Financev1.0.0By uristocratVerified

GL to Report

Takes a raw general-ledger export and reformats it into your reporting template (the flash report), then drafts plain-English variance commentary against prior actuals and budget. Handles the close-and-reporting drudgery: line-and-column reformatting plus a first-pass narrative on what moved and why. Every commentary line cites both the variance math and the claimed driver. Unmapped GL lines are flagged, not force-mapped. Sign-convention mismatches between export and template are flagged, not silently re-signed. Blank Rules (no mappings, threshold, or layout) hard-stop the run for plan-mode input. Works with any GL system (Sage Intacct, QuickBooks, etc.). The upstream GL pull is a separate skill.

general ledgerflash reportvariance commentarymonthly closefinancial reporting
Install

Simple install — no setup required

1

Download the skill file below

2

Add it to Claude — pick your platform:

Claude desktop app

  1. Open the Claude desktop app
  2. Go to Code, then Customize
  3. Click Create a new skill
  4. Upload the skill file you downloaded

claude.ai (web)

  1. Go to Customize, then Skills
  2. Click +, then Create a new skill
  3. Upload the skill file you downloaded
3

Say a trigger phrase to activate it

Download skill file

What this skill does

This is an overview of the skill from the site, not the skill's real instructions. The full SKILL.md Claude reads when this skill is active lives on GitHub at the pinned source below.

GL to Report

Turn a raw accounting/GL export into a clean reporting template (flash report) and draft variance commentary against prior actuals and budget. Use for the monthly close and the recurring flash report.

Every commentary line cites both the variance math and the claimed driver. Unmapped GL lines are flagged, not force-mapped. Sign-convention mismatches are surfaced, not silently re-signed. Blank Rules hard-stop the run for plan-mode input rather than guessing.

Includes an eval contract with five self-tests covering over-threshold commentary, unmapped account flagging, driverless variance rejection, blank-Rules hard-stop, and sign-convention flip detection.

View full SKILL.md on GitHub