Menu
Decompose variances into drivers with narrative explanations and waterfall analysis
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full ASM JSON, flattened CSV for easy import, and exportable Python code for data engineers. Common triggers include converting instrument files, standardizing lab data, preparing data for upload to LIMS/ELN systems, or generating parser code for production pipelines.
Run nf-core bioinformatics pipelines (rnaseq, sarek, atacseq) on sequencing data. Use when analyzing RNA-seq, WGS/WES, or ATAC-seq data—either local FASTQs or public datasets from GEO/SRA. Triggers on nf-core, Nextflow, FASTQ analysis, variant calling, gene expression, differential expression, GEO reanalysis, GSE/GSM/SRR accessions, or samplesheet creation.
Strategic scientific problem selection, project ideation, and troubleshooting based on the Fischbach & Walsh framework.
Deep learning for single-cell analysis using scvi-tools and scverse ecosystem. This skill should be used when users need (1) data integration and batch correction with scVI/scANVI, (2) ATAC-seq analysis with PeakVI, (3) CITE-seq multi-modal analysis with totalVI, (4) multiome RNA+ATAC analysis with MultiVI, (5) spatial transcriptomics deconvolution with DestVI, (6) label transfer and reference mapping, (7) RNA velocity with veloVI, or (8) QC analysis of single-cell RNA-seq data. Triggers include scVI, scANVI, totalVI, QC, quality control, batch correction, integration, multi-modal.
A conversational framework for systematic scientific problem selection, project ideation, troubleshooting, and strategic decision making.
| name | finance-variance-analysis |
| description | Decompose variances into drivers with narrative explanations and waterfall analysis |
If you see unfamiliar placeholders or need to check which tools are connected, please ask about available integrations.
Important: This skill assists with variance analysis workflows but does not provide financial advice. All analyses should be reviewed by qualified financial professionals before use in reporting.
Decompose variances into underlying drivers, provide narrative explanations for significant variances, and generate waterfall analysis.
You can ask to analyze variances for a specific area (e.g., "Analyze revenue variance for Q4" or "Explain the flux in OPEX").
area — The area to analyze:
revenue — Revenue variance by stream, product, geography, customer segmentopex — Operating expense variance by category, department, cost centercapex — Capital expenditure variance vs budget by project and asset classheadcount — Headcount and compensation variance by department and role levelcogs or cost-of-revenue — Cost of revenue variance by componentgross-margin — Gross margin analysis with mix and rate effectsperiod-comparison — The periods to compare. Formats:
2024-12 vs 2024-11 — Month over month2024-12 vs 2023-12 — Year over year2024-Q4 vs 2024-Q3 — Quarter over quarter2024-12 vs budget — Actual vs budget2024-12 vs forecast — Actual vs forecast2024-Q4 vs 2024-Q3 vs 2023-Q4 — Three-way comparisonIf an ERP or data warehouse is connected:
If no data source is connected:
Connect an ERP or data warehouse to pull financial data automatically. To analyze manually, provide:
- Actual data for both comparison periods (at account or line-item detail)
- Budget/forecast data (if comparing to plan)
- Any operational metrics that drive the financial results (headcount, volumes, pricing, etc.)
VARIANCE SUMMARY: [Area] — [Period 1] vs [Period 2]
Period 1 Period 2 Variance ($) Variance (%)
-------- -------- ------------ ------------
Total [Area] $XX,XXX $XX,XXX $X,XXX X.X%
Break down the total variance into constituent drivers. Use the appropriate decomposition method for the area:
Revenue Decomposition:
Operating Expense Decomposition:
CapEx Decomposition:
Headcount Decomposition:
Generate a text-based waterfall showing how each driver contributes to the total variance:
WATERFALL: [Area] — [Period 1] vs [Period 2]
[Period 2 Base] $XX,XXX
|
|--[+] [Driver 1 description] +$X,XXX
|--[+] [Driver 2 description] +$X,XXX
|--[-] [Driver 3 description] -$X,XXX
|--[+] [Driver 4 description] +$X,XXX
|--[-] [Driver 5 description] -$X,XXX
|
[Period 1 Actual] $XX,XXX
Variance Reconciliation:
Driver 1: +$X,XXX (XX% of total variance)
Driver 2: +$X,XXX (XX% of total variance)
Driver 3: -$X,XXX (XX% of total variance)
Driver 4: +$X,XXX (XX% of total variance)
Driver 5: -$X,XXX (XX% of total variance)
Unexplained: $X,XXX (XX% of total variance)
--------
Total: $X,XXX (100%)
For each significant driver, generate a narrative explanation:
[Driver name] — [Favorable/Unfavorable] variance of $X,XXX (X.X%)
[2-3 sentence explanation of what caused this variance, referencing specific operational factors, business events, or decisions. Include quantification where possible.]
Outlook: [Whether this is expected to continue, reverse, or change in future periods]
If the decomposition does not fully explain the total variance, flag the residual:
Unexplained variance: $X,XXX (X.X% of total)
Possible causes to investigate:
- [Suggested area 1]
- [Suggested area 2]
- [Suggested area 3]
Ask the user for additional context on unexplained variances:
Provide: