{"slug": "claudette-make-claude-stop-talking-like-a-buzzfeed-article", "title": "Claudette: Make Claude Stop Talking Like a BuzzFeed Article", "summary": "Anthropic's Claude Code now has a community-built skill called /debuzz that pipes Claude's verbose, clickbait-style responses through Google's Gemini CLI to produce plain-English translations, with modes for engineers, managers, and directors. The skill, released under the MIT license by developer Adnan Akil, preserves all file paths and code blocks while stripping theatrics, and it falls back to Claude's own rewrite only if Gemini errors. The tool addresses a common complaint that Claude's output reads like a BuzzFeed article, offering a practical fix for developers who want concise technical communication.", "body_md": "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](https://claude.com/claude-code) skill (`/debuzz`\n\n) 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\".\n\nClaudette 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.\n\nThis 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.\n\n**Before (Claude):**\n\nHere'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.\n\n**After ( /debuzz, colleague mode):**\n\nThe sync pipeline's retry logic has three bugs.\n\n`syncQueue.ts:142`\n\nswallows`ETIMEDOUT`\n\ninstead 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.\n\n```\ngit clone https://github.com/adnanakil/nobuzz\nmkdir -p ~/.claude/skills\ncp -r nobuzz/debuzz ~/.claude/skills/\n```\n\nRequirements:\n\n- Claude Code\n- The\n[Gemini CLI](https://github.com/google-gemini/gemini-cli)(`npm install -g @google/gemini-cli`\n\n), authenticated — run`gemini`\n\nonce and use`/auth`\n\n, or set`GEMINI_API_KEY`\n\n.\n\n```\n/debuzz [mode] [text]\n```\n\n| Mode | Audience | What you get |\n|---|---|---|\n`colleague` (default) |\nAn engineer | Same content, every file path and code block intact, zero theatrics |\n`manager` |\nA technical-adjacent manager | What happened, why it matters, what's next — about a third the length, no code |\n`director` |\nAn executive | Three to five sentences: outcome, impact, ask. Assumes thirty seconds of attention |\n\nWith 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.\"\n\nNo magic. Claudette writes its previous reply to a temp file, pipes it through `gemini -p \"<plain-English style instructions>\"`\n\n, 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.\n\nMIT", "url": "https://wpnews.pro/news/claudette-make-claude-stop-talking-like-a-buzzfeed-article", "canonical_source": "https://github.com/adnanakil/nobuzz/blob/main/README.md", "published_at": "2026-08-21 14:31:52+00:00", "updated_at": "2026-08-21 14:45:37.023120+00:00", "lang": "en", "topics": ["developer-tools", "large-language-models", "generative-ai"], "entities": ["Anthropic", "Claude Code", "Gemini CLI", "Google", "Adnan Akil", "Claudette", "nobuzz"], "alternates": {"html": "https://wpnews.pro/news/claudette-make-claude-stop-talking-like-a-buzzfeed-article", "markdown": "https://wpnews.pro/news/claudette-make-claude-stop-talking-like-a-buzzfeed-article.md", "text": "https://wpnews.pro/news/claudette-make-claude-stop-talking-like-a-buzzfeed-article.txt", "jsonld": "https://wpnews.pro/news/claudette-make-claude-stop-talking-like-a-buzzfeed-article.jsonld"}}