Takes a GL extract and a subledger extract for the same scope, normalizes both to a common key, then outer-joins and buckets every line as matched, amount break, quantity break, timing break, or one-side-only. For each break it tags a likely cause like FX mismatch, timing difference, or mapping issue. You get a break report sorted by materiality and a summary with match percentages. It's built for daily or month-end reconciliation across asset classes and knows to treat subledger data as untrusted input, not instructions. Honestly the classification logic saves hours compared to staring at pivot tables, and the output pairs cleanly with root-cause tooling.
npx skills add https://github.com/anthropics/financial-services --skill gl-recon