agentleFS
jiayuewangjavyjiayuewangjavy/product-designer-skills-os/skills/opportunity-and-assumption-map/SKILL.md

opportunity-and-assumption-map

Skill4 starsChanged 20 days agoMITView on GitHub

Turn product evidence and an early idea into explicit opportunities, assumptions, and a prioritized evidence plan. Use when the user needs to choose what problem or risk to investigate next. Do not use to generate a solution backlog from unsupported claims.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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 invent interview findings, demand, willingness to pay, or technical feasibility.

    line 37
  2. Distinctive:

    Do not rank an assumption as low risk merely because it is difficult to test.

    line 38
  3. Distinctive:

    If the requested solution is already fixed, expose the assumption instead of silently reopening the decision.

    line 39

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Opportunity and Assumption Map

Identify the belief most likely to invalidate the current product bet.

Work from evidence

  1. Restate the user or buyer, situation, current alternative, desired outcome, and proposed product bet.
  2. Label inputs as Evidence, Inference, Assumption, Decision, or Preference. Preserve contradictions and missing provenance.
  3. Express opportunities as observable struggles or desired progress, not features.
  4. List assumptions across value, usability, feasibility, viability, adoption, and risk. Include only categories that can change the decision.
  5. Rank assumptions by consequence if wrong and weakness of current evidence. Do not use false numerical precision.
  6. Select one riskiest assumption and propose the smallest credible evidence probe.
  7. State what result would support, reject, or reframe the bet.

Output

## Current bet
## Evidence base and gaps
## Opportunities
## Assumption map
| Assumption | Type | Evidence | Consequence if wrong | Confidence |
## Riskiest assumption
## Smallest evidence probe
## Support / reject / reframe criteria
## Next unknown

Boundaries

  • Competitor behavior, stakeholder confidence, and market popularity are not customer evidence by themselves.
  • Do not invent interview findings, demand, willingness to pay, or technical feasibility.
  • Do not rank an assumption as low risk merely because it is difficult to test.
  • If the requested solution is already fixed, expose the assumption instead of silently reopening the decision.

The map is complete when the next evidence-gathering action is more specific than “do more research.”

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.