Agent skill · Databases

premortem-assassin

Kill the plan on paper before reality does it for money. Use when a plan, launch, migration, or strategy is about to be committed to and nobody has tried hard to murder it yet — the assassin attacks through twelve named failure vectors and writes the post-mortem of the failure that hasn't happened. Produces a premortem: the death narrative, the twelve-vector attack with survival verdicts, the three kill-shots most likely to land, and the cheap tripwires that would give early warning.

mohitagw15856github.com/mohitagw15856GitHub ↗
claude-codecursorMIT
Install
npx skills add mohitagw15856/pm-claude-skills --skill premortem-assassin --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 4 KB
Bundled scripts: none
Path: skills/premortem-assassin/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 1,255
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Premortem Assassin A premortem inverts the postmortem: assume the plan is already dead, then explain how it died. Most teams do this politely and learn nothing. The assassin does it professionally — every plan gets attacked through the same twelve vectors, so the blind spot the team shares cannot protect itself. ## Required Inputs - **The plan** — the actual document, not a summary. The assassin attacks what's written, and what's *missing* from what's written. - **The success definition** — what "it worked" means, with a number and a date. Without it, the assassin first shows that the plan can't fail *visibly*, which is its own kill-shot. - Optional: constraints already known (budget ceiling, headcount, hard deadline) and the political context (who wants this to fail). ## The Twelve Vectors Attack through every one; report survival honestly (a plan that "fails" all twelve was attacked lazily): 1. **The dependency that lies** — the external team/vendor/API whose "yes" was optimistic 2. **The estimate that compounds** — the task whose overrun cascades 3. **The silent stakeholder** — approved it, never bought it, kills it at week 9 4. **The demand mirage** — the interest that was po

What's inside
Steps it walks through
  1. Required Inputs
  2. The Twelve Vectors
  3. Output Format
  4. Quality Checks
  5. Anti-Patterns
More from pm-claude-skills
All skills →
About this skill
What does the premortem-assassin skill do?

Kill the plan on paper before reality does it for money. Use when a plan, launch, migration, or strategy is about to be committed to and nobody has tried hard to murder it yet — the assassin attacks through twelve named failure vectors and writes the post-mortem of the failure that hasn't happened. Produces a premortem: the death narrative, the twelve-vector attack with survival verdicts, the three kill-shots most likely to land, and the cheap tripwires that would give early warning.

How do I install it?

Run `npx skills add mohitagw15856/pm-claude-skills --skill premortem-assassin --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From mohitagw15856/pm-claude-skills, a repository with 1,255 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going