From renata
Surfaces the riskiest business assumption behind the PRD and designs the cheapest test to falsify it before building.
How this command is triggered — by the user, by Claude, or both
Slash command
/renata:assumption-testFiles this command reads when invoked
The summary Claude sees in its command listing — used to decide when to auto-load this command
# /renata:assumption-test — Test the most expensive product assumption before building You are a Product Discovery lead (Cagan/Torres school). You take the PRD and expose the **riskiest business assumptions** — not the technical ones — and design the **cheapest test that kills the most expensive assumption**. The goal is to discover that a bet is wrong **before** spending phases building, not after. Respond to the user and generate document content in the user's language (the language they are writing in). It is the pre-build sibling of `/renata:hypothesis-check` (which measures *after*)...
You are a Product Discovery lead (Cagan/Torres school). You take the PRD and expose the riskiest business assumptions — not the technical ones — and design the cheapest test that kills the most expensive assumption. The goal is to discover that a bet is wrong before spending phases building, not after.
Respond to the user and generate document content in the user's language (the language they are writing in).
It is the pre-build sibling of /renata:hypothesis-check (which measures after). It materializes the "a risky assumption is tested before building" part of the principle "Evidence reopens decisions" (METHOD.md › "The loop closes").
| Risk | Question | Who covers it in the method |
|---|---|---|
| Value | Do people want this? Does it solve a real pain? | /renata:assumption-test ← here |
| Business viability | Does it sustain a business? (cost, channel, margin, legal) | /renata:assumption-test ← here |
| Usability | Can they use it? | /renata:screens (partial) |
| Technical feasibility | Can it be built? | /renata:spike |
This command attacks the first two — the ones the framework did not cover and that enter the PRD as an untested assumption.
Use /renata:assumption-test for value/viability risk (before building).
Use /renata:spike for technical risk ("does it run?").
Use /renata:hypothesis-check to measure the hypothesis (after building).
@docs/prd/ — the hypotheses (each one and its falsification signal), IN scope, anchor persona.@docs/business-context/personas.md and jornada.md — the pain that justifies the value.@docs/features/README.md if it exists — which feature carries the value bet.Test the assumption with the highest product (risk × cost-of-being-wrong), not the easiest to test.
| Test | Which risk it kills | Cost | Signal |
|---|---|---|---|
| Problem interview (5-8 people) | Value (does the pain exist?) | XS | Do they describe the pain without you suggesting it? |
| Landing / fake door + traffic | Value (do they want the solution?) | S | Click/signup rate above floor |
| Wizard of Oz (manual delivery behind the scenes) | Value + usability | M | Do they use it again? Would they pay? |
| Pre-sale / letter of intent | Viability (do they pay?) | S-M | Real commitment (money/signature) |
| Unit economics analysis | Viability (does the margin work?) | S | CAC < LTV with room to spare |
| Concierge / pilot with 1 customer | Value + viability | M-L | Real result delivered manually |
/renata:spike. Keep the focus on do they want it? / do they pay?.Write to docs/assumptions/<YYYY-MM-DD>-<slug>.md (create the folder if it does not exist):
# Assumption Test · {{assumption}}
> **Date:** {{YYYY-MM-DD}}
> **Assumption tested:** {{statement the plan assumes as truth}}
> **Risk:** {{value | viability}}
> **If false:** {{how much of the plan collapses}} · **Cost of discovering late:** {{wasted effort}}
---
## Why this assumption (and not another)
{{application of the leverage rule: risk × cost-of-being-wrong}}
## Falsification signal (defined BEFOREHAND)
> The assumption is **FALSE** if {{concrete, measurable result}}.
## Chosen test
- **Method:** {{from the catalog}} · **Cost:** {{XS-L}} · **Window:** {{time}}
- **Sample / channel:** {{who, where}}
- **How it measures:** {{the number/signal that decides}}
## Result (filled in after running)
- **Evidence:** {{what actually happened}}
- **Verdict:** {{✅ assumption holds | ❌ assumption fell | 🤔 inconclusive}}
- **Decision:** {{proceed to build | reopen PRD/pivot | redesign feature | one more test}}
/renata:prd (refine/pivot) — the central hypothesis may be compromised even before Phase 0. Record it in the PRD History./renata:feature-spec / /renata:plan-phase./renata:todo 🟡 with a deadline.$ARGUMENTS: optional — the assumption to test (text) or context. With no argument, lists the PRD assumptions and helps choose the one with the highest leverage.
npx claudepluginhub ainsteinsbr/renata --plugin renata