If you're dealing with AI detection tools flagging your content, this skill pipes text through HumanizerAI's API to rewrite it with a more natural voice. You get three intensity levels (light, medium, aggressive) depending on how heavily the text needs reworking, and it shows before/after detector scores so you can see the shift. Uses a credit system at one credit per word, which adds up fast on longer pieces. The workflow is straightforward: paste text, pick intensity, get rewritten output. Honestly most useful if you're in academic or professional contexts where AI detectors are actually deployed, otherwise you're probably better off just editing manually.

install copies · 90 days. Times the install command was copied on this site in the last 90 days, bots filtered.
7
skills.sh installs
4.1K
GitHub stars
55
last updated
Aug 21, 2026

Install

$ npx -y skills add humanizerai/agent-skills --skill humanize --agent claude-code

Installs into .claude/skills of the current project.

Files

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

ValueNameDescriptionBest For
lightLightSubtle changes, preserves styleAlready-edited text, low AI scores
mediumMediumBalanced rewrites (default)Most use cases
aggressiveBypassMaximum bypass modeHigh 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

Sponsors

Details

Repository
github.com/humanizerai/agent-skills
Categories
AI & Agent Building, Office & Documents

More from humanizerai/agent-skills

All 6
1github avatargsap-framer-scroll-animationgithub/awesome-copilotUse this skill whenever the user wants to build scroll animations, scroll effects, parallax, scroll-triggered reveals, pinned sections, horizontal scroll, text 4Kskills.sh installs
2mongodb avatarmongodb-atlas-stream-processingmongodb/agent-skillsManages MongoDB Atlas Stream Processing (ASP) workflows. Handles workspace provisioning, data source/sink connections, processor lifecycle operations, debugging3.9Kskills.sh installs
3github avatareval-driven-devgithub/awesome-copilotImprove AI application with evaluation-driven development. Define eval criteria, instrument the application, build golden datasets, observe and evaluate applica3.9Kskills.sh installs
4openai avatarchatgpt-appsopenai/skillsBuild, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, regist3.5Kskills.sh installs
5elastic avatarkibana-anomaly-detectionelastic/agent-skillsElastic ML anomaly detection skill — investigation/RCA, score explanation, job operations (create, datafeed, start/stop, results), and troubleshooting (missing 3.4Kskills.sh installs
6openclaw avatarautoreviewopenclaw/agent-skillsRun a structured code review (Codex default, optional Claude, Pi, Droid, Copilot, or OpenCode) as a closeout check on a local or PR branch before commit or ship3.1Kskills.sh installs