Murphyjitsu

CFAR rationality technique for bulletproofing plans by systematically imagining failure modes and creating defenses. Combines Murphy's Law with pre-mortem analysis. Use when the user: (1) has a plan they want to stress-test, (2) wants to identify what could go wrong before it does, (3) needs to build a more robust plan, (4) wants to practice pre-mortem thinking, or (5) is about to start a project and wants to anticipate obstacles. Triggers: "murphyjitsu", "what could go wrong", "pre-mortem", "stress test my plan", "inner simulator", "surprise-o-meter", "failure modes", "plan review", "CFAR".

5 stars 1 forksTesting & QA

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add EquiStamp/CFAR-Claude-Skills --skill murphyjitsu
Manual install
git clone --depth 1 https://github.com/EquiStamp/CFAR-Claude-Skills.git /tmp/CFAR-Claude-Skills
mkdir -p ~/.claude/skills
cp -r /tmp/CFAR-Claude-Skills/murphyjitsu ~/.claude/skills/murphyjitsu

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Murphyjitsu (Inner Simulator)

A CFAR technique for bulletproofing plans by deliberately imagining failure, identifying the most likely failure modes, and creating defenses. Named after Murphy's Law + martial arts ("jitsu").

## Three Modes

1. **Design Mode** — Help create a robust plan with failure modes already addressed
2. **Practice Mode** — Walk through the technique on a practice plan to build skill
3. **Execute Mode** — Stress-test a real plan the user is about to implement

## Core Algorithm

```
1. State a concrete plan
2. Imagine: "It's the day after. The plan failed. What happened?"
3. Check the surprise-o-meter
4. If genuinely shocked → done
5. Otherwise → identify the most likely failure mode
6. Create a defense against it
7. Go to step 2
```

## The Surprise-o-Meter

After imagining failure, assess how surprised you'd be:
- **"Yeah, sounds right"** → Keep iterating. You have known failure modes.
- **"Somewhat surprised"** → Getting close. Address remaining risks.
- **"Genuinely shocked"** → Your inner simulator endorses the plan. Stop here.

The technique continues until you'd be genuinely shocked to see the plan fail.

## Step-by-Step Facilitation

### 1. Articulate the Plan
"What's your concrete plan? What specific actions, in what order, by when?"
Ensure the plan is concrete enough to simulate. Vague goals can't be Murphyjitsued.

### 2. Initial Simulation
"Imagine you've executed this plan and suddenly realize it failed. Oh no — why? What happened?"
Read the full skill on GitHub

Details

Skill name
murphyjitsu
Path
murphyjitsu/SKILL.md
Repo updated
5 February 2026

FAQ

What does the Murphyjitsu skill do?

CFAR rationality technique for bulletproofing plans by systematically imagining failure modes and creating defenses. Combines Murphy's Law with pre-mortem analysis. Use when the user: (1) has a plan they want to stress-test, (2) wants to identify what could go wrong before it does, (3) needs to build a more robust plan, (4) wants to practice pre-mortem thinking, or (5) is about to start a project and wants to anticipate obstacles. Triggers: "murphyjitsu", "what could go wrong", "pre-mortem", "stress test my plan", "inner simulator", "surprise-o-meter", "failure modes", "plan review", "CFAR".

How do I install the Murphyjitsu skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add EquiStamp/CFAR-Claude-Skills --skill murphyjitsu. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Murphyjitsu popular?

It lives in EquiStamp/CFAR-Claude-Skills, which has 5 GitHub stars and 1 forks.

Related skills

Aversion Factoring

5

EquiStamp/CFAR-Claude-Skills

CFAR rationality technique for decomposing aversions into specific addressable components using the LEGO brick model. Use when the user: (1) avoids something they believe they should do, (2) says "I hate doing X" and wants to understand why, (3) wants to overcome a specific aversion, (4) practice decomposing emotional resistance, or (5) wants to understand the gap between what they want to want and what they actually want. Triggers: "aversion factoring", "I hate", "I avoid", "I can't make myself", "why do I resist", "overcome aversion", "ugh field", "CFAR", "decompose aversion".

Frontend & Design

Bucket Errors

5

EquiStamp/CFAR-Claude-Skills

CFAR rationality technique for identifying where you've entangled questions that should be separate, causing you to flinch away from evidence. Use when the user: (1) feels defensive about acknowledging something true, (2) conflates unrelated beliefs ("Am I a good writer?" with "Did I spell this correctly?"), (3) has trouble accepting feedback, (4) wants to practice detecting question substitution, or (5) notices they avoid thinking about certain topics. Related to Kahneman's attribute substitution. Triggers: "bucket error", "conflating", "flinching away", "defensive about", "question substitut

Writing & Content

Double Crux

5

EquiStamp/CFAR-Claude-Skills

CFAR rationality technique for resolving disagreements by finding shared underlying belief divergence points (cruxes). Use when the user wants to: (1) resolve a disagreement by finding the real point of contention, (2) prepare for a difficult conversation by mapping belief structure, (3) practice collaborative truth-seeking, (4) examine beliefs by finding what would change their mind, or (5) facilitate a structured disagreement between two positions. Triggers: "double crux", "disagree", "what would change my mind", "crux", "resolve disagreement", "find the real issue", "belief examination", "C

Other

Testing

9

jscraik/Agent-Skills

Validate and choose proportionate test proof for tests, CI, coverage, evals, and closeout evidence: map changed files to repo-native commands, place checks at commit, push, and pull-request gates, classify pass/fail/blocked ownership, and preserve trace/regression artifacts. Use when users ask what tests or gates to run, how to design coverage, why validation failed, or what proof supports a claim.

Testing & QA

Azure Microsoft Playwright Testing Ts

9

huytran1120/vietnam-agentic-skills

Run Playwright tests at scale with cloud-hosted browsers and integrated Azure portal reporting.

Testing & QA

Pilot Event Replay

9

TeoSlayer/pilot-skills

Record and replay event streams for debugging, testing, and audit purposes. Use this skill when: 1. You need to capture event streams for later analysis 2. You need to replay events to test downstream consumers 3. You need to debug event-driven workflows 4. You need to audit event history with timestamps Do NOT use this skill when: - You need real-time event forwarding (use pilot-event-bus instead) - You need long-term storage with rotation (use pilot-event-log instead) - You need filtering before recording (use pilot-event-filter first)

Testing & QA

Browse the most popular Claude skills, all testing & qa skills, or write your own with the skills generator.