$npx -y skills add humanizerai/agent-skills --skill humanizeTransform AI-generated text into natural, human-like content that bypasses AI detectors like GPTZero, Turnitin, and Originality.ai. Uses credits based on word count.
| 1 | # Humanize AI Text |
| 2 | |
| 3 | Transform AI-generated content into natural, human-like writing using the HumanizerAI API. |
| 4 | |
| 5 | ## How It Works |
| 6 | |
| 7 | When the user invokes `/humanize`, you should: |
| 8 | |
| 9 | 1. Parse $ARGUMENTS for text and optional --intensity flag |
| 10 | 2. Call the HumanizerAI API to humanize the text |
| 11 | 3. Present the humanized text with before/after scores |
| 12 | 4. Show remaining credits |
| 13 | |
| 14 | ## Parsing Arguments |
| 15 | |
| 16 | The user may provide: |
| 17 | - Just text: `/humanize [their text]` |
| 18 | - With intensity: `/humanize --intensity aggressive [their text]` |
| 19 | |
| 20 | Default intensity is `medium`. |
| 21 | |
| 22 | ## Intensity Levels |
| 23 | |
| 24 | | Value | Name | Description | Best For | |
| 25 | |-------|------|-------------|----------| |
| 26 | | `light` | Light | Subtle changes, preserves style | Already-edited text, low AI scores | |
| 27 | | `medium` | Medium | Balanced rewrites (default) | Most use cases | |
| 28 | | `aggressive` | Bypass | Maximum bypass mode | High AI scores, strict detectors | |
| 29 | |
| 30 | ## API Call |
| 31 | |
| 32 | Make a POST request to `https://humanizerai.com/api/v1/humanize`: |
| 33 | |
| 34 | ``` |
| 35 | Authorization: Bearer $HUMANIZERAI_API_KEY |
| 36 | Content-Type: application/json |
| 37 | |
| 38 | { |
| 39 | "text": "<user's text>", |
| 40 | "intensity": "medium" |
| 41 | } |
| 42 | ``` |
| 43 | |
| 44 | ## Response Format |
| 45 | |
| 46 | Present results like this: |
| 47 | |
| 48 | ``` |
| 49 | ## Humanization Complete |
| 50 | |
| 51 | **Score:** X → Y (improvement) |
| 52 | **Words Processed:** N |
| 53 | **Credits Remaining:** X |
| 54 | |
| 55 | --- |
| 56 | ### Humanized Text |
| 57 | |
| 58 | [The humanized text] |
| 59 | |
| 60 | --- |
| 61 | |
| 62 | [Recommendation based on final score] |
| 63 | ``` |
| 64 | |
| 65 | ## Credit Usage |
| 66 | |
| 67 | - 1 word = 1 credit |
| 68 | - Detection is free |
| 69 | - Check credits at https://humanizerai.com/dashboard |
| 70 | |
| 71 | ## Error Handling |
| 72 | |
| 73 | ### Insufficient Credits |
| 74 | If the user doesn't have enough credits: |
| 75 | 1. Show how many credits are needed vs available |
| 76 | 2. Direct them to https://humanizerai.com/dashboard to top up |
| 77 | |
| 78 | ### Invalid API Key |
| 79 | 1. Check HUMANIZERAI_API_KEY environment variable |
| 80 | 2. Direct to https://humanizerai.com to get a key |
| 81 | |
| 82 | ### Rate Limit |
| 83 | If rate limited, suggest waiting or upgrading to Business plan. |