detect-ai
starsforks
How to install detect-ai?
humanizerai/agent-skills/detect-ai
$npx -y skills add humanizerai/agent-skills --skill detect-aiAnalyze text to detect if it was written by AI. Returns a score from 0-100 with detailed metrics. Use when checking content before publishing or submitting.
SKILL.md
| 1 | # Detect AI Content |
| 2 | |
| 3 | Analyze text to determine if it was written by AI using the HumanizerAI API. |
| 4 | |
| 5 | ## How It Works |
| 6 | |
| 7 | When the user invokes `/detect-ai`, you should: |
| 8 | |
| 9 | 1. Extract the text from $ARGUMENTS |
| 10 | 2. Call the HumanizerAI API to analyze the text |
| 11 | 3. Present the results in a clear, actionable format |
| 12 | |
| 13 | ## API Call |
| 14 | |
| 15 | Make a POST request to `https://humanizerai.com/api/v1/detect`: |
| 16 | |
| 17 | ``` |
| 18 | Authorization: Bearer $HUMANIZERAI_API_KEY |
| 19 | Content-Type: application/json |
| 20 | |
| 21 | { |
| 22 | "text": "<user's text>" |
| 23 | } |
| 24 | ``` |
| 25 | |
| 26 | ## API Response Format |
| 27 | |
| 28 | The API returns JSON like this: |
| 29 | |
| 30 | ```json |
| 31 | { |
| 32 | "score": { |
| 33 | "overall": 82, |
| 34 | "perplexity": 96, |
| 35 | "burstiness": 15, |
| 36 | "readability": 23, |
| 37 | "satPercent": 3, |
| 38 | "simplicity": 35, |
| 39 | "ngramScore": 8, |
| 40 | "averageSentenceLength": 21 |
| 41 | }, |
| 42 | "wordCount": 82, |
| 43 | "sentenceCount": 4, |
| 44 | "verdict": "ai" |
| 45 | } |
| 46 | ``` |
| 47 | |
| 48 | **IMPORTANT:** The main AI score is `score.overall` (not `score` directly). This is the score to display to the user. |
| 49 | |
| 50 | ## Present Results Like This |
| 51 | |
| 52 | ``` |
| 53 | ## AI Detection Results |
| 54 | |
| 55 | **Score:** [score.overall]/100 ([verdict]) |
| 56 | **Words Analyzed:** [wordCount] |
| 57 | |
| 58 | ### Metrics |
| 59 | - Perplexity: [score.perplexity] |
| 60 | - Burstiness: [score.burstiness] |
| 61 | - Readability: [score.readability] |
| 62 | - N-gram Score: [score.ngramScore] |
| 63 | |
| 64 | ### Recommendation |
| 65 | [Based on score.overall, suggest whether to humanize] |
| 66 | ``` |
| 67 | |
| 68 | ## Score Interpretation (use score.overall) |
| 69 | |
| 70 | - 0-20: Human-written content |
| 71 | - 21-40: Likely human, minor AI patterns |
| 72 | - 41-60: Mixed signals, could be either |
| 73 | - 61-80: Likely AI-generated |
| 74 | - 81-100: Highly likely AI-generated |
| 75 | |
| 76 | ## Error Handling |
| 77 | |
| 78 | If the API call fails: |
| 79 | 1. Check if HUMANIZERAI_API_KEY is set |
| 80 | 2. Suggest the user get an API key at https://humanizerai.com |
| 81 | 3. Provide the error message for debugging |
People who liked this also viewed
6 picksType
- seo-auditWhen the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tagSkillsJul 2026
- copywritingWhen the user wants to write, rewrite, or improve marketing copy for any page — including homepage, landing pages, pricing pages, feature pages, about pages, or product pages. Also use when the user sSkillsJul 2026
- marketing-psychologyWhen the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental models,' 'cognitive bias,' 'persuasion,'SkillsJul 2026
- content-strategyWhen the user wants to plan a content strategy, decide what content to create, or figure out what topics to cover. Also use when the user mentions "content strategy," "what should I write about," "conSkillsJul 2026
- programmatic-seoWhen the user wants to create SEO-driven pages at scale using templates and data. Also use when the user mentions "programmatic SEO," "template pages," "pages at scale," "directory pages," "location pSkillsJul 2026
- marketing-ideasWhen the user needs marketing ideas, inspiration, or strategies for their SaaS or software product. Also use when the user asks for 'marketing ideas,' 'growth ideas,' 'how to market,' 'marketing stratSkillsJul 2026
