Humanizer
PassAudited by ClawScan on May 1, 2026.
Overview
This appears to be a transparent writing-editing skill with no credential, persistence, or broad system access, though users should use the AI-text masking features responsibly and verify the optional CLI install source.
This skill looks safe to install as a text-editing aid. Be mindful that it can make AI-assisted writing harder to identify, and only use that capability where it is allowed. If you use the optional standalone CLI rather than just the OpenClaw skill, verify the GitHub source before installing.
Findings (2)
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 skill can help AI-assisted text look more human, which may conflict with school, workplace, publishing, or platform disclosure rules if misused.
The skill is explicitly designed to reduce visible AI-writing signals. This is disclosed and central to the purpose, but users should recognize the authorship-disclosure implications.
Your goal: make writing sound like a specific human wrote it ... Use when asked to humanize text, de-AI writing ... score text for AI detection
Use it as an editing aid and follow any applicable rules about disclosing AI assistance.
If the user chooses the CLI path, they will be trusting the referenced repository and npm-installed development dependencies.
The optional standalone CLI setup instructs users to clone a remote repository and install npm packages. This is user-directed and expected for a CLI, but it is still a supply-chain step users should verify.
git clone https://github.com/brandonwise/humanizer.git cd humanizer npm install
Install the OpenClaw instruction-only skill if that is all you need; if using the CLI, verify the repository and review package changes before running npm install.