notoriouslab

notoriouslab / bu-ketao

Public

不客套 — Strip Chinese AI verbosity. 繁體中文 LLM 輸出壓縮規則集。~72% token compression, zero semantic loss.

18
0
100% credibility
Found Apr 15, 2026 at 23 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
AI Summary

bu-ketao offers ready-to-use instructions and prompts to strip unnecessary pleasantries and fillers from Chinese AI model outputs, achieving about 72% compression without losing key information.

How It Works

1
🔍 Discover bu-ketao

You stumble upon bu-ketao while searching for ways to make Chinese AI chat responses shorter and less chatty.

2
📖 See the magic

You read real examples where long, polite AI answers shrink to quick, clear facts without losing meaning.

3
✨ Before and after wow

The transformation hits you – fluffy explanations turn into punchy summaries, saving tons of reading time.

4
Pick your AI buddy
🤖
For Claude

Copy a simple command file to your Claude setup for instant concise mode.

💬
For ChatGPT or others

Paste a special instruction at the start of your chat to trim the fluff.

✏️
For Cursor

Drop a rule note into your project folder for shorter coding help.

5
💻 Start chatting

Ask your question in the AI, and watch it reply straight to the point.

🎉 Shorter, smarter chats

You now get fast, no-nonsense answers that save time, tokens, and money every day.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 23 to 18 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is bu-ketao?

bu-ketao strips pleasantries, fillers, and hedging from Traditional Chinese LLM outputs, compressing responses by ~72% tokens with zero semantic loss—think turning verbose AI explanations into tight, dev-ready summaries. It targets uniquely Chinese verbosity patterns like "好的，讓我來幫你" or "希望這對你有幫助," which English tools miss entirely. Paste ready rules into Claude commands, ChatGPT system prompts, or Cursor project files for instant terse Chinese replies.

Why is it gaining traction?

Unlike English compressors that drop articles or abbreviate, bu-ketao catalogs 10+ Chinese-specific patterns (hedging, repetition, hollow claims) with lite/full/ultra modes, delivering real token savings—up to 87% in tests across dev scenarios like React hooks or Docker debugging. Developers notice lower API costs (e.g., $78/year at scale) and faster reads, plus compatibility with Claude, ChatGPT, and Cursor hooks them without setup hassle. It's the only systematic Chinese output stripper, complementing input optimizers.

Who should use this?

Backend devs querying Chinese LLMs on Git rebase conflicts or Nginx proxies; frontend folks debugging React re-renders or CSS layouts in Traditional Chinese; Cursor users in Taiwan dev teams wanting concise code reviews. Ideal for anyone paying per-token on verbose Qwen or Claude outputs during daily coding sessions.

Verdict

Grab it if you work with Chinese LLMs—solid docs and test results make the low maturity (18 stars, 1.0% credibility) forgivable for early adopters. Skip if English-only; wait for more upstream integrations otherwise.

(178 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.