Data Quality Checker

Catches data quality issues in market analysis documents before you publish them. Runs five checks: price scale problems (like confusing ETF and futures prices), ticker notation errors, date and weekday mismatches, allocation percentages that don't add up to 100%, and unit inconsistencies. Everything's advisory, so it flags warnings for you to review rather than blocking publication. Works with both English and Japanese content, which is genuinely useful if you're publishing multilingual reports. The digit-count heuristic for price validation is clever because it survives market moves over time. No dependencies beyond Python standard library, and it always exits clean even when it finds issues, so it won't break your CI pipeline.

skills.sh installs: 3.6K
GitHub stars: 3.7K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add tradermonty/claude-trading-skills --skill data-quality-checker --agent claude-code

Installs into .claude/skills of the current project.

Files

Overview

Detect common data quality issues in market analysis documents before publication. The checker validates five categories: price scale consistency, instrument notation, date/weekday accuracy, allocation totals, and unit usage. All findings are advisory -- they flag potential issues for human review rather than blocking publication.