Pascal: no time to make it shorter

Summary

AI made long drafts cheap and noisy while reading time stayed fixed. Use models to think and explore, then force every thread into one page colleagues can finish without hunting for the point. The Claude skills linked here enforce that cut.

I have made this longer than usual because I have not had time to make it shorter.

- Blaise Pascal, Lettres provinciales, Letter XVI (1657)

Pascal’s apology still names the hard part of the work. A short page costs more than a long one: you have to decide what matters, discard the rest, and leave something a colleague can finish without searching for the point.

AI changed the cost of drafting without changing that constraint. Long text is cheap now. It arrives in seconds, fills shared channels, and raises noise while reading time stays fixed. People who wrote carefully when attention was scarce already knew why brevity mattered. The scarcity did not leave; only the temptation to skip the cut.

I built Claude skills that enforce a one-pager and shared them with the team. Source and install notes are in savagemanage/claude-skills. Upload either zip in Claude.ai under Settings → Capabilities / Skills, or copy the skill folders into .claude/skills for Claude Code.

exec-one-pager English exec, pitch, or startup one-pager Download .zip gov-one-pager Korean government-style grant / proposal one-pager Download .zip

Use as much AI as you need to think. Once the thinking is done, the rule is fixed: reduce every thread to one page. Efficient communication is what remains when the transcript pile is gone.