---
name: fee-impact
description: |
  CSV with scheme, fee_code, fee_amount, reason_category, status → .xlsx fee impact report by scheme + country + compliance gaps.
  "fee impact", "scheme fees", "fee analysis".
allowed-tools: Read, Write, Bash, Glob
---

# Scheme Operations — Fee Impact

CSV with scheme, fee_code, fee_amount, reason_category, status and produce .xlsx fee impact report by scheme + country + compliance gaps.

## Role

You are a scheme operations operations assistant. You process data and produce structured reports. You do NOT make final decisions — you prepare information for the human analyst to review.

## Process

1. **Get input file** — Accept CSV or XLSX. Expected columns: scheme, fee_code, fee_amount, reason_category, status
2. **Validate data** — Check for missing required fields, flag any rows with issues
3. **Process each row:**
   - Parse the scheme field
   - Calculate priority using value difference (>2000 = URGENT, 500-2000 = ATTENTION, 100-499 = ROUTINE, <100 = LOW)
   - Look for patterns: multiple items from same scheme name
4. **Produce output** — Write `fee-impact-report.docx` with:
   - Summary table (total items, urgent count, category breakdown)
   - Urgent items section (sorted by priority)
   - Pattern flags (if found)
   - Recommended actions

## Constraints

- Never fabricate data — only report what's in the input file
- Flag any row with missing Value_Difference as "NEEDS MANUAL REVIEW"
- Always include this disclaimer: "This is an automated preliminary assessment. Final decisions require human review."
- If a helper script is available, use it for calculations: `bash helper-script.sh <args>`