Humanize

Name: Humanize
Author: humanizerai

humanizerai/agent-skills

3.5k installs
38 repo stars
Updated February 5, 2026
humanizerai/agent-skills

humanize is an agent skill that rewrites AI-generated text via the HumanizerAI API with configurable intensity and reports detector score improvements plus credit usage.

About

humanize is a HumanizerAI agent skill that transforms AI-generated prose into more natural writing by calling the HumanizerAI REST API when users invoke /humanize. It parses arguments for input text and an optional --intensity flag defaulting to medium, with light for subtle edits, medium for balanced rewrites, and aggressive labeled Bypass for strict detectors like GPTZero, Turnitin, and Originality.ai. The POST endpoint is https://humanizerai.com/api/v1/humanize with Bearer HUMANIZERAI_API_KEY, sending text and intensity in JSON. Responses should present before-and-after detector scores, words processed, credits remaining, the humanized text, and a recommendation based on the final score. Credit usage charges one credit per word while detection checks are free, with balances viewable at humanizerai.com/dashboard. Error handling covers insufficient credits with needed versus available counts, invalid API keys pointing to account setup, and rate limits suggesting wait or Business plan upgrade. The skill is user-invocable with argument hints for text and intensity, giving agent workflows a standardized humanization step with transparent scoring and credit accounting.

Calls HumanizerAI POST /api/v1/humanize with text and light, medium, or aggressive intensity.
Parses /humanize arguments including optional --intensity flag defaulting to medium.
Presents before-and-after detector scores, word count, credits remaining, and humanized output.
One credit per word charged; detection checks are free per documented pricing.
Handles insufficient credits, invalid API keys, and rate limit errors with dashboard links.

Humanize by the numbers

3,494 all-time installs (skills.sh)
+167 installs in the week ending Aug 4, 2026 (Skillselion tracking)
Ranked #229 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
Security screen: MEDIUM risk (skills.sh audit)
Data as of Aug 4, 2026 (Skillselion catalog sync)

At a glance

humanize capabilities & compatibility

1 credit per word via HumanizerAI API

Capabilities: argument parsing for text and intensity flag · humanizerai api humanization requests · score and credit usage reporting · error handling for credits, api keys, and rate l
Use cases: copywriting · translation
Pricing: Bring your own API key

From the docs

What humanize says it does

Transform AI-generated text into natural, human-like content that bypasses AI detectors

SKILL.md

1 word = 1 credit

SKILL.md

npx skills add https://github.com/humanizerai/agent-skills --skill humanize

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

[![Listed on Skillselion](https://skillselion.com/badge/skills/humanizerai/agent-skills/humanize.svg)](https://skillselion.com/skills/humanizerai/agent-skills/humanize)

Installs	3.5k
repo stars	★ 38
Security audit	1 / 3 scanners passed
Last updated	February 5, 2026
Repository	humanizerai/agent-skills ↗

How do I rewrite AI-generated text so it reads naturally and scores lower on detectors like GPTZero or Turnitin?

Rewrite AI-generated text through the HumanizerAI API with light, medium, or aggressive intensity to reduce detector scores while reporting credits used.

Who is it for?

Writers polishing AI drafts who need API-driven humanization with intensity control and credit tracking.

Skip if: Skip when you need factual verification, citation editing, or humanization without a HumanizerAI API key.

When should I use this skill?

User runs /humanize with text and optional --intensity light, medium, or aggressive.

What you get

Humanized text with before-and-after detector scores, words processed count, and remaining credit balance.

Humanized text output
Detector score before-and-after report

By the numbers

Supports three intensity levels: light, medium, and aggressive
Credits consumption is based on input word count

Files

SKILL.mdMarkdownGitHub ↗

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 flag 2. Call the HumanizerAI API to humanize the text 3. Present the humanized text with before/after scores 4. 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_KEY
Content-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 Credits

If the user doesn't have enough credits: 1. Show how many credits are needed vs available 2. Direct them to https://humanizerai.com/dashboard to top up