# Universal Claude.md

10 Hacker News commenters recommended Universal Claude.md and 15 criticized it, November 2025 to November 2026. It was recommended in 1 of 13 months.

**Verdict:** Instruction set that measurably cuts Claude's output verbosity, though critics say it may hurt quality on complex tasks and is not benchmarked for accuracy.

## Why people recommend it

- Useful instructions that reduce verbosity (2 comments): "If you're goal is quality outputs, then it is likely too extreme, but there are otherwise useful instructions in this repo to (quantifiably) reduce verbosity." ([source](https://news.ycombinator.com/item?id=47582185)) "While I love this set of prompts, I've not seen my clause opus 4.6 give such verbose responses when using Claude code." ([source](https://news.ycombinator.com/item?id=47581840))

## What people warn about

- Unclear quality impact without benchmarks (3 comments): "without comparing before/after performance on some standard LLM benchmark to see if the instructions hurt intelligence" ([source](https://news.ycombinator.com/item?id=47581870)) "The benchmark is totally useless. It measures single prompts, and only compares output tokens with no regard for accuracy." ([source](https://news.ycombinator.com/item?id=47582905)) "the benchmarks here are heavily biased towards single-shot explanatory tasks" ([source](https://news.ycombinator.com/item?id=47581841))
- May hurt quality on complex tasks (3 comments): "forcing short responses can hurt coherence in longer agentic sessions" ([source](https://news.ycombinator.com/item?id=47585933)) "For complex tasks this is not a useful prompt." ([source](https://news.ycombinator.com/item?id=47582223)) "this would, generally, make the model worse" ([source](https://news.ycombinator.com/item?id=47581963))
- Could raise total token spending (2 comments): "Considering the 1:5 (input:output) token cost ratio, this could increase total spending." ([source](https://news.ycombinator.com/item?id=47582131)) "You're paying this disproportionately-huge amount upfront to save a pittance." ([source](https://news.ycombinator.com/item?id=47583082))

## Alternatives hackers recommend

- [Superpowers](https://hackerapproved.com/p/superpowers.md): 138 recommend
- [Claude Skills](https://hackerapproved.com/p/claude-skills.md): 59 recommend
- [grill-me skill by Matt Pocock](https://hackerapproved.com/p/grill-me-skill.md): 39 recommend
- [Get Shit Done](https://hackerapproved.com/p/get-shit-done.md): 31 recommend
- [Matt Pocock's skills](https://hackerapproved.com/p/matt-pocock-s-skills.md): 27 recommend

## Cite as

Hacker Approved, "Universal Claude.md", https://hackerapproved.com/p/universal-claude-md/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).