agentleFS
DrifterXXXDrifterXXX/auto-company/.claude/skills/premortem/SKILL.md

premortem

Skill0 starsChanged 5 months agoMITView on GitHub

Pre-mortem analysis that imagines a plan has failed, then works backward to identify causes and preventions. Use before launches, major decisions, or risky initiatives to surface hidden risks.

46 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use agent-context-isolation.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 34 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    After this analysis, how confident are you in success?

    line 56
  2. Distinctive:

    Don't filter for "that won't happen"—the point is to surface hidden concerns

    line 62
  3. Distinctive:

    Look for single points of failure

    line 64

“Common” is measured: kept by at least 6 in 10 of the 34 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Pre-Mortem Analysis

Imagine the plan has completely failed, then work backward to identify what went wrong and how to prevent it.

Instructions

Set the scene: "It's [timeframe] in the future. This initiative was a complete disaster. Looking back, what happened?"

Generate failure scenarios without filtering for likelihood—get everything on the table first, then prioritize.

Output Format

The Plan Summarize what's being attempted and the success criteria.

Time Jump "It's [X months] later. This has failed completely. The outcome: [describe the disaster vividly]."

What Went Wrong

Generate 8-12 plausible failure causes across categories:

CategoryFailure ModeHow It Played Out
Execution[What failed][The story of how]
External[What failed][The story of how]
People[What failed][The story of how]
Technical[What failed][The story of how]
Assumptions[What failed][The story of how]

Risk Prioritization

Failure ModeLikelihoodImpactPriority
...High/Med/LowHigh/Med/Low1-5

Top 3 Risks & Mitigations

For each top risk:

  • Risk: [Description]
  • Early Warning Signs: What would indicate this is happening?
  • Prevention: How to reduce likelihood
  • Mitigation: How to reduce impact if it occurs
  • Owner: Who's responsible for watching this?

Pre-Mortem Insights What did this exercise reveal that wasn't obvious before?

Revised Confidence After this analysis, how confident are you in success? What would increase confidence?

Guidelines

  • Be vivid and specific—"the database corrupted" not "something went wrong"
  • Include uncomfortable possibilities (key person leaves, competitor moves, we were wrong)
  • Don't filter for "that won't happen"—the point is to surface hidden concerns
  • Assign real owners to mitigations
  • Look for single points of failure

$ARGUMENTS

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.