decision-trees

What This Skill Does

The decision-trees skill provides a structured, quantitative framework for evaluating complex choices where outcomes are probabilistic. By utilizing decision tree analysis—a method that maps out potential actions, chance events, and final outcomes—this skill helps you calculate the Expected Value (EV) of various options. It allows you to move beyond gut feelings by assigning numerical utility and probability weights to your decisions, ensuring that you select the path with the highest mathematical likelihood of success.

Installation

To integrate this analytical capability into your OpenClaw environment, execute the following command in your terminal: clawhub install openclaw/skills/skills/evgyur/decision-trees

Use Cases

This skill is highly versatile and applies to any scenario where you must choose between multiple paths with uncertain results.

• Business Strategy: Evaluating whether to invest in a new product line, enter a new market, or choose between two competing vendors.
• Financial Planning: Assessing risk/reward scenarios for stock market positions, real estate investments, or budget allocations.
• Operations & Management: Deciding whether to outsource specific functions, expand infrastructure, or hire new personnel based on project failure or success probabilities.
• Personal Life: Choosing between career paths, determining if a major purchase is justified, or evaluating relocation options based on potential happiness and financial stability metrics.

Example Prompts

1. "Should I pivot our marketing strategy to focus on influencers, or stay with traditional PPC? Help me evaluate the risks and EV for both."
2. "I'm considering quitting my job to start a freelance business. Use a decision tree to compare the financial outcomes based on a 40% success rate."
3. "Evaluate the pros and cons of investing in this tech stock versus a safe bond fund. Use probability weighting for market volatility."

Tips & Limitations

To get the best out of this skill, ensure your probability estimates are as objective as possible. The primary limitation of decision tree analysis is that it relies heavily on the input data; if your assigned probabilities or values are biased or inaccurate, the resulting EV will be misleading. Furthermore, this skill is not suitable for 'Black Swan' events (unpredictable, high-impact occurrences) or decisions that require rapid, intuitive reaction times. It works best when you have sufficient data to estimate outcomes and want to structure a logical, defensible decision-making process.