How do I install the Pre Mortem skill?

Run npx skillmds@latest add broomva/pre-mortem in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Pre Mortem safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Pre Mortem?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Pre Mortem free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Pre Mortem?

broomva (@broomva) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Pre Mortem by broomva — Agent Skill

Name: Pre Mortem
Author: broomva

Pre Mortem

Assumes a project has already failed, works backward to identify the top causes, scores them by likelihood and impact, and outputs a mitigation plan. Use when starting a new project, before a major launch, evaluating risky decisions, or when the user says "pre-mortem", "what could go wrong", "risk analysis", "failure modes", "red team this plan".

broomva cdfe8ad 2.6 KB Updated Sep 17, 2026

File contents

Pre-Mortem

Assume the project has already failed. Work backward to find out why.

Workflow

Gather context — Read the project description, plan, or doc the user provides. If a vault path is given, read it. If the user describes the project verbally, capture the key facts.
Generate failure scenarios — Imagine it is 6 months from now and the project has failed catastrophically. Generate 8-12 distinct failure causes across these categories:
- Technical — architecture gaps, scaling limits, dependency risks, security holes
- Execution — timeline, staffing, skill gaps, coordination failures
- Market/External — competition, regulation, user adoption, economic shifts
- Organizational — stakeholder alignment, funding, priority shifts, team morale
Score each cause — For each failure cause, assign:
- Likelihood (1-5): How probable is this failure mode?
- Impact (1-5): If it happens, how severe is the damage?
- Risk Score = Likelihood × Impact (1-25)
Rank and filter — Sort by risk score descending. Present the top 5-8.
Mitigation plan — For each top risk, provide:
- Early warning signal — What would you see first if this is happening?
- Mitigation action — Concrete step to reduce likelihood or impact
- Owner suggestion — Who should own this mitigation?
- Deadline heuristic — When should this be addressed relative to project timeline?

Output Format

## Pre-Mortem: [Project Name]

**Scenario**: It is [date + 6 months]. The project has failed.

### Top Risks

| # | Cause | Category | Likelihood | Impact | Risk | Early Warning |
|---|-------|----------|-----------|--------|------|---------------|
| 1 | ... | Technical | 4 | 5 | 20 | ... |

### Mitigation Plan

#### Risk 1: [Cause]
- **Signal**: ...
- **Action**: ...
- **Owner**: ...
- **By**: ...

Vault Integration

If the user has an Obsidian vault, save the output to: vault/decisions/pre-mortem-[project]-[YYYY-MM-DD].md

Add frontmatter:

---
type: pre-mortem
project: [name]
date: [YYYY-MM-DD]
top_risk_score: [highest score]
tags: [pre-mortem, risk, project-name]
---

---name: pre-mortemdescription: Assumes a project has already failed, works backward to identify the top causes, scores them by likelihood and impact, and outputs a mitigation plan. Use when starting a new project, before a major launch, evaluating risky decisions, or when the user says "pre-mortem", "what could go wrong", "risk analysis", "failure modes", "red team this plan".---# Pre-MortemAssume the project has already failed. Work backward to find out why.## Workflow1. **Gather context** — Read the project description, plan, or doc the user provides. If a vault path is given, read it. If the user describes the project verbally, capture the key facts.2. **Generate failure scenarios** — Imagine it is 6 months from now and the project has failed catastrophically. Generate 8-12 distinct failure causes across these categories: - **Technical** — architecture gaps, scaling limits, dependency risks, security holes - **Execution** — timeline, staffing, skill gaps, coordination failures - **Market/External** — competition, regulation, user adoption, economic shifts - **Organizational** — stakeholder alignment, funding, priority shifts, team morale3. **Score each cause** — For each failure cause, assign: - **Likelihood** (1-5): How probable is this failure mode? - **Impact** (1-5): If it happens, how severe is the damage? - **Risk Score** = Likelihood × Impact (1-25)4. **Rank and filter** — Sort by risk score descending. Present the top 5-8.5. **Mitigation plan** — For each top risk, provide: - **Early warning signal** — What would you see first if this is happening? - **Mitigation action** — Concrete step to reduce likelihood or impact - **Owner suggestion** — Who should own this mitigation? - **Deadline heuristic** — When should this be addressed relative to project timeline?## Output Format```markdown## Pre-Mortem: [Project Name]**Scenario**: It is [date + 6 months]. The project has failed.### Top Risks| # | Cause | Category | Likelihood | Impact | Risk | Early Warning ||---|-------|----------|-----------|--------|------|---------------|| 1 | ... | Technical | 4 | 5 | 20 | ... |### Mitigation Plan#### Risk 1: [Cause]- **Signal**: ...- **Action**: ...- **Owner**: ...- **By**: ...```## Vault IntegrationIf the user has an Obsidian vault, save the output to:`vault/decisions/pre-mortem-[project]-[YYYY-MM-DD].md`Add frontmatter:```yaml---type: pre-mortemproject: [name]date: [YYYY-MM-DD]top_risk_score: [highest score]tags: [pre-mortem, risk, project-name]---```

Frequently asked questions