Decision Frameworks Skill for Claude
Structures difficult decisions using Annie Duke's probabilistic thinking and Ben Horowitz's hard decisions frameworks. Use when facing tough choices, applying expected value thinking, or reducing decision paralysis with regret minimization and pre-mortems.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/menkesu/awesome-pm-skills --skill decision-frameworksThe instruction itself
10 sections, as written by the authorDecision Architecture
When This Skill Activates
Claude uses this skill when:
- Facing difficult product decisions
- Choosing between multiple options
- Reducing decision paralysis
- Evaluating tradeoffs
Core Frameworks
1. Expected Value Thinking (Source: Annie Duke)
The Formula:
Expected Value = (Probability of Success × Value if Successful)
- (Probability of Failure × Cost if Fails)
Example:
Decision: Build feature A or B?
Feature A:
- 70% chance of +$100K revenue = $70K
- 30% chance of -$20K cost = -$6K
- Expected value: +$64K
Feature B:
- 30% chance of +$500K revenue = $150K
- 70% chance of -$50K cost = -$35K
- Expected value: +$115K
Choose B (higher EV despite lower probability)
2. Regret Minimization (Source: Jeff Bezos)
The Question:
> "When I'm 80 years old, will I regret not trying this?"
Framework:
- Imagine yourself in the future
- Work backwards
- Minimize long-term regret
Action Templates
Template: Decision Matrix
# Decision: [Choice A vs Choice B]
## Expected Value
### Option A
- Success probability: [X]%
- Success value: [$Y]
- Failure probability: [Z]%
- Failure cost: [$W]
- **Expected value:** [$EV]
### Option B
- Success probability: [X]%
- Success value: [$Y]
- Failure probability: [Z]%
- Failure cost: [$W]
- **Expected value:** [$EV]
## Regret Minimization
- If I choose A, will I regret not trying B?
- If I choose B, will I regret not trying A?
## Reversibility
- Can we reverse this? [Yes/No]
- Cost to reverse: [Low/Medium/High]
## Decision: [Option] because [reasoning]
Quick Reference
🎲 Decision Checklist
Analysis:
- [ ] Expected value calculated
- [ ] Regret minimization applied
- [ ] Reversibility assessed
- [ ] Pre-mortem completed
Decision:
- [ ] Choice made
- [ ] Reasoning documented
- [ ] Success criteria defined
Key Quotes
Annie Duke:
> "Life is poker, not chess. We're making decisions with incomplete information."
Jeff Bezos:
> "Most decisions should probably be made with somewhere around 70% of the information you wish you had."
Other skills for the same job
different authors, same section of the catalogue
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.
Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.). Saves hours of brainstorming and manual checking.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.
Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
How to use it
Take menkesu/decision-frameworks from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.