Assumption mapping
Agentic personal OS to automate high-leverage workflows with Codex, Claude Code, Pi, OpenClaw and other coding agents/ runtime platforms.
npx -y skills add itseffi/agentic-os --skill assumption-mappingAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
What its author says it does
Copied from the file, not written here
Surface and categorize assumptions underlying product strategy. Use early in development to document what you're betting on.
SKILL.md
1.8 KB, as published. Nobody here has run it
Assumption Mapping
Generate and categorize assumptions underlying a product strategy.
When to Use
Early in product development to surface and document what you're betting on.
The Framework
Organize assumptions into four categories:
| Category | Focus | Example Questions |
|---|---|---|
| Desirability | Will users want this? | Problem severity, willingness to pay, switching triggers |
| Feasibility | Can we build it? | Technical risks, data needs, integrations, security |
| Viability | Will it make money? | Pricing, margins, retention, unit economics |
| Usability | Can users use it? | Task success, learnability, error tolerance |
The Process
1. Gather Inputs
Document:
- Product description
- Core problem being solved
- Target user
2. Generate Assumptions
For each category, create at least 5 assumptions:
Format:
- Statement: "We believe that [specific, falsifiable claim]"
- Impact if wrong: [concrete consequence]
Good example:
- Statement: "We believe that SMB admins will pay $20/user/month if onboarding drops below 30 minutes"
- Impact if wrong: Premium pricing underperforms due to insufficient WTP
3. Quality Check
Each assumption should be:
- Specific (include numbers, segments, timeframes)
- Testable (you could run an experiment)
- One idea per assumption (no compound claims)
Output
Four lists of 5+ assumptions each:
- Desirability assumptions
- Feasibility assumptions
- Viability assumptions
- Usability assumptions
Each with statement and impact if wrong.
When Not to Use
Do not use this skill when the request is unrelated, low-stakes, or better handled by a simpler direct response.