# 克劳黛特：让 Claude 别再像 BuzzFeed 文章那样说话

- 来源：Hacker News 热门（buzzing.cc 中文翻译）
- 作者：aakil
- 发布时间：2026-08-22 03:49
- AIHOT 分数：62
- AIHOT 链接：https://aihot.virxact.com/items/cmt3ddu020omrro6t451gm8lr
- 原文链接：https://github.com/adnanakil/nobuzz/blob/main/README.md

## AI 摘要

开发者与 Claude 合作构建了一个 Claude Code 技能 /debuzz，将 Claude 的回复通过 Gemini CLI 翻译成简洁直白的英文，避免其“千禧年点击诱饵”式表达。该技能支持同事、经理、高管三种模式，分别输出不同详略程度的版本，并承诺逐字打印 Gemini 的翻译结果。

## 正文

README.md

History

README.md

File metadata and controls

NoBuzz

Obviously it's common knowledge by now that Anthropic has solely trained claude on old Buzzfeed articles (explaining its love for 90s nostalgia). So Claude and I built a Claude Code skill (/debuzz) that takes Claude's last response and runs it through the Gemini CLI to translate it from talking like a millennial clickbait to regular English. We're thinking of calling it "Claudette" but Cat Wu is famously litigious so it's definitely absolutely not called "Claudette".

The problem

Claudette is our solution to Claude being a great engineer with one incurable condition: it talks like it's delivering a TED talk about its own pull request. You ask why a test is flaky and you get a "load-bearing assumption," three numbered revelations, and a solemn note that the third one is the most instructive yet. Nothing is ever just a bug. There is always a kicker.

This skill accepts that no amount of prompting fully cures this, and does the honest thing instead: it hands the response to a different model, Gemini (remember gemini from last summer?), whose only job is to say it like a human person. Claudette has pinky promised to print Gemini's translation verbatim, because letting Claude "tidy up" the translation reintroduces exactly the voice being removed.

Before / after

Before (Claude):

Here's where it gets interesting: the retry logic isn't just a nice-to-have — it's - the - load-bearing - assumption - of - the - entire - sync - pipeline. Three things jumped out at me, and the third one is the most instructive yet. [...] And third — and this is the kicker — the dedupe key includes a timestamp, which means retries are never actually deduplicated.

After (/debuzz, colleague mode):

The sync pipeline's retry logic has three bugs. syncQueue.ts:142 swallows ETIMEDOUT instead of re-queuing the job. The backoff caps at 2 seconds, which is too low for mobile networks. And the dedupe key includes a timestamp, so retries are never deduplicated. Fix: strip the timestamp from the key, raise the cap to 30 seconds, and re-throw the timeout error.

Install

git clone https://github.com/adnanakil/nobuzz mkdir -p ~/.claude/skills cp -r nobuzz/debuzz ~/.claude/skills/

Claude Code

The Gemini CLI (npm install -g @google/gemini-cli), authenticated — run gemini once and use /auth, or set GEMINI_API_KEY.

Usage

/debuzz [mode] [text]

Mode Audience What you get

colleague (default) An engineer Same content, every file path and code block intact, zero theatrics

manager A technical-adjacent manager What happened, why it matters, what's next — about a third the length, no code

director An executive Three to five sentences: outcome, impact, ask. Assumes thirty seconds of attention

With no text argument it translates Claude's previous reply. Paste text after the mode to translate that instead. It also triggers on natural phrases like "say that in normal english."

How it works

No magic. Claudette writes its previous reply to a temp file, pipes it through gemini -p "<plain-English style instructions>", and prints Gemini's output verbatim. If Gemini errors (usually auth), you see the actual error — Claude only offers its own rewrite as a clearly labeled fallback, because a debuzzer that quietly asks the buzzer to debuzz itself is how you end up with a load-bearing translation.