Description
datapack-builder is an agent skill from the anthropics/financial-services collection for building standardized financial data packs for private equity, investment banking and asset management. It turns information from confidential information memorandums, offering memorandums, SEC filings, web search or financial data servers into a polished Excel workbook for investment committee review. The skill sets critical success factors that every pack must meet, and it treats failure on any of them as making the deliverable unusable. The first is data accuracy with zero tolerance for errors: every number is traced to its source document with a page reference, all calculations are formulas rather than typed values, subtotals and totals are cross-checked, the balance sheet must balance, and cash flow must tie to the balance sheet changes. The skill uses the spreadsheet skill for all Excel work. It is useful for deal and investment teams who need a consistent, auditable data pack from a set of source documents. The numbers in a pack support a real investment decision, so every figure should be checked against its source, and the pack should be reviewed by the deal team before it goes to a committee. The skill is installed with the skills CLI from the anthropics/financial-services repository. Its skills.sh page showed about 1.7K installs, with Gen Agent Trust Hub and Socket passing and Snyk showing a warning at the time of the scan.…
Highlights
- Data packs from memorandums, filings and data servers
- Zero-tolerance data accuracy rules
- Every number traced to a page reference
- Formula-based calculations and balance checks
- Installs with the skills CLI
Ratings & Reviews
No ratings yet
Be the first to rate datapack-builder.
People also visit
3-statement-model
Complete, populate and fill out 3-statement financial model templates
datapack-builder FAQ
What does it build?
A standardized Excel data pack from offering memorandums, CIMs, SEC filings, web search or financial data servers.
What accuracy rules apply?
Every number traced to a page reference, formulas instead of typed values, cross-checked totals, and a balance sheet that balances.
Should the numbers be checked?
Yes. Each figure should be checked against its source, and the deal team should review the pack before committee.
How do I install it?
Run npx skills add https://github.com/anthropics/financial-services --skill datapack-builder.
What security audits does it have?
skills.sh lists three audits: Gen Agent Trust Hub Pass, Socket Pass and Snyk Warn. A Warn or Fail is worth reading before you install.
What are the best datapack-builder alternatives?
Popular alternatives to datapack-builder include 3-statement-model, audit-xls and clean-data-xls. See all datapack-builder alternatives