- Home
- Skills
- Finance & Accounting
- same event stress test
same event stress test
Build and audit live, multi-channel financial stress tests for DCF models with formula-linked sensitivity charts.
Free
Works with the AI Agents you already use
same event stress test
Example session with this skill installed
Generate a multi-channel stress test for a 20% commodity price drop for my gold mining DCF. Include revenue, royalty, and cost elasticity channels.
- Read your context and instructions
- Compiled the same event stress
I have generated the multi-channel stress test for a 20% commodity price shock. The model isolates the impact across revenue, royalties, and cost co-movement, ensuring the net-debt bridge remains distinct from operating cash flows.
Commodity Price Stress Test (-20% Shock)
| Row | Channel | Impact Type | Valuation Impact (USD/sh) | %Δ vs Base |
|---|---|---|---|---|
| A | Revenue (Price x Volume) | Standalone | -4.20 | -18.5% |
| B | Royalties / Mining Tax | Standalone | +0.45 | +2.0% |
| C | Cost Co-move (Opex Elasticity) | Standalone | +0.85 | +3.7% |
| D | Capex / Reserve Pace | Standalone | +0.15 | +0.7% |
| E | Net Debt / Dividend Bridge | Diagnostic | [Excl. from FULL] | N/A |
| FULL | Cumulative (A+B+C+D) | Cumulative | -2.75 | -12.1% |
Blended-Mid Sensitivity Proxy: -12.1% Δ applied to $22.50 blended mid = $19.78
The tornado and football-field ranges have been wired to the
FULL cumulative row. The cost elasticity (Row C) uses the calibrated yellow judgment input of 0.3x. All values are live formulas; changing the commodity price input will update the entire sensitivity stack.
Next steps
- Review the cost elasticity yellow-fill cell to ensure the 0.3x assumption matches current opex guidance.
- Run
python scripts/check_workbook.pyto confirm no static values were introduced during the wiring of the football field. - Update the cover page to include the "Draft, not investment advice" label before distribution.
Connects securely to your tools. The creator never sees your data.
About this skill
Valuation models often fail because stress tests are either static pastes or messy stacks of unrelated events. This skill provides a rigorous framework for building same-event multi-channel sensitivity tests that stay live, formula-linked, and audit-ready.
What it does
- Multi-channel mapping isolates standalone and cumulative transmission channels for a single shock like interest rates or commodity prices.
- Formula-linked outputs ensures tornado, envelope, and football-field charts update automatically when inputs change.
- Blended-mid proxying applies percentage changes from individual valuation methods to the blended midpoint for consistent reporting.
- Automated validation runs checks for orphan pasted values, financing double-counts, and formula-label mismatches.
- Audit-ready gates issues a CLEAR or BLOCK verdict based on a structured review of workbook integrity and pass-through invariants.
How it works
- Initialize the base model using operating-only FCFF, a clean net-debt bridge, and diluted share counts.
- Build event-specific tables for named shocks, mapping each channel to standalone rows and a cumulative FULL row.
- Wire visualization components by linking chart data ranges directly to the FULL row sensitivity proxies.
- Validate via script to detect static values or sign bugs in royalty and tax calibrations.
- Execute review checklist to generate a cell-cited verdict on workbook construction quality.
Frameworks & tools
The skill utilizes Python scripts for workbook generation and automated checking. It supports Excel and LibreOffice workbooks, focusing on DCF models, WACC calculations, and enterprise value bridges.
Why this beats prompting it yourself
Generic prompts often result in stacked scenarios that break the valuation base or double-count financing impacts. This skill enforces strict channel isolation and "financing once" rules that prevent the mathematical errors common in AI-generated financial models.
Use cases
- Interest rate sensitivity mapping WACC shifts and fixed-debt MTM adjustments without double-counting interest cash.
- Commodity price shocks modeling revenue and opex elasticity separately to avoid re-fitting historical costs.
- Regulatory impact analysis combining volume outages, fiscal changes, and risk-premium add-ons into a single named event.
- Pre-deal model auditing to verify that sensitivity bands are truly live and formula-driven rather than hard-coded.
Known limitations
Does not support stacking multiple unrelated events in a single table. Formula caches remain empty after regeneration until a manual recalculation is performed in Excel or LibreOffice.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Finance & Accounting.
Requires manual recalculation to refresh formula caches after generation. Cannot stack unrelated events in one table. Does not provide investment advice or endorsement of assumptions.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 9 days ago
- Free with an Agensi account
- Software
Python