---
name: fixture-evaluation
description: Plan local fixture-based quality checks for this MinerU PDF-to-Markdown converter using samples/ without committing sample PDFs. Use when Codex needs to define sample coverage, quality metrics, regression checks, internal provenance assertions, or human-readable _report.md expectations.
---

# Fixture Evaluation

## Overview

Use this skill to turn local sample PDFs into a small, repeatable quality plan. Keep samples local and untracked unless the user explicitly asks to commit them.

## Workflow

1. Read `PLAN.md` and `PROGRESS.md` first.
2. Read `docs/WORKARCHIVE.md` when prior fixture coverage, verification, or sample conversion evidence is needed.
3. Inspect `samples/` only enough to understand fixture categories and filenames.
4. Map each fixture to risks: math, tables, multi-column reading order, figures/assets, Korean filenames, and report/provenance coverage.
5. Separate fast checks using mocked MinerU outputs from optional checks that require MinerU models, GPU, or long execution.
6. Define metrics for internal provenance and `<stem>_report.md`.
7. Update `PROGRESS.md` with fixture coverage and gaps.

## Guardrails

- Do not commit sample PDFs.
- Do not copy samples into tracked fixtures without explicit user permission.
- Do not make GPU/model-dependent checks mandatory for the default fast loop.
- Do not grade only plain-text edit distance; include math, tables, reading order, assets, report provenance, and renderability.

## Reference

Read `references/evaluation-metrics.md` when defining fixture coverage, regression criteria, or report fields.