---
title: PromptLean
emoji: ⚡
colorFrom: purple
colorTo: indigo
sdk: static
app_file: index.html
pinned: false
license: mit
short_description: 120 prompts, three token-efficiency variants each
---

# PromptLean

A curated library of token-efficient prompts. **120 prompts across 14 categories**, each shipped in three variants: **Lean**, **Balanced**, and **Max Quality**.

Most published prompts are overengineered. A code review does not need 200 tokens of preamble, but some tasks genuinely earn the extra context. Keeping all three variants side by side makes that tradeoff visible: across the library, Lean averages about 86% fewer tokens than Max Quality.

Browse by category, compare variants side by side, and check token counts per model.

- Prompts as a dataset: [kishormorol/promptlean-prompts](https://huggingface.co/datasets/kishormorol/promptlean-prompts)
- Source and contributions: [github.com/kishormorol/promptlean](https://github.com/kishormorol/promptlean)

MIT licensed.