\"Invert, always invert.\" Apply Carl Jacobi's mathematical principle and Charlie Munger's investing wisdom to solve problems by thinking backward from failure. Use when: **Goal setting** - Define what would guarantee failure, then avoid it; **Risk analysis** - Identify what could destroy your project before starting; **Decision making** - Evaluate choices by examining their worst outcomes; **Problem solving** - When direct approaches aren't working, reverse the question; **Strategy development...
npx skills add https://github.com/guia-matthieu/clawfu-skills --skill inversion
> "Invert, always invert." Apply Carl Jacobi's mathematical principle and Charlie Munger's investing wisdom to solve problems by thinking backward from failure.
| Aspect | Details |
|--------|---------|
| Source | Carl Gustav Jacob Jacobi (1804-1851), mathematician; Charlie Munger, investor |
| Expert | Munger credits Jacobi: "Invert, always invert" (from "man muss immer umkehren") |
| Core Principle | Many problems are best solved backward. Instead of asking "How do I succeed?", ask "What would guarantee failure?" then avoid those things. |
| Claude Does | You Decide |
|-------------|------------|
| Structures content frameworks | Final messaging |
| Suggests persuasion techniques | Brand voice |
| Creates draft variations | Version selection |
| Identifies optimization opportunities | Publication timing |
| Analyzes competitor approaches | Strategic direction |
Apply Inversion to this goal:
[describe your goal]
What would GUARANTEE failure? What should I avoid at all costs?
Use Inversion to evaluate this decision:
[describe the choice you're facing]
If I wanted this to fail spectacularly, what would I do?
Invert this strategy to find weaknesses:
[describe your plan]
How could a competitor or circumstances destroy this plan?
When applying Inversion, follow this systematic process:
## Forward Statement
**What I want to achieve:**
[Clear, specific goal]
**Current approach:**
[How I'm thinking about solving it]
**Why direct approach may be insufficient:**
[Complexity, uncertainty, blind spots]
## The Inversion
**Original Question:**
"How do I [achieve goal]?"
**Inverted Question:**
"How do I GUARANTEE [failure/opposite of goal]?"
**Reframe:**
Instead of: "How do I build a successful company?"
Ask: "How do I guarantee my company fails?"
Instead of: "How do I have a happy marriage?"
Ask: "How do I guarantee divorce?"
Instead of: "How do I get healthy?"
Ask: "How do I guarantee I stay unhealthy?"
Munger's Insight:
"It is remarkable how much long-term advantage people like us have gotten by trying to be consistently not stupid, instead of trying to be very intelligent."
## Failure Recipe
**If I wanted to GUARANTEE failure, I would:**
1. [Action/behavior that ensures failure]
2. [Action/behavior that ensures failure]
3. [Action/behavior that ensures failure]
4. [Action/behavior that ensures failure]
5. [Action/behavior that ensures failure]
**Attitudes that guarantee failure:**
-
-
-
**Decisions that guarantee failure:**
-
-
-
**Habits that guarantee failure:**
-
-
-
Be Thorough: Generate at least 10-15 failure paths. The most obvious ones come first, but the subtle ones are often more dangerous.
## Inversion to Success
| Guaranteed Failure | Therefore, I Must... |
|--------------------|---------------------|
| [Failure action 1] | [Avoid/do opposite] |
| [Failure action 2] | [Avoid/do opposite] |
| [Failure action 3] | [Avoid/do opposite] |
**Key Avoidances (Non-Negotiable):**
1. Never [failure behavior]
2. Never [failure behavior]
3. Never [failure behavior]
**Required Actions (Derived from Inversion):**
1. Always [opposite of failure]
2. Always [opposite of failure]
3. Always [opposite of failure]
## Anti-Goals
**Definition:** Things I commit to NEVER doing, regardless of circumstances.
### My Anti-Goals:
1. **I will NEVER:** [specific anti-goal]
**Because it guarantees:** [failure outcome]
2. **I will NEVER:** [specific anti-goal]
**Because it guarantees:** [failure outcome]
3. **I will NEVER:** [specific anti-goal]
**Because it guarantees:** [failure outcome]
### Tripwires (Early Warning Signs)
If I notice any of these, STOP and reassess:
- [Warning sign that I'm heading toward failure]
- [Warning sign that I'm heading toward failure]
- [Warning sign that I'm heading toward failure]
Context: Founder wants to build a successful startup.
Input:
> "I want to build a successful startup. Apply Inversion - what would guarantee failure?"
Output:
Forward Statement:
The Inversion:
"How do I GUARANTEE my startup fails?"
Failure Recipe - Top 15 Ways to Kill a Startup:
10. Obsess over competition - Copy instead of innovate
11. Poor communication with investors - Surprise them with bad news
12. Single point of failure - One key customer, one key employee, one key feature
13. Technical debt mountain - Ship fast forever, never refactor
14. Premature scaling - Spend on growth before product works
15. Founder burnout - Work 100-hour weeks indefinitely
Inversion to Success:
| Guaranteed Failure | Therefore, I Must... |
|--------------------|---------------------|
| Build without customer input | Talk to 50+ customers before building |
| Run out of money | Always maintain 18+ months runway |
| Co-founder misalignment | Have explicit co-founder agreement before starting |
| Ignore unit economics | Know CAC, LTV, payback from day 1 |
| Premature scaling | Only scale after clear product-market fit signals |
Anti-Goals for This Startup:
Why This Works: Instead of chasing "success tactics," we've identified the landmines. Avoiding these gives us a massive advantage over founders who hit them.
