explaingit

wwtlitee/natural-chinese-copy-core

23JavaScriptAudience · writerComplexity · 2/5Setup · easy

TLDR

A set of AI assistant skills and Node.js validators that help produce natural-sounding Chinese copy by enforcing grammar rules specific to Chinese writing and detecting patterns that indicate machine translation.

Mindmap

mindmap
  root((natural-chinese-copy))
    What it does
      Natural Chinese writing
      Bad pattern detection
      Grammar validation
    Process
      Chinese fact draft
      Sentence validation
      Manual review stage
    How it works
      AI skill files
      Node.js validators
      Feedback loop
    Compatibility
      Codex support
      Claude support
      No external services
    Audience
      Chinese copywriters
      Content creators
Click or tap to explore — scroll the page freely

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

Things people build with this

USE CASE 1

Generate natural-sounding Chinese marketing copy that avoids the stiff phrasing typical of AI-translated text.

USE CASE 2

Run automated grammar and bad-pattern checks on AI-generated Chinese text before sending it to manual review.

USE CASE 3

Add a bad sentence example to the feedback loop to create a new validation rule for future writing tasks.

Tech stack

JavaScriptNode.js

Getting it running

Difficulty · easy Time to first run · 30min

No external services or accounts required. Works with both Codex and Claude as the AI assistant backend.

In plain English

This repository is a writing skill for AI coding assistants (specifically Codex and Claude) that helps produce natural-sounding Chinese copy. The project name translates roughly as "Chinese is the real deal," and the skill is built around a specific problem: AI-generated Chinese text often sounds stiff, machine-translated, or built on English sentence structure rather than natural Chinese phrasing. The skill introduces a multi-step process before delivering any finished text. First it creates what the README calls a Chinese fact draft: a raw summary of the source material written directly in Chinese rather than translated from an English framing. Then it checks each key sentence for whether the subject, verb, and object are correctly matched, and whether the verb describes something the subject can actually do. Sentences that match a known list of bad patterns are discarded entirely and rewritten from the fact draft rather than patched in place. After the automated checks pass, there is still a manual review stage for checking whether the output is appropriate for its intended audience, channel, and publication context. The project explicitly separates passing the automated validators from being ready to publish. The repository also includes a feedback loop: when a user points out a bad sentence, the example goes into a sample file, gets reviewed, and may eventually become a new rule or validator. Single feedback cases do not automatically become hard rules, which protects the system from overreacting to one-off preferences. The project ships as a directory of skill files, reference documents, and Node.js validation scripts. It is compatible with both Codex and Claude and requires no external services or accounts to use. The README is written entirely in Chinese, reflecting its intended audience of Chinese-language copywriters and content creators.

Copy-paste prompts

Prompt 1
Use the natural-chinese-copy-core skill to write a product description in natural Chinese from these key facts: [paste your facts here].
Prompt 2
Run the Chinese copy validator on this draft and flag any sentences that match known bad-pattern or machine-translation rules.
Prompt 3
Create a Chinese fact draft for this topic first, then generate the final copy without translating from an English sentence structure.
Prompt 4
Check this Chinese paragraph for subject-verb-object mismatches and rewrite any sentences that describe an action the subject cannot do.
Open on GitHub → Explain another repo

← wwtlitee on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.