Keyboard shortcuts

Press or to navigate between chapters

Press S or / to search in the book

Press ? to show this help

Press Esc to hide this help

Analyze JD

After searching, use the Analyze step to have Claude AI parse each job description and compute a match score against your profile.

Usage

kairos jobs analyze <job-id>
kairos jobs analyze --all --min-score 0.5   # batch analyze

What Gets Extracted

FieldDescription
Required SkillsMust-have technical skills
Preferred SkillsNice-to-have skills
Years ExperienceMinimum years required
Key ResponsibilitiesMain duties of the role
ATS KeywordsKeywords to include in your resume
PR RequiredWhether permanent residency is required
Citizenship RequiredWhether citizenship is required
Visa SponsorshipWhether the employer offers visa sponsorship
Match Score0.0 - 1.0 match against your profile
Match ReasoningWhy this score was given

Match Scoring

flowchart LR
    JD[Job Description] --> LLM[Claude AI]
    SP[Skill Profile] --> LLM
    Profile[User Profile] --> LLM
    LLM --> Analysis[JdAnalysis]
    Analysis --> Score[Match Score]
    Analysis --> Keywords[ATS Keywords]
    Analysis --> Gaps[Skill Gaps]

The match score considers:

  • Skill proficiency match — your proficiency level per skill vs. what the JD requires (not just “have it or not”)
  • Experience level — your years vs. what they ask for
  • Work rights compatibility — PR/citizenship requirements vs. your status, visa sponsorship availability
  • Role alignment — how well responsibilities match your background

Proficiency-Based Matching

Instead of binary “has skill / doesn’t have skill”, matching uses your Skill Profile:

JD requires: Rust (strong), Python (any), React (strong)
Your profile: Rust 8/10, Python 6/10, React 3/10

  Rust      ████████░░  8/10 vs. required strong → ✓ strong match
  Python    ██████░░░░  6/10 vs. preferred any   → ✓ exceeds
  React     ███░░░░░░░  3/10 vs. required strong → ✗ gap (need ~7+)

This produces a more accurate match score and clearly shows which skills are gaps vs. strengths.

Cost

Each analysis calls Claude API (~500-1500 tokens per JD):

  • ~$0.003-0.01 per job analyzed
  • Batch of 50 jobs ~ $0.15-0.50

The CLI shows estimated cost before batch analysis.