← 返回 Skills 市场
cp3d1455926-svg

Humanize Ai Text

作者 cp3d1455926-svg · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ⚠ suspicious
174
总下载
0
收藏
1
当前安装
2
版本数
在 OpenClaw 中安装
/install humanize-ai-text-cp3d
功能描述
Detect and remove AI-generated writing patterns to rewrite text for a more natural, human-written style with diagnostic reports and version comparison.
使用说明 (SKILL.md)

\r \r

Humanize AI Text\r

\r Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written.\r \r Based on Wikipedia's comprehensive "Signs of AI writing" guide.\r \r

Features\r

\r

  • AI Detection: Identifies 16 pattern categories of AI-generated text\r
  • Pattern Categories:\r
    • Citation bugs\r
    • Knowledge-cutoff phrases\r
    • Chatbot artifacts\r
    • Markdown/code remnants\r
    • AI-specific vocabulary\r
    • Filler phrases\r
    • Punctuation quirks\r
    • Stylistic parallelisms\r
    • Inflated symbolism\r
    • Promotional language\r
    • Superficial -ing analyses\r
    • Vague attributions\r
    • Em dash overuse\r
    • Rule of three\r
    • Negative parallelisms\r
    • Excessive conjunctive phrases\r \r
  • Diagnostic Reports: Generate detailed AI detection reports\r
  • Text Transformation: Rewrite text to sound more human\r
  • Comparison Mode: Compare original vs humanized versions\r \r

