Finance Dataset Readiness Review
Profile financial data, isolate reporting risks, reconcile control totals, and identify which analyses the data can support.
Before & after
Same prompt, same agent — the only difference is the skill.
I can look at your revenue data. Typically you'd want to check for missing values, duplicates, and outliers. Do you have the data in a spreadsheet or database? What date range covers it? How frequently does it get updated? Once I can see the structure, I can help you spot any obvious problems, though a full data quality audit would take some time and detailed inspection.
DATA QUALITY PROFILE: Revenue Dataset → DATASET OVERVIEW Rows: 24,847 transactions Columns: 12 (date, customer_id, amount, product, region, discount, etc.) Date range: Jan 1, 2025 – Aug 31, 2025 (9 months complete) File format: CSV, 3.2 MB → MISSING DATA ISSUES (data cannot support all analyses) customer_id: 0 missing (100% complete) amount: 18 missing rows (0.07% – acceptable for most analyses) discount: 1,247 missing (5.02% – HIGH, cannot calculate true LTV) region: 0 missing Trap: Discount field missing biases analysis toward full-price customers only Impact: Revenue analysis okay; margin analysis unreliable → NEGATIVE VALUES & OUTLIERS Negative amounts: 234 refunds (legitimate, separate analysis needed) Amounts > $100k: 3 rows (verify not data entry errors) Amounts < $1: 67 rows (mostly legitimate small add-ons) Recommendation: Flag large transactions for manual spot-check (verify real) → DUPLICATES & FORMATTING Exact duplicates: 0 found Near-duplicates: 12 rows (same customer, same date, same amount – likely double-posted) Date format issues: All dates parsed correctly (no malformed entries) Fix: Remove 12 near-duplicates (customer_id + date + amount combo must be unique) → DISTRIBUTION QUALITY Revenue by month: Concentrated in June-July (seasonal spike, not data error) Revenue by region: North accounts for 58% (concentration okay if real) Top 10 customers: $2.8M of $18.4M total (27% concentration – typical for B2B) → RECOMMENDED ANALYSES (data quality supports these) ✓ Monthly revenue trend analysis (complete data) ✓ Regional performance comparison (all regions present) ✓ Customer cohort retention (customer_id clean) ✗ Margin by product (discount field too sparse) ✗ Discount impact study (5% missing creates bias) → DATA PREP ACTIONS First: Remove 12 near-duplicates (creates single source of truth) Then: Impute discount? No – remove rows where discount = null for margin analysis Document: Margin analysis only on 23,600 records (discount present) Finalize: Dataset is ready for revenue and customer analysis; margin analysis limited scope
About this skill
Your export opens cleanly, but revenue still looks wrong. This review checks the grain, business keys, missing values, sign conventions, period coverage, and control totals before those problems reach a forecast or dashboard.
What it does
- Maps columns to financial measures, identifiers, dimensions, dates, and their intended aggregation rules.
- Separates exact duplicate rows from repeated business keys, legitimate line items, and conflicting versions.
- Quantifies missing data by row count, percentage, financial exposure, and reporting segment.
- Checks currencies, units, negative values, date ambiguity, period gaps, and incomplete reporting periods.
- Reconciles comparable totals and explains differences without silently changing source data.
- Ranks fixes by financial impact and identifies which requested analyses can proceed.
What you get
A scoped readiness review with a field map, quantified findings, reconciliation bridge, and prioritized fix list. Each requested analysis receives a ready, conditional, blocked, or not-assessed verdict, with the evidence and limitations behind it.
Best for
FP&A analysts, finance teams, and data analysts validating ERP exports, transaction feeds, ledger extracts, or reporting tables before building models and dashboards.
SKILL.md preview
---
name: finance-dataset-readiness-review
description: Profiles unfamiliar financial datasets by establishing row grain, testing business keys and financial semantics, quantifying defects, and reconciling comparable control totals. Determines which requested analyses are supportable before modeling or reporting. Use when the user says "check this finance export", "can I trust this dataset?", "profile this ledger", "my revenue totals keep changing", "find duplicate transactions", "validate this data before forecasting", or "what analysis can this file support?".
---
# Finance Dataset Readiness Review
… (sign up to view the full skill)More finance skills
View all Finance skills →Portfolio Rebalance Advisor
Drop in your current holdings and target allocation — get the exact buy/sell list, tax-loss opportunities, and drift alert.
Personal Finance Q&A
Ask any personal-finance question and get a plain-English answer tailored to your bracket, timeline, and risk appetite.
Earnings Report Analyzer
Paste a 10-K, 10-Q, or earnings call transcript — get the numbers that matter, the narrative changes, and what the CFO tried to bury.
Investment Committee Decision Memo
Turn deal materials into an investment memo with traced evidence, reconciled financials, downside cases, and decision gates.