SurefireStudios/tldr

9 stars · Last commit 2026-09-16

Too long; didn't read — for AI coding agents. A skill that makes Claude Code, Cursor, Codex, Gemini CLI and 16 more lead with a 3-line TL;DR and fold the detail instead of burying the answer. Measured on Sonnet and Opus, every run published — including the ones that failed. Demote, don't delete.

README preview

<p align="center">
  <img src="./assets/logo.svg" alt="tldr — too long; didn't read, for AI coding agents" width="150" />
</p>

<h1 align="center">tldr</h1>

<p align="center">
  <strong>Too long; didn't read — for AI coding agents.</strong>
</p>

<p align="center">
  Your coding agent buries the answer in four paragraphs.<br/>
  This makes it lead with three lines and fold the rest.<br/>
  <em>Demote, don't delete.</em>
</p>

<p align="center">
  <a href="LICENSE"><img src="https://img.shields.io/github/license/SurefireStudios/tldr?style=flat-square" alt="License: MIT"></a>
  <a href="https://github.com/SurefireStudios/tldr/stargazers"><img src="https://img.shields.io/github/stars/SurefireStudios/tldr?style=flat-square" alt="Stars"></a>
  <a href="INSTALL.md"><img src="https://img.shields.io/badge/agents-20%20supported-blue?style=flat-square" alt="20 agents supported"></a>

View full repository on GitHub →