Context: Professional wants to advance their career over the next 5 years.
Input:
> "I want to advance my career. What would guarantee I stay stuck?"
Output:
The Inversion:
"How do I GUARANTEE career stagnation?"
Failure Recipe - 12 Ways to Kill Your Career:
10. Avoid difficult conversations - Let resentments build
11. Be the expert in a dying field - Double down on obsolete skills
12. Complain without solutions - Be known as the negative one
Inversion to Success:
| Guaranteed Stagnation | Therefore, I Must... |
|-----------------------|---------------------|
| Stop learning | Dedicate 5 hours/week to skill development |
| Avoid hard problems | Volunteer for one stretch assignment per year |
| Stay invisible | Publish/present at least quarterly |
| Rely on one sponsor | Cultivate 3-5 relationships with senior people |
| Ignore feedback | Actively seek and act on feedback monthly |
Anti-Goals for My Career:
Tripwires:
## Inversion Canvas: [Goal/Problem]
┌─────────────────────────────────────────────────────────────────┐
│ FORWARD VIEW │
│ │
│ GOAL: _________________________________________________ │
│ │
│ Current approach: ______________________________________ │
│ │
└─────────────────────────────────────────────────────────────────┘
│
▼
INVERT IT
│
▼
┌─────────────────────────────────────────────────────────────────┐
│ INVERTED VIEW │
│ │
│ "How do I GUARANTEE failure?" │
│ │
│ 1. ________________________________________________________ │
│ 2. ________________________________________________________ │
│ 3. ________________________________________________________ │
│ 4. ________________________________________________________ │
│ 5. ________________________________________________________ │
│ │
└─────────────────────────────────────────────────────────────────┘
│
▼
INVERT BACK
│
▼
┌─────────────────────────────────────────────────────────────────┐
│ ACTION VIEW │
│ │
│ ANTI-GOALS (Never do): │
│ 1. ________________________________________________________ │
│ 2. ________________________________________________________ │
│ 3. ________________________________________________________ │
│ │
│ MUST-DOS (Derived from inversion): │
│ 1. ________________________________________________________ │
│ 2. ________________________________________________________ │
│ 3. ________________________________________________________ │
│ │
└─────────────────────────────────────────────────────────────────┘
## Quick Inversion (5 Minutes)
**Goal:** ________________________
**Invert:** "How do I guarantee failure?"
□ ________________________________
□ ________________________________
□ ________________________________
**Therefore, I must AVOID:**
□ ________________________________
□ ________________________________
□ ________________________________
**One Anti-Goal to commit to:**
"I will NEVER ________________________________"
## Decision Inversion Template
**Decision:** Should I [option A] or [option B]?
### Invert Option A:
"If I choose A and it fails catastrophically, why?"
-
-
-
### Invert Option B:
"If I choose B and it fails catastrophically, why?"
-
-
-
### Comparison:
| Failure Mode | Option A Risk | Option B Risk |
|--------------|---------------|---------------|
| [Mode 1] | High/Med/Low | High/Med/Low |
| [Mode 2] | High/Med/Low | High/Med/Low |
| [Mode 3] | High/Med/Low | High/Med/Low |
**Insight from Inversion:**
[What did reverse thinking reveal?]
**Decision:**
[Which option has more avoidable failure modes?]
## Charlie Munger's Inversion Questions
Apply these to any goal or decision:
1. "What could cause this to fail completely?"
2. "What would a competitor do to destroy us?"
3. "What's the most likely way I'm wrong?"
4. "What would make me look back and say 'how did I miss that'?"
5. "If this failed, what would the post-mortem say?"
6. "What am I not seeing because I don't want to see it?"
7. "How would a smart, well-resourced enemy attack this?"
8. "What would I have to believe for this to fail?"
## You MUST Apply Inversion When:
- [ ] Stakes are high (career, money, relationships)
- [ ] Decision is irreversible or hard to reverse
- [ ] You're feeling overconfident
- [ ] Everyone agrees (groupthink risk)
- [ ] You haven't considered failure modes
- [ ] The plan seems "foolproof"
- [ ] You're emotionally attached to the outcome
## Warning: Inversion Reveals Uncomfortable Truths
Be prepared to discover:
- Plans you love have fatal flaws
- "Sure things" aren't sure at all
- You've been avoiding obvious risks
- The easy path leads to failure
name: inversion
category: strategy
subcategory: decision-making
version: 1.0
author: MKTG Skills
source_expert: Carl Jacobi, Charlie Munger
source_work: Poor Charlie's Almanack, Seeking Wisdom
difficulty: beginner
estimated_value: $1,500 strategy consultation
tags: [decision-making, risk-analysis, Munger, problem-solving, mental-models]
created: 2026-01-25
updated: 2026-01-25
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".
Take guia-matthieu/inversion 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.