Humanize
PassAudited by VirusTotal on May 12, 2026.
Overview
Type: OpenClaw Skill Name: humanize Version: 1.0.0 The OpenClaw skill bundle is benign. All files, including the `SKILL.md` instructions for the AI agent, are focused solely on text transformation and style guidance to remove AI writing patterns. There is no executable code, no instructions for data exfiltration, malicious execution, persistence, or any form of prompt injection aiming to subvert the agent's intended purpose or security. The instructions are purely descriptive of the desired output style.
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.
Text revised with this skill may appear more personally written than it really is.
The skill openly aims to make AI-sounding text read as human-written, which is purpose-aligned but can affect how readers perceive authorship or authenticity.
Remove signs of AI-generated writing. ... rewriting text to sound more natural and human-written.
Use it for legitimate editing, but review the result for accuracy, authorship expectations, and any required AI-use disclosure.
The edited text could imply personal views or experiences that the actual author did not intend to claim.
The skill encourages adding voice and first-person language, which can be useful for style but may over-personalize text if the output is not carefully reviewed.
- **Have opinions** - react to facts, don't just report - **Use "I" when appropriate** - first person signals a real person
Check any added opinions, feelings, or first-person statements before sending or publishing.