# Loss Run Parser

> Parse a workers'-comp loss run into normalized rows. Use when a user has a carrier loss-run PDF or spreadsheet and needs claims, paid, reserves, and incurred extracted per claim.

- Skill: `jdutton/loss-run-parser` (Agent Skill)
- Install (CLI): `npx skillmds@latest add jdutton/loss-run-parser`
- Raw SKILL.md: https://api.skillmd.com/api/skills/jdutton/loss-run-parser/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Data & Analytics
- Author: jdutton (https://skillmd.com/u/jdutton)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/jdutton/loss-run-parser

---


# Loss Run Parser

Normalize a carrier loss run into one row per claim with paid, reserve, and
incurred figures.

## Column mapping

Carrier column names vary. See [the column-mapping reference](references/column-aliases.md)
for the alias table covering the major carriers.

## Steps

1. Detect the header row and map carrier columns to the canonical schema.
2. Emit one normalized row per claim.
3. Report rows where paid + reserve does not tie to incurred.