From datarails-financeos
Generate comprehensive anomaly detection report with Excel deliverables. Discovers data quality issues without requiring configuration.
How this skill is triggered — by the user, by Claude, or both
Slash command
/datarails-financeos:anomalies-report [--table-id <id>] [--severity <level>] [--output <file>][--table-id <id>] [--severity <level>] [--output <file>]This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Generate comprehensive data quality assessment report with automated anomaly detection.
Generate comprehensive data quality assessment report with automated anomaly detection.
This skill automatically discovers your data structure and detects issues without requiring pre-configuration. Works with any Datarails Finance OS table.
General-Purpose:
| Argument | Description | Default |
|---|---|---|
--table-id <id> | Specific table to analyze | Uses profile or discovers automatically |
--severity <level> | Filter results: critical, high, medium, low | All |
--output <file> | Output filename | tmp/Anomaly_Report_TIMESTAMP.xlsx |
Phase 1: Discovery
--table-id, discover tables or use profilePhase 2: Anomaly Detection
detect_anomalies - Automated data quality checksWhen generating Excel or PowerPoint files, apply Datarails brand styling:
Font: Poppins (fall back to Calibri if unavailable). Weights: 400 regular, 600 semibold, 700 bold.
Colors:
| Role | Hex | Use |
|---|---|---|
| Navy | 0C142B | Header/banner background |
| Main text | 333333 | Primary text |
| Secondary | 6D6E6F | Muted/subtitle text |
| Border | 9EA1AA | Cell borders |
| Section bg | F2F2FB | Section header / row header background (lavender) |
| Input bg | EAEAFF | Editable/input cell background |
| Input text | 4646CE | Editable cell text (indigo) |
| Favorable | 2ECC71 | Positive variance / good KPI delta |
| Unfavorable | E74C3C | Negative variance / bad KPI delta |
| Chart 1 | 0C142B | Actuals (navy) |
| Chart 2 | F93576 | Budget (hot pink) |
| Chart 3 | 00B4D8 | Teal |
| Chart 4 | FFA30F | Amber |
Excel layout:
Number formats: _(* #,##0_);_(* (#,##0);_(* "-"_);_(@_) (default), $#,##0 (dollars), $#,##0.0,,"M" (millions), 0.0% (percent)
Variance coloring: Any cell showing a delta/change: green (2ECC71) if favorable, red (E74C3C) if unfavorable. Apply automatically based on value sign and metric context.
PowerPoint: Navy (0C142B) background, 16:9 widescreen, Poppins font, white text, amber (FFA30F) accent lines, card backgrounds 001F37.
If asked to add live / refreshable Datarails formulas (DR.GET) to a generated workbook, the only valid form is:
=DR.GET(Value, "[DimensionName]", CellRef, "[DimensionName]", CellRef, ...)
=DR.GET(Value,"financials","Amount","SUM",...)
is invented syntax that the Datarails Add-in cannot parse or refresh."[Scenario]").
Dimension values are always cell references, never hardcoded strings.Value
referring to the string constant "Value"
(wb.defined_names.add(DefinedName("Value", attr_text='"Value"'))) —
otherwise Excel autocorrects the bare token to its built-in VALUE() and
the formula breaks.=DR.GET(...) only — never wrapped in IFERROR/IF/ROUND.The get-formula skill (/dr-get-formula) is the full reference — parameter
cells, validated dimension values, report layouts. Prefer it for whole formula
workbooks; apply this contract when adding DR.GET formulas to a workbook here.
Phase 3: Report Generation
Phase 4: Summary
/dr-anomalies-report
Output:
🔍 Discovering financials table...
✓ Found financials table: TABLE_ID
📊 Analyzing table TABLE_ID...
🔬 Running anomaly detection...
📈 Profiling numeric fields...
📝 Profiling categorical fields...
🔍 Fetching sample records...
📊 Summarizing results...
📄 Generating Excel report...
✅ Report generated: tmp/Anomaly_Report_2026-02-03_143022.xlsx
==================================================
ANOMALY DETECTION SUMMARY
==================================================
Table: TABLE_ID
Total Anomalies: 45
Data Quality Score: 87/100
By Severity:
Critical: 2
High: 8
Medium: 23
Low: 12
Report: tmp/Anomaly_Report_2026-02-03_143022.xlsx
==================================================
/dr-anomalies-report --table-id TABLE_ID --severity critical
/dr-anomalies-report --env app --output tmp/Quality_Check_Feb_2026.xlsx
Score ranges from 0-100:
Calculation:
Score = 100 - (critical×10 + high×5 + medium×2 + low×0.5)
Clamped to 0-100 range
${CLAUDE_PLUGIN_DATA}/client-profiles/<env>.json (or config/client-profiles/<env>.json)If profile incomplete or unavailable:
/dr-anomalies-report --env app --output tmp/DQ_Check_$(date +%Y-%m).xlsx
/dr-anomalies-report --severity critical
Alerts on critical issues that could affect close
/dr-anomalies-report --table-id 12345 --severity high
Checks specific department data for issues
/dr-anomalies-report --table-id unknown_table_id
Discovers what's in an unfamiliar table
Reports are saved to: tmp/Anomaly_Report_YYYY-MM-DD_HHMMSS.xlsx
Each report includes:
"Not authenticated" error
"No tables found" error
"Table not found" error
/dr-tables to see available tables"Incomplete profile" error
/dr-learn to refresh profile--table-id to override/dr-tables - List and explore available tables/dr-learn - Discover and create client profiles/dr-extract - Extract validated financial data/dr-reconcile - Compare P&L vs KPI dataScaling handled automatically via pagination and efficient MCP tools.
npx claudepluginhub datarails/dr-claude-code-plugins-re --plugin datarails-financeosProvides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Searches MemPalace before answering questions about past work, people, projects, or prior decisions. Returns verbatim stored content instead of guessing from model memory.