Pre Mortem Agent Skill
Run a pre-mortem risk analysis on a PRD or launch plan. Categorizes risks as Tigers (real problems), Paper Tigers (overblown concerns), and Elephants (unspoken worries), then classifies as launch-blocking, fast-follow, or track. Use when preparing for launch, stress-testing a product plan, or identifying what could go wrong.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/phuryn/pm-skills --skill pre-mortemThe instruction itself
6 sections, as written by the authorPre-Mortem: Risk Analysis for Product Launch
Purpose
You are a veteran product manager conducting a pre-mortem analysis on $ARGUMENTS. This skill imagines launch failure and works backward to identify real risks, distinguish them from perceived worries, and create action plans to mitigate launch-blocking issues.
Context
A pre-mortem is a structured risk-identification exercise that forces teams to think critically about what could go wrong before launch, when there's still time to act. By assuming failure, we surface hidden concerns and separate legitimate threats from overblown worries.
Instructions
- Gather the PRD: If the user provides a PRD or product plan file, read it thoroughly. Understand the product, target market, key assumptions, and timeline. If relevant, use web search to research competitive landscape or market conditions.
- Think Step by Step:
- Imagine the product launches in 14 days
- Now imagine it fails—customers don't adopt it, revenue targets miss, reputation takes a hit
- What went wrong?
- What did we miss or not execute well?
- What were we overconfident about?
- Categorize Risks: Classify each potential failure as one of three types:
Tigers: Real problems you personally see that could derail the project
- Based on evidence, past experience, or clear logic
- Should keep you awake at night
- Require action
Paper Tigers: Problems others might worry about, but you don't believe in them
- Valid concerns on the surface, but unlikely or overblown
- Not worth significant resource investment
- Worth documenting to align stakeholders
Elephants: Something you're not sure is a problem, but the team isn't discussing it enough
- Unspoken concerns or assumptions nobody is validating
- Could be real; you're unsure
- Deserve investigation before launch
- Classify Tigers by Urgency:
Launch-Blocking: Must be solved before launch
- Example: Core feature broken, regulatory blocker, key customer dependency unmet
Fast-Follow: Must be solved within 30 days post-launch
- Example: Performance issues, secondary features incomplete
Track: Monitor post-launch; solve if it becomes an issue
- Example: Nice-to-have features, edge cases
- Create Action Plans: For every Launch-Blocking Tiger:
- Describe the risk clearly
- Suggest a concrete mitigation action
- Identify the best owner (function/person)
- Set a decision/completion date
- Structure Output: Present the analysis as:
## Pre-Mortem Analysis: [Product Name]
### Tigers (Real Risks)
[List each real risk with category and mitigation plan]
### Paper Tigers (Overblown Concerns)
[List each, explain why it's not a true risk]
### Elephants (Unspoken Worries)
[List each, recommend investigation approach]
### Action Plans for Launch-Blocking Tigers
[For each, include: Risk, Mitigation, Owner, Due Date]
- Save the Output: Save as a markdown document:
PreMortem-[product-name]-[date].md
Notes
- Be honest and constructive—the goal is to improve launch readiness, not assign blame
- Default to "Tiger" if unsure; it's better to address risks early
- Involve cross-functional perspectives (engineering, design, go-to-market) in your analysis
- Revisit the pre-mortem 2-3 weeks before launch to verify mitigations are on track
Further Reading
Other skills for the same job
different authors, same section of the catalogue
Automated LLM-driven hypothesis generation and testing on tabular datasets. Use when you want to systematically explore hypotheses about patterns in empirical data (e.g., deception detection, content analysis). Combines literature insights with data-driven hypothesis testing. For manual hypothesis formulation use hypothesis-generation; for creative ideation use scientific-brainstorming.
Statistical analysis toolkit. Hypothesis tests (t-test, ANOVA, chi-square), regression, correlation, Bayesian stats, power analysis, assumption checks, APA reporting, for academic research.
Automated hypothesis generation and testing using large language models. Use this skill when generating scientific hypotheses from datasets, combining literature insights with empirical data, testing hypotheses against observational data, or conducting systematic hypothesis exploration for research discovery in domains like deception detection, AI content detection, mental health analysis, or other empirical research tasks.
Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows
UX research and design toolkit for Senior UX Designer/Researcher including data-driven persona generation, journey mapping, usability testing frameworks, and research synthesis. Use for user research, persona creation, journey mapping, and design validation.
Guided statistical analysis for research data - test selection, assumption checking, effect sizes, power analysis, Bayesian alternatives, and APA-formatted reporting. Use whenever a user wants to compare groups, test a hypothesis, analyze experimental or survey data, check statistical assumptions, compute required sample sizes, or write up results - even if they never name a specific test. Covers t-tests, ANOVA, chi-square, correlation, regression, non-parametric and Bayesian methods. For low-level model APIs, see the statsmodels and pymc skills.
> Jurisdiction-aware wage/hour and employment Q&A — classification, overtime, meal/rest breaks, leave, final pay — answered for the specific state/country with the controlling rule researched and cited rather than stated from memory. Use when the user asks any employment law question, or says "what's the rule in [state]", "is this exempt", "do we have to pay overtime for", or "can we classify this as".
> Deep-dive audit using the full testsmells.org 19-smell academic catalog for tests in any language. Every finding maps to a named, citable smell from the research literature (Assertion Roulette, Duplicate Assert, Mystery Guest, Eager Test, Sensitive Equality, Conditional Test Logic, Sleepy Test, Magic Number Test, etc.) with research-backed severity. (RSpec/Minitest), Rust, Swift, Kotlin (JUnit/Kotest), PowerShell (Pester), C++ (GoogleTest/Catch2). INVOKE ONLY when explicitly asked for the testsmells.org 19-smell academic catalog or citable smell names from the literature. writing new tests (use code-testing-agent, or writing-mstest-tests for MSTest); running tests (use run-tests); framework migration.
How to use it
Take phuryn/pre-mortem 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.