python, SQL, Power BI"], "language": "en"}'

The Actor is also available to AI agents through the Apify MCP server.

FAQ

Can I see the whole taxonomy? Yes, through the HireLayer Skills API.

Need help? Open an issue in the Issues tab or write to contact@hirelayer.co.