A premortem is a powerful way to find problems before they happen. It asks teams to imagine a project has failed and then figure out why. This method helps spot hidden risks in plans, code, or designs.
You can run a quick analysis for pull requests or a deep one before starting a big implementation. The skill uses a simple framework with labels like Tiger for real threats and Paper Tiger for things that only look risky. Every potential risk must be carefully checked before flagging it.
To use the skill, just type /premortem in your chat. The agent will detect the context and ask about depth. It then provides a structured checklist to verify each concern. This reduces false alarms and focuses on the most important issues.
Global
mkdir -p ~/.claude/skills/premortemProject
mkdir -p .claude/skills/premortemSource Repository
Improve Codebase Architecturemattpocock/skills
Scan your codebase for architecture improvements with visual reports and pick one to refactor
Web Design Guidelinesvercel-labs/agent-skills
Review your UI code for compliance with web interface guidelines
Caveman Reviewjuliusbrussee/caveman
Ultra-compressed one-line code review comments that cut noise
Zoom Outmattpocock/skills
Get a big picture view of your code with a simple map of modules and callers
Codebase Designmattpocock/skills
Create deep modules with tiny interfaces and lots of hidden logic for testability
Requesting Code Reviewobra/superpowers
Catch code issues early with focused automated reviews before every merge
Request Refactor Planmattpocock/skills
Plan safe code refactors with tiny commits and clear GitHub issues
Receiving Code Reviewobra/superpowers
Think first, then code. Verify feedback before making changes. Stay objective