detect-ai
Detect AI analyzes text to identify AI authorship, returning a confidence score alongside linguistic metrics like perplexity and burstiness. Use it to review content before publication or submission.
Detect AI identifies whether text was written by an AI system using HumanizerAI's analysis engine.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-02-05
Detect AI identifies whether text was written by an AI system using HumanizerAI's analysis engine. Detect AI analyzes text to identify AI authorship, returning a confidence score alongside linguistic metrics like perplexity and burstiness. Use it to review content before publication or submission.
Use it when
- detect-ai examines linguistic metrics including perplexity and burstiness to understand AI likelihood.
- Yes, detect-ai verifies content authenticity by analyzing whether text was written by AI or a human.
Verify before relying
Read SKILL.md below before installing (1 file). Open directory: indexed for reading, not audited.
Install
humanizerai/agent-skills/detect-ai
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How does detect-ai check if text is AI generated?
detect-ai analyzes your text to identify AI authorship by examining linguistic patterns and returning a confidence score. The skill evaluates metrics like perplexity and burstiness to determine the likelihood that an AI wrote the content, helping you verify authenticity before publishing or submitting.
What metrics does detect-ai use to analyze text?
detect-ai examines linguistic metrics including perplexity and burstiness to understand AI likelihood. These measurements help the skill assess writing patterns and generate a confidence score that indicates whether the text was likely written by artificial intelligence or by a human author.
Can detect-ai verify if content is human or AI written?
Yes, detect-ai verifies content authenticity by analyzing whether text was written by AI or a human. The skill processes your submission and returns both a confidence score and detailed text metrics, allowing you to confirm human authorship before publication or content submission.
When should I use detect-ai to scan text for AI patterns?
Use detect-ai before publishing or submitting content when you need to verify human authorship. The skill is designed to detect AI-generated content in submissions, helping you identify machine-generated text patterns and ensure your published work meets authenticity requirements.
What does detect-ai's confidence score tell me?
detect-ai's confidence score indicates the likelihood that artificial intelligence wrote the analyzed text. Combined with linguistic metrics like perplexity and burstiness, this score helps you understand the AI probability level and make informed decisions about content authenticity before publishing.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Detect AI Content
Analyze text to determine if it was written by AI using the HumanizerAI API.
How It Works
When the user invokes /detect-ai, you should:
- Extract the text from $ARGUMENTS
- Call the HumanizerAI API to analyze the text
- Present the results in a clear, actionable format
API Call
Make a POST request to https://humanizerai.com/api/v1/detect:
Authorization: Bearer $HUMANIZERAI_API_KEY
Content-Type: application/json
{
"text": "<user's text>"
}
API Response Format
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
(truncated - see the full file via the links below)
File tree — 1 file
skills/detect-ai/SKILL.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Detect whether text was written by AI before publishing”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Humanize rewrites AI-generated content to read naturally and evade detection systems. Choose from light, medium, or aggressive intensity modes depending on your needs, with credit usage based on word count.
humanize transforms machine-generated content into natural-sounding text by identifying and eliminating 16 common AI patterns—from overused buzzwords and mechanical connectors to uniform paragraph structure and excessive passive voice. The skill applies a structured workflow to detect, prune, vary, and personalize text, then verifies results against AI detectors and conversational authenticity.
Follow-up writes re-engagement emails for prospects who haven't responded, adapting tone and strategy based on timing. It uses three distinct frameworks—The Bump for early nudges, The Value-Add for mid-sequence pivots, and The Breakup for final attempts—each calibrated to feel natural rather than needy.
Cold Email generates targeted outreach messages using three proven copywriting frameworks—AIDA, PAS, and BAB—to maximize engagement. It enforces reply-friendly best practices including strict word limits, personalized openers, and single clear calls-to-action while eliminating template filler.
Text Human strips AI surface patterns and applies domain-fit human style to source code, documentation, articles, and chat text. It detects context automatically, runs a two-pass model to remove validated AI tells and inject natural phrasing, and surfaces behavior-changing issues for review rather than auto-editing.
word-stats delivers immediate text metrics including word and character counts, reading and speaking time estimates, plus word-level insights like unique word percentage and sentence structure breakdowns. Input your text and receive clean, table-formatted results without prompts or extra commentary.
More skills humanizer-ru (MIT) · readability (MIT) · humanizer (MIT) · Humanizer (GPL-3.0) · humanize-ig (MIT)