# op7418/Humanizer-zh

Humanizer 的汉化版本，Claude Code Skills，旨在消除文本中 AI 生成的痕迹。

Repository: https://github.com/op7418/Humanizer-zh
Canonical: https://ross.abutalabs.com/products/humanizer-zh
License: MIT
License Family: permissive
Last push: 2026-01-19T07:46:35+00:00

## Health v2 (maintenance only)
Score: 44/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 63, release rhythm 35, longevity 16
- inputs: {"age_days": 226, "days_push": 226, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 16121, forks 1077 (observed 2026-08-28T04:11:14.810499+00:00)

## What it is
A Chinese-localized Claude Code skill that removes AI-generated writing patterns from text, rewriting it to sound more natural and human. It is a translation of blader/humanizer with additional quality-check utilities, detecting 24 AI writing patterns across content, grammar, style, and filler categories.

## Use cases
- humanize AI-generated Chinese text
- rewrite marketing copy to remove AI tone
- make academic abstracts sound human-written
- de-slop blog posts written by LLMs
- learn to recognize common AI writing patterns
- edit Claude or ChatGPT output for publication

## When to choose
- you use Claude Code and want a one-command skill to humanize Chinese text
- you need to polish AI-drafted Chinese content for marketing, academic, or blog use
- you want a reference checklist of AI writing tells in Chinese

## When to avoid
- you need humanization for languages other than Chinese (use the original blader/humanizer)
- you need automated detection without an LLM runtime
- you want a standalone CLI or web app rather than a Claude Code skill

## Facets
- artifact type: plugin
- maturity: active
- function: nlp, prompt-engineering, developer-tools
- domain: developer-tools
- platform: cli, cross-platform
- tags: claude-code-skill, ai-text-humanization, chinese-localization, writing-style, text-rewriting, natural-language-processing, localization

## Member repositories
- op7418/Humanizer-zh (main) score 44

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:14.810499+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 2026-08-29T17:05:14.092898+00:00, confidence not recorded.
  - readme: https://github.com/op7418/Humanizer-zh (fetched 2026-08-28T04:11:14.810499+00:00, sha 2a457a766a6f)
- Data as of 2026-08-30T08:39:29.467469+00:00.