agentleFS
Sign inStart free
yuusakuriyuusakuri/agent-skills/skills/identify-assumptions-new/SKILL.md

identify-assumptions-new

Skill2 starsChanged 10 days agoMITView on GitHub

Identify risky assumptions for a new product idea across 8 risk categories including Go-to-Market, Strategy, and Team. Use when evaluating startup risks, assessing a new product concept, or mapping assumptions for a new venture.

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    If the user provides files (business plans, research), read them first.

    line 14
  2. Distinctive:

    Ethics: Should we do it at all? Are there any ethical considerations?

    line 37

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Identify Assumptions (New Product)

Comprehensive risk identification across 8 categories — extending the 4 core product risks (Teresa Torres, Continuous Discovery Habits) with Ethics, Go-to-Market, Strategy & Objectives, and Team risks that are critical for new products.

Context

You are evaluating assumptions for a new product: $ARGUMENTS.

If the user provides files (business plans, research), read them first.

Domain Context

The 4 core product risks (Teresa Torres, Continuous Discovery Habits): Value, Usability, Viability, Feasibility.

For new products, extend to 8 risk categories. Good teams assume at least three-quarters of their ideas won't perform as they hope.

Instructions

The user will describe the product concept, target segment, and feature idea. Work through these steps:

  1. Think from three perspectives about why this product might fail:
    • Product Manager: Market demand, willingness to pay, competitive landscape
    • Designer: First-time user experience, onboarding, engagement
    • Engineer: Build vs. buy decisions, scalability, technical debt

  2. Identify assumptions across 8 risk categories:

    • Value: Will it create value for customers? Will they keep using it?
    • Usability: Will people figure out how to use it? Can we onboard them fast enough? Will it increase cognitive load?
    • Viability: Can we sell/monetize/finance it? Is it worth the cost? Can we support customers and help them succeed? Can we scale? Will it be compliant?
    • Feasibility: Can we do it with the current technology? Is this integration possible? Can it be efficient? Can we scale it?
    • Ethics: Should we do it at all? Are there any ethical considerations? Will it pose a risk for our customers?
    • Go-to-Market (especially critical for new products): Can we market it? Do we have the required channels? Can we convince customers to try it? Is this the right messaging for this channel? Is this the right time? Is this the right way to launch it?
    • Strategy & Objectives: What are our assumptions? Can others copy our strategy? Have we considered political, economic, legal, technological, and environmental factors? Are those the best problems to solve?
    • Team: How well will the team work together? Do we have the right people? Do we have the right tools? Will the entire team stay with us long enough?
  3. For each assumption, rate confidence and suggest a test.

Think step by step. Save as markdown.

Further Reading

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