# Send Humanize Chinese to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "humanize-chinese",
    "name": "Humanize Chinese",
    "source": "tencent",
    "type": "skill",
    "category": "通讯协作",
    "sourceUrl": "https://clawhub.ai/swaylq/humanize-chinese",
    "canonicalUrl": "https://clawhub.ai/swaylq/humanize-chinese",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/humanize-chinese",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=humanize-chinese",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "evals/evals.json",
      "package.json",
      "scripts/compare_cn.py",
      "scripts/detect_cn.py"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "humanize-chinese",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T06:18:23.387Z",
      "expiresAt": "2026-05-07T06:18:23.387Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=humanize-chinese",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=humanize-chinese",
        "contentDisposition": "attachment; filename=\"humanize-chinese-2.4.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "humanize-chinese"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/humanize-chinese"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/humanize-chinese",
    "downloadUrl": "https://openagent3.xyz/downloads/humanize-chinese",
    "agentUrl": "https://openagent3.xyz/skills/humanize-chinese/agent",
    "manifestUrl": "https://openagent3.xyz/skills/humanize-chinese/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/humanize-chinese/agent.md"
  }
}
```
## Documentation

### Humanize Chinese AI Text v2.0

Comprehensive CLI for detecting and transforming Chinese AI-generated text. Makes robotic AI writing natural and human-like.

v2.0 highlights: weighted 0-100 scoring, sentence-level analysis, sentence restructuring (merge/split), context-aware replacement, rhythm variation, vocabulary diversification, 7 style transforms, external pattern config (patterns_cn.json).

### Quick Start

# Detect AI patterns (20+ categories, 0-100 score)
python scripts/detect_cn.py text.txt
python scripts/detect_cn.py text.txt -v          # verbose + worst sentences
python scripts/detect_cn.py text.txt -s           # score only
python scripts/detect_cn.py text.txt -j           # JSON output

# Humanize text
python scripts/humanize_cn.py text.txt -o clean.txt
python scripts/humanize_cn.py text.txt --scene social
python scripts/humanize_cn.py text.txt --scene tech -a   # aggressive mode
python scripts/humanize_cn.py text.txt --seed 42         # reproducible

# Apply writing styles
python scripts/style_cn.py text.txt --style zhihu -o zhihu.txt
python scripts/style_cn.py text.txt --style xiaohongshu
python scripts/style_cn.py --list

# Compare before/after
python scripts/compare_cn.py text.txt --scene tech -a
python scripts/compare_cn.py text.txt -o clean.txt

### Scoring

Weighted 0-100 score with 4 severity levels:

ScoreLevelMeaning0-24LOWLikely human-written25-49MEDIUMSome AI signals50-74HIGHProbably AI-generated75-100VERY HIGHAlmost certainly AI

### Detection Categories

🔴 Critical (weight: 8)

CategoryExamplesThree-Part Structure首先...其次...最后, 一方面...另一方面, 其一...其二...其三Mechanical Connectors值得注意的是, 综上所述, 不难发现, 归根结底, 由此可见Empty Grand Words赋能, 闭环, 数字化转型, 协同增效, 全方位, 多维度

🟠 High Signal (weight: 4)

CategoryExamplesAI High-Frequency Words助力, 彰显, 底层逻辑, 抓手, 触达, 沉淀, 复盘Filler Phrases值得一提的是, 众所周知, 毫无疑问Balanced Arguments虽然...但是...同时, 既有...也有...更有Template Sentences随着...的不断发展, 在当今...时代, 作为...的重要组成部分

🟡 Medium Signal (weight: 2)

CategoryExamplesHedging Language在一定程度上, 某种程度上, 通常情况下 (>5 occurrences)List AddictionExcessive numbered/bulleted listsPunctuation OveruseDense em dashes, semicolonsExcessive Rhetoric对偶/排比句过多

⚪ Style Signal (weight: 1.5)

CategoryDescriptionUniform ParagraphsLow CV in paragraph lengthsLow BurstinessMonotonous sentence lengthsEmotional FlatnessLack of emotional/personal expressionsRepetitive StartersSame sentence starters >3 timesLow EntropyLow character-level entropy (predictable text)

### Sentence-Level Analysis

With -v (verbose) mode, the detector identifies the most AI-like sentences:

── 最可疑句子 ──
  1. [16分] 随着人工智能技术的不断发展，在当今数字化转型时代...
