Pre Mortem

Before starting ANY significant task (feature build, refactor, integration, migration, or architectural change), first imagine the project has failed. Generate 3-5 specific failure scenarios, assess risk levels, identify mitigations, then adjust the implementation plan to address high-risk items FIRST. Do not start coding until the pre-mortem is acknowledged.

62 stars 2 forksSoftware Development

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add ElliotJLT/Claude-Skill-Potions --skill pre-mortem
Manual install
git clone --depth 1 https://github.com/ElliotJLT/Claude-Skill-Potions.git /tmp/Claude-Skill-Potions
mkdir -p ~/.claude/skills
cp -r /tmp/Claude-Skill-Potions/skills/pre-mortem ~/.claude/skills/pre-mortem

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

From the SKILL.md

# Pre-mortem

<purpose>
Elite engineers instinctively ask "how could this fail?" before writing code.
Claude does the opposite - jumps to implementation, discovers problems mid-way,
patches reactively. This skill encodes prospective hindsight: imagine failure,
then prevent it.
</purpose>

## Why This Works

Gary Klein's research on prospective hindsight shows teams who imagine failure
identify 30% more risks than teams who just "plan carefully." The mental shift
from "how do we succeed?" to "why did we fail?" unlocks different thinking.

## Instructions

<trigger>
Activate before ANY task involving:
- New feature implementation
- External service integration (payments, auth, APIs)
- Database migrations or schema changes
- Refactoring across multiple files
- Dependency upgrades
- Infrastructure changes
- Anything the user calls "significant" or "important"
</trigger>

### Step 1: Pause Before Implementing

Do NOT start writing code. First, run analysis:

```bash
python scripts/analyse_risk.py --task "<task description>" --path .
```

Or manually assess by examining:
- Files that will be touched
- External dependencies involved
- Data/state that could be corrupted
- User-facing impact if broken

### Step 2: Generate Failure Scenarios

Imagine it's 2 weeks later. The task failed. Ask: **"Why did it fail?"**

Generate 3-5 specific failure scenarios. For each:

| Component | Description |
|-----------|-------------|
| Scenario | Concrete failure description |
Read the full skill on GitHub

Details

Skill name
pre-mortem
Path
skills/pre-mortem/SKILL.md
License
MIT
Repo updated
12 February 2026

FAQ

What does the Pre Mortem skill do?

Before starting ANY significant task (feature build, refactor, integration, migration, or architectural change), first imagine the project has failed. Generate 3-5 specific failure scenarios, assess risk levels, identify mitigations, then adjust the implementation plan to address high-risk items FIRST. Do not start coding until the pre-mortem is acknowledged.

How do I install the Pre Mortem skill?

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

Is Pre Mortem popular?

It lives in ElliotJLT/Claude-Skill-Potions, which has 62 GitHub stars and 2 forks.

Related skills

Agent Audit

62

ElliotJLT/Claude-Skill-Potions

When reviewing, optimizing, or inheriting an LLM agent, systematically identify what's actually load-bearing vs. cruft. Instruments usage, ablates components, and strips the agent to minimum viable form. Answers: "What can we remove without degrading quality?" The goal is the leanest agent that still works.

AI, LLMs & Agents

Battle Plan

62

ElliotJLT/Claude-Skill-Potions

Before ANY significant development task (new feature, refactor, integration, migration), run a complete planning ritual by orchestrating other skills in sequence: rubber-duck (clarify scope) -> pre-mortem (assess risks) -> eta (estimate time) -> final confirmation. Do not start coding until the battle plan is approved.

Software Development

Breadcrumbs

62

ElliotJLT/Claude-Skill-Potions

Leaves notes for future Claude sessions in .claude/breadcrumbs.md. At session end or after significant work, records what was tried, what worked, what failed, and context for next time. On session start, reads breadcrumbs to understand history. Session-to-session memory without manual updates.

Productivity & Notes

Reducing Complexity

43

obra/clank

Managing complexity is software's primary technical imperative - all other goals are secondary

Software Development26

Pair Mode

62

ElliotJLT/Claude-Skill-Potions

When activated, Claude becomes a pair programming partner rather than a code-generation tool. Explains reasoning, teaches patterns, asks questions that build understanding, and adjusts depth based on the person's goals. Balances getting work done with building lasting knowledge. Activate with "let's pair on this" or by setting a learning focus at session start.

Software Development

Refactoring Safely

43

obra/clank

Refactor with tests first, one change at a time, never mix refactoring with bug fixes or new features

Software Development26

Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.