Decision Bias Review
Get the decision from the user. If they haven't described it, ask:
"What decision are you about to make? Tell me the options you're
considering and which way you're leaning."
Understand the stakes: Is this reversible? High or low impact?
What's the timeline?
Analyze the decision for bias vulnerabilities:
Sunk cost check: Are past investments influencing this more
than they should? Would you make the same choice starting fresh?Confirmation check: What evidence supports the preferred option?
What evidence against it has been dismissed or minimized?Availability check: Are recent or vivid examples
disproportionately influencing the assessment?Social pressure check: How much does what others think or do
affect this decision? Would you decide differently in private?Overconfidence check: How certain is the expected outcome?
What's the track record on similar predictions?Status quo check: Is staying the course getting unfair advantage
just because it's the current state?
Present a decision-focused analysis:
Decision Bias Review
The Decision
[Summarize the choice and current leaning]
Bias Risk Assessment
High Risk:
[Biases that appear to be significantly affecting this decision]
Watch For:
[Biases that could be at play but aren't clearly evident]
Seems Clear:
[Areas where the reasoning appears balanced]
Debiasing Questions
Before finalizing this decision, consider:
- [Question to counteract the most significant bias]
- [Additional question if warranted]
- [Third question if needed]
What Would Change Your Mind?
[Specific evidence or events that should trigger reconsideration]
Frame recommendations as helpful prompts for reflection, not
mandates to decide differently.
To run this task you must have the following required information:
> A pending decision or choice the user is about to make
If you don't have all of this information, exit here and respond asking for any extra information you require, and instructions to run this task again with ALL required information.
---
You MUST use a todo list to complete these steps in order. Never move on to one step if you haven't completed the previous step. If you have multiple read steps in a row, read them all at once (in parallel).
Add all steps to your todo list now and begin executing.
## Steps
1. [Read Bias Detection Framework]: Read the documentation in: `skills/sauna/[skill_id]/references/analysis.bias.framework.md`
2. Get the decision from the user. If they haven't described it, ask:
"What decision are you about to make? Tell me the options you're
considering and which way you're leaning."
Understand the stakes: Is this reversible? High or low impact?
What's the timeline?
3. Analyze the decision for bias vulnerabilities:
1. **Sunk cost check:** Are past investments influencing this more
than they should? Would you make the same choice starting fresh?
2. **Confirmation check:** What evidence supports the preferred option?
What evidence against it has been dismissed or minimized?
3. **Availability check:** Are recent or vivid examples
disproportionately influencing the assessment?
4. **Social pressure check:** How much does what others think or do
affect this decision? Would you decide differently in private?
5. **Overconfidence check:** How certain is the expected outcome?
What's the track record on similar predictions?
6. **Status quo check:** Is staying the course getting unfair advantage
just because it's the current state?
4. Present a decision-focused analysis:
## Decision Bias Review
### The Decision
[Summarize the choice and current leaning]
### Bias Risk Assessment
**High Risk:**
[Biases that appear to be significantly affecting this decision]
**Watch For:**
[Biases that could be at play but aren't clearly evident]
**Seems Clear:**
[Areas where the reasoning appears balanced]
### Debiasing Questions
Before finalizing this decision, consider:
1. [Question to counteract the most significant bias]
2. [Additional question if warranted]
3. [Third question if needed]
### What Would Change Your Mind?
[Specific evidence or events that should trigger reconsideration]
Frame recommendations as helpful prompts for reflection, not
mandates to decide differently.