Humanizer
AdvisoryAudited by Static analysis on Apr 30, 2026.
Overview
No suspicious patterns detected.
Findings (0)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
The agent may edit files as part of humanizing text, so unintended changes are possible if the target file or scope is unclear.
The skill is allowed to read, search, write, and edit files. That fits a writing-editing skill, but it means it could change local documents if invoked on them.
allowed-tools:\n - Read\n - Write\n - Edit\n - Grep\n - Glob\n - AskUserQuestion
Use it on specific documents or pasted text, and review diffs or rewritten output before accepting changes.
Using the skill could make AI-assisted text appear more human-authored than it is, which may matter in academic, professional, or disclosure-sensitive settings.
The skill openly aims to make text appear less AI-generated. This is disclosed and central to the purpose, but it can affect reader trust or expectations about authorship.
Remove signs of AI-generated writing from text... make it sound more natural and human-written.
Use the skill transparently where disclosure or authorship rules apply, and verify that edits preserve the intended meaning and voice.