Humanize
Polish AI-drafted blogs, newsletters, and landing copy so it reads naturally and shows lower scores on common AI detectors before you publish.
Overview
Humanize is an agent skill most often used in Grow (also Launch SEO and Validate landing) that rewrites AI-generated text via the HumanizerAI API with selectable intensity and reports detector scores before you publish.
Install
npx skills add https://github.com/humanizerai/agent-skills --skill humanizeWhat is this skill?
- User-invocable `/humanize` command with optional `--intensity light|medium|aggressive` (default medium)
- Three intensity modes: light (subtle), medium (balanced), aggressive bypass for strict detectors
- POST to HumanizerAI API with Bearer `HUMANIZERAI_API_KEY` and credit-based word usage
- Presents humanized text with before/after detector scores and remaining credits
- Targets detectors such as GPTZero, Turnitin, and Originality.ai per skill description
- 3 intensity levels: light, medium, and aggressive (bypass)
- Default intensity is medium when `--intensity` is omitted
Adoption & trust: 2.1k installs on skills.sh; 24 GitHub stars; 1/3 security scanners passed (skills.sh audits).
What problem does it solve?
You have fast AI drafts for blogs or landing pages, but they still read robotic and score high on detectors right when you need trustworthy, publishable copy.
Who is it for?
Indie creators and one-person marketing stacks who already use agents to draft copy and want a quick API pass before shipping content or SEO pages.
Skip if: Academic or compliance contexts where evading integrity checks is prohibited, or anyone who needs offline, keyless rewriting without a HumanizerAI subscription.
When should I use this skill?
User invokes `/humanize` with text to transform, optionally with `--intensity light|medium|aggressive`.
What do I get? / Deliverables
You get humanized prose with before/after scores and a credits readout, ready to paste into your site, newsletter, or ads without another manual rewrite pass.
- Humanized text body formatted for paste into CMS or email tools
- Before/after AI detector scores as shown in the skill response template
- Remaining HumanizerAI credits after the request
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is Grow because solo builders most often humanize copy at the content-production step—after drafting with an agent and before distribution—not during initial ideation or infra work. Content subphase matches rewriting finished prose for audience-facing channels rather than building product code or running analytics dashboards.
Where it fits
Humanize a weekly newsletter draft after your agent wrote it so subscriber-facing tone stays casual and detector scores drop.
Run aggressive intensity on long-form SEO articles generated in bulk before they go live on your marketing site.
Soften hero and feature blurbs on a validation landing page so early visitors do not bounce on obviously synthetic phrasing.
Rewrite onboarding and lifecycle emails that were templated by an agent while keeping light intensity to preserve your brand voice.
How it compares
Use as a hosted rewrite-and-score integration, not a local style-guide or brainstorming skill that plans what to say.
Common Questions / FAQ
Who is humanize for?
Solo and indie builders who generate marketing, lifecycle, or landing copy with AI agents and need natural-sounding text plus detector feedback before publishing.
When should I use humanize?
Use it when finalizing Grow content (newsletters, blog posts), Launch SEO or distribution copy, or Validate landing page text after drafting—especially when detector scores are still high and you want light, medium, or aggressive rewriting via `/humanize`.
Is humanize safe to install?
The skill calls HumanizerAI over the network with your API key and sends full text payloads; review the Security Audits panel on this Prism page and your provider’s data policy before pasting sensitive or customer data.
SKILL.md
READMESKILL.md - Humanize
# 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 ### Invalid API Key 1. Check HUMANIZERAI_API_KEY environment variable 2. Direct to https://humanizerai.com to get a key ### Rate Limit If rate limited, suggest waiting or upgrading to Business plan.