Claude Agent Skill · by Humanizerai

Humanize

Install Humanize skill for Claude Code from humanizerai/agent-skills.

Install
Terminal · npx
$npx skills add https://github.com/humanizerai/agent-skills --skill humanize
Works with Paperclip

How Humanize fits into a Paperclip company.

Humanize drops into any Paperclip agent that handles this kind of work. Assign it to a specialist inside a pre-configured PaperclipOrg company and the skill becomes available on every heartbeat — no prompt engineering, no tool wiring.

S
SaaS FactoryPaired

Pre-configured AI company — 18 agents, 18 skills, one-time purchase.

$27$59
Explore pack
Source file
SKILL.md91 lines
Expand
---name: humanizedescription: Transform AI-generated text into natural, human-like content that bypasses AI detectors like GPTZero, Turnitin, and Originality.ai. Uses credits based on word count.user-invocable: trueargument-hint: "[text to humanize] [--intensity light|medium|aggressive]"allowed-tools: WebFetch--- # Humanize AI Text Transform AI-generated content into natural, human-like writing using the HumanizerAI API. ## How It Works When the user invokes `/humanize`, you should: 1. Parse $ARGUMENTS for text and optional --intensity flag2. Call the HumanizerAI API to humanize the text3. Present the humanized text with before/after scores4. Show remaining credits ## Parsing Arguments The user may provide:- Just text: `/humanize [their text]`- With intensity: `/humanize --intensity aggressive [their text]` Default intensity is `medium`. ## Intensity Levels | Value | Name | Description | Best For ||-------|------|-------------|----------|| `light` | Light | Subtle changes, preserves style | Already-edited text, low AI scores || `medium` | Medium | Balanced rewrites (default) | Most use cases || `aggressive` | Bypass | Maximum bypass mode | High AI scores, strict detectors | ## API Call Make a POST request to `https://humanizerai.com/api/v1/humanize`: ```Authorization: Bearer $HUMANIZERAI_API_KEYContent-Type: application/json {  "text": "<user's text>",  "intensity": "medium"}``` ## Response Format Present results like this: ```## Humanization Complete **Score:** X → Y (improvement)**Words Processed:** N**Credits Remaining:** X ---### Humanized Text [The humanized text] --- [Recommendation based on final score]``` ## Credit Usage - 1 word = 1 credit- Detection is free- Check credits at https://humanizerai.com/dashboard ## Error Handling ### Insufficient CreditsIf the user doesn't have enough credits:1. Show how many credits are needed vs available2. Direct them to https://humanizerai.com/dashboard to top up ### Invalid API Key1. Check HUMANIZERAI_API_KEY environment variable2. Direct to https://humanizerai.com to get a key ### Rate LimitIf rate limited, suggest waiting or upgrading to Business plan.