Month-end without the rebuild
Run the same analysis on this period's export and get a like-for-like read.
— Finance & Investment
Portfolio anomaly watch
Upload a portfolio KPI export with a row per company per period. Outlier detection flags the companies sitting well outside the portfolio norm on their numbers, trend projection shows where the headline metric lands over the next few periods, and grouping ranks companies on each measure.
- Finance & Investment
- Traceable reasoning
- Runs anywhere
1–2 weeks → ~15 minutes
For a full population, not a sample
No coding required
- Input
- Ledger, budget, forecast or model exports
- Output
- Computed figures with the workings retained per line item
- Runs in
- Skillsize · ChatGPT · Claude · Copilot
- Export
- SKILL.md · MCP
- Time saved
- ~1–2 weeks per run
— USE CASES
What people use Portfolio anomaly watch for
Variances explained, not just listed
Each material line item comes with a driver and a size, not only a number.
Cases reviewed on one standard
Hold every submission to the same test so approvals are consistent.
What it works from
- Ledger, budget, forecast or model exports
- Your thresholds, materiality rules and reporting structure
What you get back
- Computed figures with the workings retained per line item
- A commentary-ready pack aligned to how you report
— HOW IT BEHAVES
How Portfolio anomaly watch produces its result
The mechanics behind this specific template — what it reads, what it calculates, and where a human stays in the loop.
Every row of the reporting period in scope
Each row of your export is processed on the same basis, so no line item is skipped however long the table is.
Composed as work product
Findings on the reporting period in scope are written up as a document that reads like professional output, with each claim tied back to a line item.
Roll-up alongside line item-level detail
Detail rows are summarised into the grouped view of the reporting period in scope without losing the underlying line items.
Why this is expensive by hand
Finance work on the reporting period in scope is arithmetic plus interpretation, and it is the interpretation that drifts between analysts and months. Month-end without the rebuild is the typical trigger — run the same analysis on this period's export and get a like-for-like read. Done properly it is defensible; done at pace it becomes a judgement call nobody can retrace. And "properly" usually means 1–2 weeks of manual work.
How this Skill produces it
As a Skill, the work is already sequenced. You bring the evidence, and the run produces computed figures with the workings retained per line item plus a commentary-ready pack aligned to how you report. The criteria, ordering and review points that make the answer trustworthy are encoded in the Skill itself — which is the difference between a structured method and a prompt someone pastes in. The practical effect: 1–2 weeks of manual work becomes a ~15 minutes run, held to an identical standard on the tenth engagement as on the first.
Who it's for
- Finance directors and FP&A teams
- Investment, deal and corporate development teams
- Controllers and reporting managers
- Consultants building or reviewing business cases
Run it in Skillsize — or export it anywhere
Portfolio anomaly watch exports as a structured SKILL.md file and is MCP-ready, so the same method runs in ChatGPT, Claude, Copilot or your own AI products. Adapt it to your methodology, and the intelligence stays yours — not locked to one vendor.
ChatGPTClaudeCopilotAI Products (MCP)
More Finance & Investment Skills
Browse the full library →Finance & Investment
Portfolio concentration & correlation X-ray
Upload a holdings export with a row per position (or per position per period). Correlation analysis shows which measures move together, outlier detection flags positions sitting far outside the norm on weight or exposure, trend projection shows where sector weight drifts if the current path holds, and grouping totals exposure by sector, region and asset class.
Finance & Investment
Invoice late-payment predictor
Upload a payment-history export with a row per invoice and a column recording how it settled (e.g. 'Payment status' = Late/On time, blank for invoices still open).
Finance & Investment
Investment Potential Analysis
Scores a public company's fundamentals alongside live market signals and research for near-term momentum, medium-term trajectory and long-term durability, reconciling all three into one investment-potential verdict.