     原因: 数字化转型, 深度融合, 模板: 随着.*?的(不断)?发展

### Transforms (applied in order)

Structure cleanup — Remove three-part structure (首先/其次/最后)
Phrase replacement — Context-aware replacement of AI phrases (regex patterns first, then plain text, longest-first matching)
Sentence merge — Merge overly short consecutive sentences
Sentence split — Split long sentences at natural breakpoints (但是/不过/同时)
Punctuation normalization — Reduce excessive semicolons, em dashes
Vocabulary diversification — Replace repeated words (进行/实现/提供 etc.) with synonyms
Paragraph rhythm — Vary uniform paragraph lengths (merge short, split long)
Casual injection — Add human expressions (scene-dependent)
Paragraph shortening — For social/chat scenes

### Scenes

SceneCasualnessBest Forgeneral0.3Default, balancedsocial0.7Social media, short poststech0.3Tech blogs, tutorialsformal0.1Formal articles, reportschat0.8Conversations, messaging

### Aggressive Mode (-a)

Adds +0.3 casualness, more colloquial expressions, stronger sentence restructuring. Typical score reduction: 60-80 points on heavily AI-generated text.

### Reproducibility

Use --seed N for reproducible results (same input + seed = same output).

### Writing Style Transforms

7 specialized Chinese writing styles:

StyleNameDescriptioncasual口语化Like chatting with friends — natural, relaxedzhihu知乎Rational, in-depth, personal opinionsxiaohongshu小红书Enthusiastic, emoji-rich, product-focusedwechat公众号Storytelling, engaging, relatableacademic学术Rigorous, precise, no colloquialismsliterary文艺Poetic, imagery-rich, metaphoricalweibo微博Short, opinionated, shareable

### Combine humanize + style

python scripts/humanize_cn.py text.txt --style xiaohongshu -o xhs.txt

This first humanizes (removes AI patterns) then applies the style transform.

### External Configuration

All patterns, replacements, and scoring weights are in scripts/patterns_cn.json. Edit this file to:

Add new AI vocabulary patterns
Customize replacement alternatives
Adjust scoring weights per severity
Add regex patterns for template detection
Set thresholds for hedging language detection

### detect_cn.py

python scripts/detect_cn.py [file] [-j] [-s] [-v] [--sentences N]

FlagDescription-jJSON output-sScore only (e.g. "72/100 (high)")-vVerbose: show worst sentences--sentences NNumber of worst sentences to show (default: 5)

### humanize_cn.py

python scripts/humanize_cn.py [file] [-o output] [--scene S] [--style S] [-a] [--seed N]

FlagDescription-oOutput file--scenegeneral/social/tech/formal/chat--stylecasual/zhihu/xiaohongshu/wechat/academic/literary/weibo-aAggressive mode--seedRandom seed for reproducibility

### style_cn.py

python scripts/style_cn.py [file] --style S [-o output] [--seed N] [--list]

### compare_cn.py

python scripts/compare_cn.py [file] [-o output] [--scene S] [--style S] [-a]

Shows score diff, category changes, and metric comparison before/after humanization.

### Workflow

# 1. Check AI score
python scripts/detect_cn.py document.txt -v

# 2. Humanize with comparison
python scripts/compare_cn.py document.txt --scene tech -a -o clean.txt

# 3. Verify improvement
python scripts/detect_cn.py clean.txt -s

# 4. Optional: apply specific style
python scripts/style_cn.py clean.txt --style zhihu -o final.txt

### Batch Processing

# Scan all files
for f in *.txt; do
  echo "=== $f ==="
  python scripts/detect_cn.py "$f" -s
done

# Transform all markdown
for f in *.md; do
  python scripts/humanize_cn.py "$f" --scene tech -a -o "${f%.md}_clean.md"
done
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: swaylq
- Version: 2.0.0
## Source health
- Status: healthy
- Item download looks usable.
- Yavira can redirect you to the upstream package for this item.
- Health scope: item
- Reason: direct_download_ok
- Checked at: 2026-04-30T06:18:23.387Z
- Expires at: 2026-05-07T06:18:23.387Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/humanize-chinese)
- [Send to Agent page](https://openagent3.xyz/skills/humanize-chinese/agent)
- [JSON manifest](https://openagent3.xyz/skills/humanize-chinese/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/humanize-chinese/agent.md)
- [Download page](https://openagent3.xyz/downloads/humanize-chinese)