← Back to Skills Marketplace
Humanizer
by
Nissan Dookeran
· GitHub ↗
· v2.2.0
· MIT-0
431
Downloads
0
Stars
0
Active Installs
4
Versions
Install in OpenClaw
/install reddi-humanizer
Description
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comp...
Usage Guidance
This skill appears internally consistent for editing text: it asks the agent to detect AI patterns and rewrite prose, and it declares no network or credential access. Two practical cautions: (1) The skill's frontmatter allows file operations (Read/Write/Edit/Grep/Glob). Those are reasonable for a document editor, but if you want to restrict file enumeration or bulk searches, consider limiting those permissions before enabling the skill. (2) The instructions encourage injecting 'personality' and opinions to make text sound human — review outputs for unwanted assertions or hallucinated facts, especially if the original text included sensitive or factual content. If either of these concerns matter, ask the developer to remove Grep/Glob from allowed-tools or to clarify scope limits.
Capability Analysis
Type: OpenClaw Skill
Name: reddi-humanizer
Version: 2.2.0
The 'reddi-humanizer' skill is a set of markdown-based instructions designed to guide an AI agent in editing text to remove common AI-generated patterns. It relies on standard file manipulation tools (Read, Write, Edit) and explicitly disables outbound network access in its metadata. The instructions are well-documented, based on legitimate Wikipedia style guides, and contain no evidence of malicious intent, data exfiltration, or prompt-injection attacks against the host environment.
Capability Assessment
Purpose & Capability
Name/description (remove AI patterns, make prose more human) lines up with the included SKILL.md, README, tests, and changelog. It does not request credentials, binaries, or unrelated services.
Instruction Scope
The runtime instructions focus on scanning and rewriting text and explicitly aim to preserve meaning while injecting 'voice'. That can legitimately involve adding new phrasing or subjective tone (which may introduce stylistic judgment or mild hallucination), but the SKILL.md does not instruct the agent to read arbitrary system files or transmit data externally. The frontmatter does include file-related tools (Read/Write/Edit/Grep/Glob), which are reasonable for document editing but broaden what the agent could access if the platform grants those permissions.
Install Mechanism
Instruction-only skill with no install spec and no code files to execute. Lowest-risk install footprint.
Credentials
No environment variables, credentials, or config paths are required. The skill does not ask for unrelated secrets or cloud keys.
Persistence & Privilege
always is false and there is no evidence of the skill modifying system-wide settings or other skills. Autonomous invocation is enabled by default (normal) but not combined with other risky requests.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install reddi-humanizer - After installation, invoke the skill by name or use
/reddi-humanizer - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.2.0
Major rewrite: added soul/personality section, extended AI pattern detection, added voice guidelines
v2.1.1
- Added a CHANGELOG.md file and a new test case file (tests/cases.yaml) for improved documentation and testing.
- Removed redundant _meta.json file.
- Updated SKILL.md to reflect version 2.1.1, clarify forking information, and improve formatting.
- Enhanced metadata: added "fork-of: humanizer" for clearer project lineage.
v1.0.1
- Added metadata block describing network and bin requirements for OpenClaw compatibility.
- No changes to the core skill logic or instructions. All text processing remains local; no outbound network calls.
v1.0.0
Fork of humanizer by biostartechnology. Enhanced for technical blog writing with personality injection and voice guide integration.
Metadata
Frequently Asked Questions
What is Humanizer?
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comp... It is an AI Agent Skill for Claude Code / OpenClaw, with 431 downloads so far.
How do I install Humanizer?
Run "/install reddi-humanizer" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Humanizer free?
Yes, Humanizer is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Humanizer support?
Humanizer is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Humanizer?
It is built and maintained by Nissan Dookeran (@nissan); the current version is v2.2.0.
More Skills