larashero3-dotcom/lieflat-less-ai-tone
A skill that detects and minimally rewrites AI-sounding writing patterns in Chinese text, based on a 5.2-million-character corpus study.
Collecting fresh signals — velocity needs a few days of history.
collecting data…
star history
The project studies stylistic markers that make LLM-generated Chinese text read as AI-written, using a corpus of 1,169 articles, 100+ metrics, and roughly 500,000 model-based semantic judgments. Packaged as a skill, it first produces a detection report with metrics, reference examples, and suggested fixes, then rewrites the text after user confirmation and re-tests the result. It targets LLM writing quality rather than coding or reasoning tasks.
Frequently asked
- What is larashero3-dotcom/lieflat-less-ai-tone?
- A skill that detects and minimally rewrites AI-sounding writing patterns in Chinese text, based on a 5.2-million-character corpus study.
- Is lieflat-less-ai-tone open source?
- Yes — larashero3-dotcom/lieflat-less-ai-tone is an open-source project tracked on heatdrop.
- What language is lieflat-less-ai-tone written in?
- larashero3-dotcom/lieflat-less-ai-tone is primarily written in Python.
- How popular is lieflat-less-ai-tone?
- larashero3-dotcom/lieflat-less-ai-tone has 4.3k stars on GitHub.
- Where can I find lieflat-less-ai-tone?
- larashero3-dotcom/lieflat-less-ai-tone is on GitHub at https://github.com/larashero3-dotcom/lieflat-less-ai-tone.