Analyzes text to detect AI generation using HumanizerAI API. Returns overall score (0-100), verdict, word count, and metrics like perplexity, burstiness, readability. Useful for content review before publishing.
npx claudepluginhub joshuarweaver/cascade-content-creation-misc-2 --plugin humanizerai-agent-skillsThis skill is limited to using the following tools:
Analyze text to determine if it was written by AI using the HumanizerAI API.
Humanizes AI-generated text to bypass detectors like GPTZero, Turnitin, and Originality.ai using HumanizerAI API. Invoke via /humanize with optional intensity for natural rewrites and score reports.
Detects and removes AI-generated writing patterns like lexical signals and statistical regularities from text, producing natural human-sounding output while preserving meaning and facts.
Detects AI-generated writing patterns like corporate buzzwords, formulaic transitions, vague intensifiers, and structural overuse; suggests authentic human-like replacements. Useful for reviewing, editing, or generating prose, docs, and communications.
Share bugs, ideas, or general feedback.
Analyze text to determine if it was written by AI using the HumanizerAI API.
When the user invokes /detect-ai, you should:
Make a POST request to https://humanizerai.com/api/v1/detect:
Authorization: Bearer $HUMANIZERAI_API_KEY
Content-Type: application/json
{
"text": "<user's text>"
}
The API returns JSON like this:
{
"score": {
"overall": 82,
"perplexity": 96,
"burstiness": 15,
"readability": 23,
"satPercent": 3,
"simplicity": 35,
"ngramScore": 8,
"averageSentenceLength": 21
},
"wordCount": 82,
"sentenceCount": 4,
"verdict": "ai"
}
IMPORTANT: The main AI score is score.overall (not score directly). This is the score to display to the user.
## AI Detection Results
**Score:** [score.overall]/100 ([verdict])
**Words Analyzed:** [wordCount]
### Metrics
- Perplexity: [score.perplexity]
- Burstiness: [score.burstiness]
- Readability: [score.readability]
- N-gram Score: [score.ngramScore]
### Recommendation
[Based on score.overall, suggest whether to humanize]
If the API call fails: