humanizer

Purpose

Review prose against 35 documented AI-writing patterns and revise it for naturalness, specificity, rhythm, and voice while protecting meaning and quotations.

Task categories

Project phases

Routing behavior

Trigger conditions

• The request specifically concerns editing.
• The request specifically concerns voice.

Anti-trigger conditions

• Need fact-checking or source research
• Need to conceal prohibited AI use or misrepresent authorship

Inputs & outputs

Required inputs

A concrete, bounded request plus the files, data, account, or project context explicitly required by this component.

Produced outputs

The component's documented artifact, answer, command result, graph record, media deliverable, or external action. Review it before relying on it.

Dependencies & services

Dependencies

Compatible agent host

Required tools

Compatible agent host; Node.js for npx skills installation

Required services

Only the chosen model/agent provider

Limitations

• Style judgments remain subjective
• A human review is still required
• It does not verify facts or citations

Security notes

The skill edits text through the host agent; review the diff and do not use it to evade disclosure, academic, or platform rules.