Use when starting a forecast to establish a statistical baseline (base rate) before analyzing specifics. Invoke when need to anchor predictions in historical reality, avoid "this time is different" bias, or establish outside view before inside view analysis. Use when user mentions base rates, reference classes, outside view, or starting a new prediction.
Establish statistical baselines by identifying historical reference classes before making predictions. Use when starting forecasts, encountering "this time is different" claims, or needing to anchor in base rates rather than narratives.
/plugin marketplace add lyndonkl/claude/plugin install lyndonkl-thinking-frameworks-skills@lyndonkl/claudeThis skill inherits all available tools. When active, it can use any tool Claude has access to.
resources/common-pitfalls.mdresources/outside-view-principles.mdresources/reference-class-selection.mdReference class forecasting is the practice of anchoring predictions in historical reality by identifying a class of similar past events and using their statistical frequency as a starting point. This is the "Outside View" - looking at what usually happens to things like this, before getting distracted by the specific details of "this case."
Core Principle: Assume this event is average until you have specific evidence proving otherwise.
Why It Matters:
Use this skill when:
Do NOT use when:
What would you like to do?
1. Find My Base Rate - Identify reference class and get statistical baseline
2. Test "This Time Is Different" - Challenge uniqueness claims
3. Calculate Funnel Base Rates - Multi-stage probability chains
4. Validate My Reference Class - Ensure you chose the right comparison set
5. Learn the Framework - Deep dive into methodology
6. Exit - Return to main forecasting workflow
Let's establish your statistical baseline.
Tell me the specific event or outcome you're predicting.
Example prompts:
I'll help you identify what bucket this belongs to.
Framework:
Key Questions:
I'll work with you to refine this until we have a specific, searchable class.
I'll help you find the base rate using:
Search Strategy:
"historical success rate of [reference class]"
"[reference class] failure statistics"
"[reference class] survival rate"
"what percentage of [reference class]"
Once we find the base rate, that becomes your starting probability.
The Rule:
You are NOT allowed to move from this base rate until you have specific, evidence-based reasons in your "inside view" analysis.
Default anchors if no data found:
Next: Return to menu or proceed to inside view analysis.
Challenge uniqueness bias.
When someone (including yourself) believes "this case is special," we need to stress-test that belief.
Question 1: Similarity Matching
Question 2: The Reversal Test
Question 3: Burden of Proof The base rate says [X]%. You claim it should be [Y]%.
Calculate the gap: |Y - X|
Required evidence strength:
I'll tell you:
Next: Return to menu
For multi-stage processes without a single base rate.
Example: "Will Bill X become law?"
No direct data on "Bill X success rate," but we can model the funnel:
Stage 1: Bills introduced → Bills that reach committee
Stage 2: Bills in committee → Bills that reach floor vote
Stage 3: Bills voted on → Bills that pass
Final Base Rate:
P(law) = P(committee) × P(floor) × P(pass)
I'll help you:
Next: Return to menu
Ensure you chose the right comparison set.
Test 1: Homogeneity
Example: "Tech startups" is too broad (consumer vs B2B vs hardware are very different). Subdivide.
Test 2: Sample Size
Test 3: Relevance
I'll walk you through:
Output: Confidence level in your reference class (High/Medium/Low)
Next: Return to menu
Deep dive into the methodology.
📄 Reference Class Selection Guide
Next: Return to menu
Find what usually happens to things like this, start there, and only move with evidence.
estimation-fermi if you need to calculate base rate from componentsbayesian-reasoning-calibration to update from base rate with new evidencescout-mindset-bias-check to validate you're not cherry-picking the reference class📁 resources/
Ready to start? Choose a number from the menu above.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.