Usage\r

\r

Detect AI Writing\r

\r

# Basic detection\r
python skills/humanize-ai-text/scripts/detect.py text.txt\r
\r
# JSON output\r
python skills/humanize-ai-text/scripts/detect.py text.txt -j\r
\r
# Score only\r
python skills/humanize-ai-text/scripts/detect.py text.txt -s\r
\r
# Pipe text directly\r
echo "This text might be AI-generated" | python skills/humanize-ai-text/scripts/detect.py\r
```\r
\r
### Transform Text\r
\r
```bash\r
# Basic transformation\r
python skills/humanize-ai-text/scripts/transform.py text.txt\r
\r
# Output to file\r
python skills/humanize-ai-text/scripts/transform.py text.txt -o clean.txt\r
\r
# Aggressive mode (more changes)\r
python skills/humanize-ai-text/scripts/transform.py text.txt -a\r
\r
# Quiet mode (no progress output)\r
python skills/humanize-ai-text/scripts/transform.py text.txt -q\r
```\r
\r
### Compare Versions\r
\r
```bash\r
# Compare original and transformed\r
python skills/humanize-ai-text/scripts/compare.py text.txt\r
\r
# Compare and save result\r
python skills/humanize-ai-text/scripts/compare.py text.txt -o document_v2.txt\r
```\r
\r
## Installation\r
\r
The skill is already installed. To use it, ensure you have Python 3 installed.\r
\r
### Dependencies\r
\r
No external dependencies required - uses Python standard library.\r
\r
## Pattern Detection\r
\r
The detection script identifies these AI writing patterns:\r
\r
### 1. Citation Bugs\r
- Fake or unverifiable sources\r
- "According to experts" without specifics\r
- Generic study references\r
\r
### 2. Knowledge Cutoff\r
- "As of my last update"\r
- "I don't have real-time information"\r
- Date-stamped limitations\r
\r
### 3. Chatbot Artifacts\r
- "I'd be happy to help"\r
- "Great question!"\r
- "Let me break this down"\r
- Excessive hedging\r
\r
### 4. AI Vocabulary\r
- "delve into"\r
- "testament to"\r
- "in conclusion"\r
- "it's worth noting"\r
- "important to understand"\r
\r
### 5. Filler Phrases\r
- Unnecessary introductions\r
- Redundant summaries\r
- Padding content\r
\r
### 6. Stylistic Issues\r
- Rule of three overuse\r
- Negative parallelisms\r
- Em dash overuse\r
- Excessive conjunctive phrases\r
\r
## Best Practices\r
\r
1. **Detect First**: Run detection before transformation\r
2. **Review Changes**: Always review transformed text\r
3. **Use Compare**: Compare versions to understand changes\r
4. **Iterate**: May need multiple passes for best results\r
5. **Custom Patterns**: Edit `patterns.json` to add custom detections\r
\r
## Customization\r
\r
### Add Custom Patterns\r
\r
Edit `skills/humanize-ai-text/scripts/patterns.json`:\r
\r
```json\r
{\r
  "custom_patterns": {\r
    "my_pattern": {\r
      "regex": "pattern_here",\r
      "replacement": "replacement_text",\r
      "description": "What this pattern detects"\r
    }\r
  }\r
}\r
```\r
\r
### Batch Processing\r
\r
Process multiple files:\r
\r
```bash\r
for f in *.md; do\r
  python skills/humanize-ai-text/scripts/detect.py "$f" -s\r
  python skills/humanize-ai-text/scripts/transform.py "$f" -a -o "${f%.md}_clean.md" -q\r
done\r
```\r
\r
## Output Formats\r
\r
### Detection Output\r
\r
```\r
AI Detection Report\r
===================\r
File: text.txt\r
AI Probability: 73%\r
\r
Patterns Detected:\r
- AI Vocabulary: 12 instances\r
- Filler Phrases: 8 instances\r
- Stylistic Parallelisms: 5 instances\r
...\r
```\r
\r
### Transformation Output\r
\r
```\r
Original: "I'd be happy to delve into this important topic."\r
Humanized: "Let's explore this topic."\r
```\r
\r
## Security Notes\r
\r
- ✅ No external network calls\r
- ✅ All processing done locally\r
- ✅ No credential access\r
- ✅ Safe file operations only\r
- ✅ No data exfiltration\r
\r
## Integration\r
\r
### With Writing Workflow\r
\r
1. Write draft (AI-assisted or not)\r
2. Run detection to check AI score\r
3. Transform if score is high\r
4. Compare versions\r
5. Manual review and final edits\r
\r
### With Content Pipeline\r
\r
```bash\r
# In CI/CD or pre-commit hook\r
python skills/humanize-ai-text/scripts/detect.py content.md -s\r
# Fail if AI score > threshold\r
```\r
\r
## Troubleshooting\r
\r
### False Positives\r
\r
Some legitimate writing may trigger patterns. Review manually.\r
\r
### False Negatives\r
\r
AI models evolve. Update patterns.json regularly.\r
\r
### Encoding Issues\r
\r
Ensure files are UTF-8 encoded:\r
```bash\r
python skills/humanize-ai-text/scripts/detect.py file.txt --encoding utf-8\r
```\r
\r
## Examples\r
\r
### Example 1: Blog Post\r
\r
```bash\r
# Check AI score\r
python skills/humanize-ai-text/scripts/detect.py blog_post.md -s\r
# Output: AI Probability: 68%\r
\r
# Transform\r
python skills/humanize-ai-text/scripts/transform.py blog_post.md -o blog_post_clean.md -a\r
\r
# Compare\r
python skills/humanize-ai-text/scripts/compare.py blog_post.md -o blog_post_clean.md\r
```\r
\r
### Example 2: Email\r
\r
```bash\r
echo "I hope this email finds you well. I wanted to reach out regarding..." | \\r
  python skills/humanize-ai-text/scripts/detect.py\r
```\r
\r
### Example 3: Academic Writing\r
\r
```bash\r
# Detect AI patterns in paper\r
python skills/humanize-ai-text/scripts/detect.py paper.md -j > report.json\r
\r
# Transform with conservative settings\r
python skills/humanize-ai-text/scripts/transform.py paper.md -o paper_clean.md\r
