payslip

/smartspender:payslip

Trigger

• /smartspender:payslip upload
• /smartspender:payslip history
• /smartspender:payslip learn
• "Upload en lønseddel"
• "Registrer min lønseddel"
• "Vis lønseddelhistorik"
• "Show my payslip history"

Arguments

Argument	Required	Values	Default
action	yes	upload, history, learn	-

---

Action: upload

Prerequisites

• At least one bank sync completed (transactions.csv exists with data) for matching to work
• User has a payslip image or PDF ready to share

Workflow

1. Prompt the user to share their payslip: "Del venligst din lønseddel — du kan indsætte et billede eller trække en PDF ind i chatten."
2. [USER ACTION]: User attaches a payslip image or PDF
3. If no file is attached, respond: "Jeg kan ikke se nogen lønseddel. Indsæt venligst et billede eller en PDF."
4. Load extraction rules: skills/payslip-parsing/SKILL.md
5. Detect employer from the uploaded file (header, CVR, filename) per the payslip-parsing skill
6. If employer detected: check for payslip-knowledge/{employer-id}/PARSER.md
   • If parser exists: load employer-specific extraction rules
   • If no parser: continue with general extraction rules
7. Extract payslip data using Claude Vision:
   • pay_period (YYYY-MM)
   • employer (company name)
   • gross_salary (bruttoløn)
   • am_bidrag (8% labor market contribution)
   • a_skat (income tax)
   • pension_employer (arbejdsgiverpension)
   • pension_employee (egetbidrag)
   • atp (ATP contribution)
   • feriepenge (holiday pay)
   • net_salary (nettoløn / udbetalt)
   • Any additional benefits (sundhedsforsikring, fritvalgskonto, etc.)
8. Calculate derived fields:
   • pension_total = pension_employer + pension_employee
   • pension_pct = (pension_total / gross_salary) * 100
9. Validate extraction per skills/payslip-parsing/SKILL.md:
   • AM-bidrag should be ~8% of gross (±5 kr tolerance)
   • Sum check: gross - deductions ≈ net (±2% tolerance)
10. Present extraction summary to user for confirmation:

    Jeg aflæste følgende fra lønsedlen:
    
    Lønperiode: {pay_period, Danish format}
    Arbejdsgiver: {employer}
    
    INDTÆGTER
    Bruttoløn:              {gross_salary} kr
    
    FRADRAG
    AM-bidrag (8%):         {am_bidrag} kr
    A-skat:                 {a_skat} kr
    ATP:                    {atp} kr
    Pension (egetbidrag):   {pension_employee} kr
    
    ARBEJDSGIVERBIDRAG
    Pension:                {pension_employer} kr
    
    TIL UDBETALING:         {net_salary} kr
    
    Samlet pension: {pension_total} kr ({pension_pct}% af bruttoløn)
    
    Er det korrekt? (Eller ret de felter der er forkerte)
    

11. [USER ACTION]: User confirms or provides corrections
12. Apply any corrections from the user
13. Load schema: skills/data-schemas/SKILL.md
14. Check for duplicate payslips in payslips.csv (same employer_id + same pay_period). If duplicate found, ask: "Denne lønseddel ligner en der allerede er registreret ({payslip_id} for {pay_period}). Vil du tilføje den alligevel?"
15. [USER ACTION] (only if duplicate): User confirms or cancels
16. If user cancels on duplicate, stop and output: "Lønsedlen blev ikke tilføjet."
17. Load matching rules: skills/transaction-matching/SKILL.md
18. Search transactions.csv for matching salary transactions:
    • Amount within ±1% of net_salary
    • Date within 5 days after pay_period end (e.g., for January payslip, search Feb 1-5)
    • Transaction type: CRDT (credit/income)
    • Description patterns: "Løn", "Salary", employer name
19. Score candidates per transaction-matching confidence rules
20. If exactly 1 match with confidence >= 0.8: auto-link to the transaction
21. If multiple candidates or confidence < 0.8: present candidates to user:

    Jeg fandt {n} mulige løntransaktioner til denne lønseddel:
    
    1. {date} — {description} — {amount} kr (match: {confidence_pct}%)
    2. {date} — {description} — {amount} kr (match: {confidence_pct}%)
    
    Hvilken transaktion hører lønsedlen til? (Eller "ingen" hvis ingen passer)
    

22. [USER ACTION] (only if ambiguous): User picks a candidate or says "ingen"
23. If no candidates found: store as unmatched
24. Generate payslip_id (ps- + 8 hex chars)
25. Create the payslips/ directory if it does not exist
26. Save the uploaded file to payslips/{payslip_id}.{ext} (preserve original extension). Set file_reference to this path.
27. Serialize benefits to JSON string for benefits_json column
28. If payslips.csv does not exist, create it with the header row
29. Append payslip row to payslips.csv
30. Append event to action-log.csv:
    • action_type: payslip
    • target: {employer}
    • status: completed
    • details: "{pay_period}, pension {pension_pct}%, {match_status}"
31. Output summary in Danish
32. If pension_pct < 15, add recommendation: "Bemærk: Din pensionsopsparing er {pension_pct}% — anbefalet minimum er 15% af bruttoløn."
33. If this was a new employer without a parser and the user made corrections, suggest: "Tip: Kør /smartspender:payslip learn for at gemme udtræksregler for {employer}."