← 返回 Skills 市场

Humanize Ai Text 1.0.0.1

Name: Humanize Ai Text 1.0.0.1
Author: jaydenlm

作者 jayden · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ✓ 安全检测通过

108

总下载

当前安装

版本数

在 OpenClaw 中安装

/install humanize-ai-text-1-0-0-1

功能描述

Humanize AI-generated text to bypass detection. This humanizer rewrites ChatGPT, Claude, and GPT content to sound natural and pass AI detectors like GPTZero,...

使用说明 (SKILL.md)

Humanize AI Text

Comprehensive CLI for detecting and transforming AI-generated text to bypass detectors. Based on Wikipedia's Signs of AI Writing.

Quick Start

# 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

Detection Categories

The analyzer checks for 16 pattern categories from Wikipedia's guide:

Critical (Immediate AI Detection)

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`

High Signal

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"

Medium Signal

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"

Style Signal

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"

Scripts

detect.py — Scan for AI Patterns

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:

Issue count and word count
AI probability (low/medium/high/very high)
Breakdown by category
Auto-fixable patterns marked

transform.py — Rewrite Text

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:

Citation bugs (oaicite, turn0search)
Markdown (**, ##, ```)
Chatbot sentences
Copula avoidance → "is/has"
Filler phrases → simpler forms
Curly → straight quotes

Aggressive (-a):

Simplifies -ing clauses
Reduces em dashes

compare.py — Before/After Analysis

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

Workflow

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)

AI Probability Scoring

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	\x3C15 issues AND \x3C2% density

Customizing Patterns

Edit scripts/patterns.json to add/modify:

ai_vocabulary — words to flag
significance_inflation — puffery phrases
promotional_language — marketing speak
copula_avoidance — phrase → replacement
filler_replacements — phrase → simpler form
chatbot_artifacts — phrases triggering sentence removal

Batch Processing

# 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

Reference

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."

安全使用建议

This skill is technically coherent: the scripts implement exactly what the README says and operate only on local files (no network calls or credentials). Before installing, consider: 1) Ethical/legal risk — the tool explicitly helps evade AI-detectors (could violate school/employer policies or service TOS). 2) Source verification — no homepage and the metadata ownerId mismatch is a minor red flag; prefer code from a known, trusted publisher. 3) Audit patterns.json and the scripts yourself (they're small and human-readable) to confirm there are no hidden behaviors. 4) Test in a sandbox or limited environment first. If you intend legitimate uses (e.g., improving writing quality), document that and avoid using the tool to bypass policy or rules.

功能分析

Type: OpenClaw Skill Name: humanize-ai-text-1-0-0-1 Version: 1.0.0 The skill bundle is a legitimate text processing utility designed to identify and rewrite AI-generated text patterns based on Wikipedia's 'Signs of AI Writing' documentation. The Python scripts (detect.py, transform.py, and compare.py) perform local string manipulation and regex replacements using a static patterns.json file. There is no evidence of data exfiltration, network activity, shell execution, or malicious prompt injection instructions.

能力评估

ℹ Purpose & Capability

The name/description (humanize AI text to bypass detectors) match the included scripts (detect.py, transform.py, compare.py) and patterns.json. The required surface (no env vars, no external binaries) is proportional. Minor packaging inconsistency: _meta.json.ownerId differs from the registry owner ID in the metadata — likely benign but worth verifying the publisher.

ℹ Instruction Scope

SKILL.md and the scripts instruct the agent to read/write local text files, scan for patterns, and rewrite content to reduce detector signals. The instructions do not request unrelated files, system credentials, or network endpoints. However, the explicit runtime objective is to bypass AI detectors — a clear misuse vector (academic dishonesty, terms-of-service evasion) even though it stays within the technical scope described.

✓ Install Mechanism

No install spec or external downloads. All code is packaged in the skill and operates locally; there are no remote fetches, archive extraction, or registry installs to review.

✓ Credentials

No environment variables, credentials, or config paths are required. The scripts only read local files (text and patterns.json) and write outputs; requested access is minimal and proportional.

✓ Persistence & Privilege

The skill does not request always:true and has no mechanism to persist or modify other skills or global agent settings. It runs on demand and only interacts with files the user provides.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install humanize-ai-text-1-0-0-1
安装完成后，直接呼叫该 Skill 的名称或使用 /humanize-ai-text-1-0-0-1 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

- Initial release of the "humanize-ai-text" skill. - Provides a CLI toolkit to detect and transform AI-generated text, making it natural and less likely to trigger AI detectors like GPTZero, Turnitin, and Originality.ai. - Analyzer checks for 16 pattern categories based on Wikipedia’s "Signs of AI Writing." - Features detection, transformation, and comparison scripts with options for aggressive rewriting and detailed AI probability scoring. - Includes customizable detection patterns and supports batch processing for multiple documents.

元数据

Slug humanize-ai-text-1-0-0-1

版本 1.0.0

许可证 MIT-0

累计安装 1

当前安装数 1

历史版本数 1

常见问题