+ + +
+
+
+ The Occupational Skill Layer +

AI with work experience.

+

A standard agent knows nothing about recruiting, accounting or project work. + skillfactor compiles public occupation data, real job ads and expert knowledge into a + ready-to-use skill per profession — a git-native library that gets better with every project.

+
+ Explore the skill catalog + How it works +
+
+
+
+
Skill package
+ 
recruiter/
+ ├─ SKILL.md
+ ├─ references/
+ │   ├─ usecases.md
+ │   ├─ intake.md
+ │   ├─ quality.md
+ │   └─ tools.md  ← 54% ATS
+ ├─ glossary · literature
+ └─ evals/
+
ATS 54%from 101 real job ads
+
100 occupationsin the catalog — refreshed monthly
+
candidate sourcing 48%market evidence
+
+
+
+
+ + +
+
+
0ESCO occupations as foundation
+
0occupation-to-skill relations
+
0ready-to-use skill packages
+
0real job ads in the evidence store
+
+
+ + +
+
+
+ The formula +

Public occupation knowledge becomes a skill

+

Occupational knowledge belongs to nobody — so nobody maintains it. + skillfactor changes that: three sources, one compilation, versioned in git.

+
+
+

Occupation taxonomies

3,000+ occupations from ESCO & O*NET — public, standardized, multilingual. Joined via the official crosswalk.

+
+
+

Job ads

Current skill requirements from global job platforms — weighted market evidence with percentages and an as-of date.

+
+
+

Expert knowledge

Best practices from literature and the web — as glossary, use cases, intake questions and quality criteria.

+
+
= AI compiles them into the ready-to-use skill for the profession
+
+
+ + +
+
+
+ Data provenance +

Every item knows where it comes from

+

After compilation, each package reports its source mix. + This is the fully enriched recruiter package — + every repo carries the same breakdown as PROVENANCE.md with a rendered chart.

+
+
+
+ + + + + + +
719content items in the recruiter package
+
+
    +
  • Job boards — market evidence

    Full market report from real job ads (JSearch API): ranked requirements with share, seniority distribution, title variants — extracted facts only, aggregated live.

    53%
    • +
  • O*NET — tasks & tools

    Task statements, work activities and software from the U.S. occupation database.

    31%
    • +
  • Wikipedia & AI expert curation

    Glossary, literature, use cases, intake questions, quality criteria and evals — AI-curated with cited web sources.

    10%
    • +
  • ESCO — occupation & competences

    The European profile: essential and optional competences per occupation.

    6%
    • +
+
+

Numbers load live from the package manifest. Library-wide, taxonomies still dominate — enrichment rolls out occupation by occupation, ~30 per month. + See the library-wide chart →

+
+
+ + +
+
+
+ The product +

One agent per employee — preloaded with the profession

+

The agent knows the job from day one — the employee makes it their own. + A sparring partner that gets better every day and never quits.

+
+
+
🏭

Preloaded

Starts with the skill profile of the profession — from ESCO, O*NET and market data.

+
📂

Knows the day-to-day

Mails, chats, documents, meeting transcripts — the personal work context, every day.

+
🎓

Grows with you

Every task and every correction improves it; hidden abilities surface in the skill graph.

+
🔒

Stays in the company

Knowledge stays with the role — even when the person leaves. The role never forgets.

+
+
+
+ + +
+
+
+ Safe sharing +

Private stays private. Public knowledge grows.

+
+
+
+
Communityshared knowledge of all customers — public
+
Companythe company's processes and standards — private
+
Rolethe position's memory — survives staff changes
+
Personpersonal style — owned by the employee
+
+
+

Every boundary is a gate

+
    +
  • Scan for personal data and secrets (sanitize.yml)
    • +
  • Anonymization — knowledge travels, names don't
    • +
  • Structural eval against the profession's test cases (eval.yml)
    • +
  • Human approval — via pull request
    • +
+

See it live: tenant PR with sanitization diff →

+
+
+
+
+ + +
+
+
+ From occupation database to colleague +

Refreshed monthly — skills follow the market

+
+
+
01
SourcesESCO · O*NET · job boards · Wikipedia · literature
+
02
Evidence storerequirements from real job ads — weighted by frequency, on Microsoft SQL Server
+
03
Generatorbuilds skill packages: tasks · intake questions · quality criteria · evals
+
04
Marketplacegit library — publishing via reviewed pull requests
+
05
Runtimeevery employee agent loads its profession's profile
+
+

Visit the marketplace with machine-readable index →

+
+
+ + +
+
+
+

The role never forgets.

+

100 professions are ready — from the production-depth recruiter to the ICT architect. + Every skill is a repo, every release a reviewed pull request.

+
+ View the recruiter skill + All repositories +
+
+
+
+ +
+ skillfactor — concept & prototype: Robert Binsack. Includes information from the O*NET database (USDOL/ETA, CC BY 4.0) + and ESCO (© European Union) — not endorsed by USDOL/ETA or the European Commission. +
+