Skip to content
SkillModel-led899 tokens in use

pre-mortem

Imagine the launch failed, sort the risks into Tigers, Paper Tigers and Elephants, and plan fixes for what blocks launch.

28,201 stars on the repository MIT Licensephuryn/pm-skills · pm-execution/skills/pre-mortem
claude plugin install pm-execution@pm-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing pre-mortem costs

77tokens idle
899tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter12/15
  • Structure23/25
  • Examples9/15
  • Output15/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity80
  • Maintenance76
  • Community60
  • Maturity32
  • Momentum40

pre-mortem runs a risk analysis on a PRD or launch plan by assuming the product launches in 14 days and then fails. It works backward to what went wrong and sorts each risk into one of three types: Tigers are real problems, Paper Tigers are overblown worries and Elephants are concerns the team is not discussing.

Tigers are then classed as launch-blocking, fast-follow within 30 days, or track, and every launch-blocking Tiger gets a mitigation, an owner and a due date.

What You Get

  • A Tigers list with a category and mitigation plan for each real risk
  • A Paper Tigers list that explains why each concern is not a true risk
  • An Elephants list with a suggested way to investigate each one
  • An action plan table for launch-blocking Tigers with risk, mitigation, owner and due date
  • A markdown file named PreMortem-[product-name]-[date].md

Common Use Cases

  • Stress-testing a PRD two weeks before launch
  • Aligning stakeholders on which worries deserve resources
  • Surfacing unspoken concerns before a go or no-go decision

What Makes It Unique

It adds the Elephant category for risks the team is quietly avoiding, and it separates Tigers by urgency so only launch-blocking items demand an owner and a date. It also points to the live-qa skill as a way to collect risks anonymously from the team.

Under The Hood

The skill is one SKILL.md of instructions with no scripts. The agent reads the PRD or plan file you provide and may use web search to research the competitive landscape or market conditions. It saves the analysis as a markdown file in your working folder.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers