# hylarucoder/ai-flavor-remover

AI 味去除 - 仅在 Gemini 2.5 Pro 上测试通过

Repository: https://github.com/hylarucoder/ai-flavor-remover
Canonical: https://ross.abutalabs.com/products/ai-flavor-remover
License Family: other
Last push: 2025-04-02T14:35:03+00:00

## Health v2 (maintenance only)
Score: 26/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 14, release rhythm 35, longevity 37
- inputs: {"age_days": 518, "days_push": 518, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1136, forks 72 (observed 2026-08-28T04:03:43.661363+00:00)

## What it is
A curated prompt (system prompt) for rewriting AI-generated Chinese text to remove its 'AI flavor' and make it read like human writing, tested on Gemini 2.5 Pro reasoning models. The repository is essentially a single well-structured prompt plus usage notes rather than runnable software.

## Use cases
- rewrite AI-generated articles to sound human-written
- reduce AI-detection scores on Chinese text
- polish LLM output to remove robotic phrasing
- expand drafts while keeping a natural tone
- humanize AI writing for blog posts

## When to choose
- you write Chinese content with LLMs and want it to read naturally
- you need a ready-made humanization prompt for a reasoning model like Gemini 2.5 Pro
- you want to lower AI-detector scores on your drafts

## When to avoid
- you need a tool, API, or CLI rather than a copy-paste prompt
- your content is not in Chinese
- you need guaranteed evasion of AI detectors or a license-protected dependency

## Facets
- artifact type: learning-resource
- maturity: active
- function: prompt-engineering, nlp
- domain: large-language-models, tutorials
- platform: cross-platform
- tags: prompt, humanize-ai-text, chinese-writing, ai-detection-evasion, gemini, natural-language-processing

## Member repositories
- hylarucoder/ai-flavor-remover (main) score 26

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:43.661363+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:36:31.143355+00:00, confidence not recorded.
  - readme: https://github.com/hylarucoder/ai-flavor-remover (fetched 2026-08-28T04:03:43.661363+00:00, sha f2eaa3897516)
- Data as of 2026-08-30T08:39:29.467469+00:00.