```\r
\r
## Resources\r
\r
- Wikipedia: "Signs of AI writing"\r
- Original research on AI text detection\r
- Community pattern contributions\r
\r
---\r
\r
*For more info, visit: https://clawhub.ai/biostartechnology/humanizer*\r
安全使用建议
Do not assume the skill is usable as-is. SKILL.md instructs running Python scripts (detect.py, transform.py, compare.py) and editing patterns.json, but the package contains only README.md and SKILL.md — the executable scripts are missing. This can mean a packaging error, an incomplete upload, or that the real code is fetched from elsewhere (not shown). Before installing or running anything: 1) Request the missing source files from the publisher or a full repository link; 2) If you obtain the scripts, review them (or run them in an isolated sandbox) to verify there are truly no network calls or secret access; 3) Prefer skills with a verifiable source (homepage or repo) and explicit install artifacts; 4) Be cautious about running arbitrary Python scripts from unknown authors even if they claim 'no network calls.' If you cannot verify the code, do not grant this skill execution privileges or include it in automated pipelines.
功能分析
Type: OpenClaw Skill Name: humanize-ai-text-cp3d Version: 1.0.1 The skill bundle provides documentation and instructions for a text processing utility designed to identify and remove AI-generated writing patterns. The SKILL.md and README.md files describe legitimate features such as AI detection, text transformation, and version comparison using local Python scripts. There is no evidence of malicious intent, prompt injection, data exfiltration, or unauthorized system access in the provided files. The instructions are consistent with the stated purpose and follow standard OpenClaw skill conventions.
能力评估
Purpose & Capability
The name and description (detect and rewrite AI-like text) match the claimed behavior, but the SKILL.md repeatedly references Python scripts (detect.py, transform.py, compare.py) and a patterns.json that are not present in the file manifest. The skill also declares Python3 is required in metadata even though no scripts are included—this mismatch suggests the distributed bundle is incomplete or mispackaged.
Instruction Scope
Runtime instructions tell the agent to execute local Python scripts, edit patterns.json, and process arbitrary files — actions that require code that isn't bundled. While the described actions (analyze and rewrite files) are within the stated purpose, the SKILL.md gives explicit commands that would run arbitrary Python code if those scripts existed. The instructions also assert 'No external network calls' and 'No credentials' but those are claims in prose and cannot be verified because the referenced scripts are missing.
Install Mechanism
There is no install spec and no code will be written to disk by an installer (instruction-only), which is low installation risk. However, the skill claims the tooling is 'already installed' and depends on Python scripts that are absent—this is an integrity/packaging issue rather than an install-method risk.
Credentials
The skill requests no environment variables or credentials, which is proportional to a text-processing tool. There is no evidence of requests for unrelated secrets or config paths in the provided files.
Persistence & Privilege
The skill does not request persistent/always-on privileges and uses default autonomous invocation settings. There is no indication it attempts to modify other skills or system-wide agent settings in the provided files.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install humanize-ai-text-cp3d
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /humanize-ai-text-cp3d 触发
  4. 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
v1.0.1
No user-facing changes in this version. - No file or documentation changes detected. - Version remains the same as previous (1.0.0). - No updates to features, usage, or documentation.
v1.0.0
Initial release with comprehensive AI text detection and humanization features. - Detects 16 categories of AI-generated writing patterns in text. - Generates detailed AI detection reports, including scores and pattern counts. - Automatically rewrites AI-like text to sound more natural and human. - Provides side-by-side comparison between original and humanized text versions. - Fully local processing using Python 3; no external dependencies or network calls required. - Supports pattern customization and batch processing.
元数据
Slug humanize-ai-text-cp3d
版本 1.0.1
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 2
常见问题

Humanize Ai Text 是什么?

Detect and remove AI-generated writing patterns to rewrite text for a more natural, human-written style with diagnostic reports and version comparison. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 174 次。

如何安装 Humanize Ai Text?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install humanize-ai-text-cp3d」即可一键安装,无需额外配置。

Humanize Ai Text 是免费的吗?

是的,Humanize Ai Text 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Humanize Ai Text 支持哪些平台?

Humanize Ai Text 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Humanize Ai Text?

由 cp3d1455926-svg(@cp3d1455926-svg)开发并维护,当前版本 v1.0.1。

💬 留言讨论