作者:互联网 时间: 2026-08-09 18:55:01
从源直接安装技能的最快方式。
npx clawhub@latest install humanize-ai-text
将技能文件夹复制到以下位置之一
全局模式~/.openclaw/skills/
工作区
<project>/skills/
优先级:工作区 > 本地 > 内置
将此提示词复制到 OpenClaw 即可自动安装。
请帮我使用 Clawhub 安装 humanize-ai-text。如果尚未安装 Clawhub,请先安装(npm i -g clawhub)。
AI 文本人性化是一套专门的 Openclaw Skills,旨在识别和消除 AI 生成内容的独特标记。基于维基百科关于 AI 写作迹象指南的广泛研究,该工具提供了一种结构化方法,使来自 ChatGPT、Claude 和 GPT-4 等模型的文本听起来自然且具有人性。它针对 16 个特定的模式类别,包括聊天机器人人工痕迹、意义夸大和可预测的词汇。
通过利用这些 Openclaw Skills,用户可以系统地清除文档中的机器特征。无论您是在处理引用错误、特定的聊天机器人短语,还是过度使用的 AI 词汇(如 'delve' 或 'tapestry'),此技能都能提供必要的自动化功能,确保您的内容通过严格的 AI 检测器,同时保持可读性和专业语气。
要开始使用这些 Openclaw Skills,请确保您已安装 Python 并遵循以下步骤:
# 克隆仓库并进入目录
git clone <repository-url>
cd humanize-ai-text
# 对文本文件运行检测脚本
python scripts/detect.py your_document.txt
# 将文本转换为类人版本
python scripts/transform.py your_document.txt -o humanized_output.txt
该技能通过集中式的配置模式组织其检测逻辑和转换规则:
| 组件 | 描述 |
|---|---|
scripts/patterns.json |
AI 词汇、填充短语和系动词规避规则的主要数据库。 |
scripts/detect.py |
根据问题密度计算 AI 概率(低、中、高、极高)的逻辑。 |
scripts/transform.py |
负责应用替换和简化 -ing 从句的引擎。 |
scripts/compare.py |
用于衡量人性化过程有效性的报告工具。 |
name: humanize-ai-text
description: Humanize AI-generated text to bypass detection. This humanizer rewrites ChatGPT, Claude, and GPT content to sound natural and pass AI detectors like GPTZero, Turnitin, and Originality.ai. Based on Wikipedia's comprehensive "Signs of AI Writing" guide. Makes robotic AI writing undetectable and human-like.
allowed-tools:
- Read
- Write
- StrReplace
- Glob
Comprehensive CLI for detecting and transforming AI-generated text to bypass detectors. Based on Wikipedia's Signs of AI Writing.
# Detect AI patterns
python scripts/detect.py text.txt
# Transform to human-like
python scripts/transform.py text.txt -o clean.txt
# Compare before/after
python scripts/compare.py text.txt -o clean.txt
The analyzer checks for 16 pattern categories from Wikipedia's guide:
| Category | Examples |
|---|---|
| Citation Bugs | oaicite, turn0search, contentReference |
| Knowledge Cutoff | "as of my last training", "based on available information" |
| Chatbot Artifacts | "I hope this helps", "Great question!", "As an AI" |
| Markdown | **bold**, ## headers, code blocks |
| Category | Examples |
|---|---|
| AI Vocabulary | delve, tapestry, landscape, pivotal, underscore, foster |
| Significance Inflation | "serves as a testament", "pivotal moment", "indelible mark" |
| Promotional Language | vibrant, groundbreaking, nestled, breathtaking |
| Copula Avoidance | "serves as" instead of "is", "boasts" instead of "has" |
| Category | Examples |
|---|---|
| Superficial -ing | "highlighting the importance", "fostering collaboration" |
| Filler Phrases | "in order to", "due to the fact that", "Additionally," |
| Vague Attributions | "experts believe", "industry reports suggest" |
| Challenges Formula | "Despite these challenges", "Future outlook" |
| Category | Examples |
|---|---|
| Curly Quotes | "" instead of "" (ChatGPT signature) |
| Em Dash Overuse | Excessive use of — for emphasis |
| Negative Parallelisms | "Not only... but also", "It's not just... it's" |
| Rule of Three | Forced triplets like "innovation, inspiration, and insight" |
python scripts/detect.py essay.txt
python scripts/detect.py essay.txt -j # JSON output
python scripts/detect.py essay.txt -s # score only
echo "text" | python scripts/detect.py
Output:
python scripts/transform.py essay.txt
python scripts/transform.py essay.txt -o output.txt
python scripts/transform.py essay.txt -a # aggressive
python scripts/transform.py essay.txt -q # quiet
Auto-fixes:
Aggressive (-a):
python scripts/compare.py essay.txt
python scripts/compare.py essay.txt -a -o clean.txt
Shows side-by-side detection scores before and after transformation
Scan for detection risk:
python scripts/detect.py document.txt
Transform with comparison:
python scripts/compare.py document.txt -o document_v2.txt
Verify improvement:
python scripts/detect.py document_v2.txt -s
Manual review for AI vocabulary and promotional language (requires judgment)
| Rating | Criteria |
|---|---|
| Very High | Citation bugs, knowledge cutoff, or chatbot artifacts present |
| High | >30 issues OR >5% issue density |
| Medium | >15 issues OR >2% issue density |
| Low | <15 issues AND <2% density |
Edit scripts/patterns.json to add/modify:
ai_vocabulary — words to flagsignificance_inflation — puffery phrasespromotional_language — marketing speakcopula_avoidance — phrase → replacementfiller_replacements — phrase → simpler formchatbot_artifacts — phrases triggering sentence removal# Scan all files
for f in *.txt; do
echo "=== $f ==="
python scripts/detect.py "$f" -s
done
# Transform all markdown
for f in *.md; do
python scripts/transform.py "$f" -a -o "${f%.md}_clean.md" -q
done
Based on Wikipedia's Signs of AI Writing, maintained by WikiProject AI Cleanup. Patterns documented from thousands of AI-generated text examples.
Key insight: "LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases."