Install
$ agentstack add skill-jeffbrines-openfpa-fpa-excel-model ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
Live-Formula Excel Model (Operate)
Overview
Finance professionals ultimately want a workbook where changing an assumption recalculates the model. This skill produces one from the model structure, with named assumption cells and real formulas, then proves it reproduces the engine before it ships. Static value dumps stay with forecast_to_excel; this skill is for living models.
Core principle: no workbook ships unverified. The workbook is generated from the model, never hand-edited values.
The standard model
For the kernel's monthly model, one call:
import pyfpa
cfg = pyfpa.load_config("config.yaml")
pyfpa.model_to_excel(cfg, "model.xlsx")
Or via CLI: python3 -m pyfpa.cli model-export --config config.yaml --out model.xlsx.
The workbook has an Assumptions sheet (every driver a named, editable cell: growth, COGS pct, seasonality, DSO/DIO/DPO, debt, tax, D&A, capex) and a Model sheet where every line of the monthly P&L and cash flow is a formula referencing those names.
Any other cadence or layout
Quarterly, weekly, a tab per segment, a lender view: these are YOUR work, not kernel variants. Compose pyfpa.excel.toolkit (add_named_cell, add_named_row, fill_formula_row, formats) in a company-specific exporter under the generated namespace (models/generated//), then register it:
python3 -m pyfpa.cli entrypoint-register --name excel-quarterly --kind report \
--description "Quarterly live-formula workbook" \
--command-json '["python3", "models/generated//excel_quarterly.py"]'
Keep formulas within the supported vocabulary (arithmetic, ^, SUM, MIN, MAX, IF) so verification works.
Verify before delivering (always)
pip install formulas(verification-only dependency, not shipped at runtime).- ```python
report = pyfpa.verifyworkbook("model.xlsx", pyfpa.cashflowfrom_config(cfg)) assert report.passed, report.failures ```
- For a bespoke exporter, verify against the frame your exporter is meant to
reproduce (the engine frame, or its quarterly/weekly aggregation).
- A failing report means the exporter is wrong. Fix the formulas, never the
tolerance, and never deliver an unverified workbook.
Guardrails
- No workbook ships unverified.
- Generated from model structure; never paste computed values into formula cells.
- Supported formula vocabulary only; if you need a function outside it, restructure
the formula (helper rows are fine) rather than expanding the vocabulary.
- Company-specific exporters live in generated namespaces and get tests like any
other generated code.
Next
Workbook delivered, then fpa-board-briefing (the narrative that goes with it).
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: JeffBrines
- Source: JeffBrines/openfpa
- License: MIT
- Homepage: https://www.guiderail.io
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.