audit-card-parsing

Compare parsed JSON card structures against Oracle text to detect misparses.

212|148|Updated Mar 10, 2026
One-click install
npx skills add https://github.com/phase-rs/phase --skill audit-card-parsing
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: audit-card-parsing
Source: https://github.com/phase-rs/phase/tree/main/.claude/skills/audit-card-parsing
Command: npx skills add https://github.com/phase-rs/phase --skill audit-card-parsing

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Semantic audit of card-data.json — compare parsed JSON structures against Oracle text to find misparses in cards the coverage system marks as "supported." Supports --after for parallel agent runs and appends to a shared report.

Core Features & Use Cases

  • Semantic cross-checks between Oracle text and parsed structures for accuracy
  • Batch processing with --after for distributed auditing
  • Consolidated reporting to .planning/parser-audit-report.md and resume-point tracking

Quick Start

Run the audit on client/public/card-data.json to start validating parsed structures against Oracle text.

Frequently Asked Questions about audit-card-parsing

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I audit parsed MTG card data for misparses against Oracle text?

The audit works by comparing parsed JSON structures against Oracle text to find misparses in cards the coverage system marks as supported. It appends findings to .planning/parser-audit-report.md for review.

Can I run parallel batch processing for card data audits?

Yes, the audit supports batch processing with the --after flag for distributed agents. Multiple agents run concurrently against card-data.json and append results to a shared parser-audit-report.md.

Do I need jq to extract and validate MTG card JSON structures?

Yes, the audit requires jq-based batch extraction to parse and validate MTG card JSON structures against Oracle text. Jq enables the semantic cross-checks needed to identify misparses.

How do I resume an interrupted MTG card data parser audit?

You resume an interrupted MTG card data parser audit using built-in resume-point tracking. The audit continues from the last checkpoint and appends new findings to the existing parser-audit-report.md.

What is a semantic cross-check for MTG card data quality?

A semantic cross-check for MTG card data quality compares parsed JSON structures against Oracle text to find misparses in supported cards. It validates that parsed data accurately reflects official card rules and mechanics.