agentleFS
Sign inStart free
itseffiitseffi/agentic-os/.agents/skills/assumption-mapping/SKILL.md

assumption-mapping

Skill114 starsChanged 10 months agoMITView on GitHub

Surface and categorize assumptions underlying product strategy. Use early in development to document what you're betting on.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not use this skill when the request is unrelated, low-stakes, or better handled by a simpler direct response.

    line 65

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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:

CategoryFocusExample Questions
DesirabilityWill users want this?Problem severity, willingness to pay, switching triggers
FeasibilityCan we build it?Technical risks, data needs, integrations, security
ViabilityWill it make money?Pricing, margins, retention, unit economics
UsabilityCan 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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free