Menu

Individual skill

tornado-sensitivity

0upvotes

Which assumption actually moves the answer — one-at-a-time sensitivity, ranked into a tornado. Use when a model's output is being argued about (LTV, ROI, forecast) and the room is debating drivers that don't matter, or before spending diligence effort: swing every driver low→high and see which one owns the outcome. Produces the ranked tornado table, share-of-swing per driver, and a real .xlsx — via the bundled zero-dependency script with a safely restricted formula evaluator.

skills/tornado-sensitivity/SKILL.md

Read pinned source

Source commit f7c90bc09ee05dc25cf257bdb1826f2c2552c2cb

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Network or broad shell
Last checked
Nov 9, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
1,537
Repository last updated
Nov 8, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# Tornado Sensitivity

Every model has four drivers people argue about and one that actually controls the answer — usually not the same one. The tornado ranks them: hold everything at base, swing one driver to its low and high, measure the output range, sort. Diligence goes to the top bar; the bottom bars stop hijacking meetings.

## Required Inputs

- **The model** — output name, a formula over named drivers (arithmetic + min/max/abs/sqrt/log/exp only), and per-driver low/base/high. The lows and highs should be *defensible bounds* ("the worst quarter we've seen", "the vendor's contractual ceiling"), not ±10% ritual.
- If the requester has a spreadsheet instead of a formula: extract the output cell's driver chain into a formula first, and show it for confirmation.

## Output Format

1. **The tornado table** — drivers sorted by output swing, with input range, output at each end, and **share of total swing**. The top driver's share is the headline ("lifetime owns 33% of the uncertainty").
2. **The meeting verdict** — one paragraph: what deserves diligence, what deserves a decision-and-move-on, and any driver whose *bounds* are the real problem (huge swing because nobody actually knows the range).
3. **The interaction caveat** — one-at-a-time ignores correlated drivers; if two move together in reality (price and churn), say so and model the pair as one driver.
Back to top