# Humanizer: Remove AI-Generated Writing from Your Text This repository profile is provided by osrepos.com, an open source repository discovery platform. Source: osrepos.com Repository profile: https://osrepos.com/repo/blader-humanizer Generated for open source discovery and AI-assisted research. Humanizer is a powerful skill for Claude Code and OpenCode designed to transform AI-generated text into more natural, human-sounding prose. By identifying and correcting over 30 common AI writing patterns, this tool helps users refine their content, ensuring it resonates authentically with readers. It even offers voice calibration to match your personal writing style. GitHub: https://github.com/blader/humanizer OSRepos URL: https://osrepos.com/repo/blader-humanizer ## Summary Humanizer is a powerful skill for Claude Code and OpenCode designed to transform AI-generated text into more natural, human-sounding prose. By identifying and correcting over 30 common AI writing patterns, this tool helps users refine their content, ensuring it resonates authentically with readers. It even offers voice calibration to match your personal writing style. ## Topics - AI writing - text humanization - Claude Code skill - OpenCode skill - content refinement - writing tools - AI detection - natural language processing ## Repository Information Last analyzed by OSRepos: Fri May 29 2026 12:47:11 GMT+0100 (Western European Summer Time) Detail views: 9 GitHub clicks: 9 ## Safety Notice OSRepos shares public repositories for knowledge and discovery only. Review source code, dependencies, licenses, and security implications before running or installing anything. ## Content ## Introduction Humanizer is an innovative skill for both Claude Code and OpenCode, specifically engineered to eliminate the tell-tale signs of AI-generated writing from your text. Its primary goal is to make your content sound more natural, authentic, and human. Whether you're refining drafts or ensuring your communications are genuinely engaging, Humanizer helps bridge the gap between AI efficiency and human expressiveness. ## Installation Getting Humanizer set up is straightforward for both Claude Code and OpenCode users. ### For Claude Code Clone the repository directly into Claude Code's skills directory: bash mkdir -p ~/.claude/skills git clone https://github.com/blader/humanizer.git ~/.claude/skills/humanizer Alternatively, if you already have the repository cloned, you can copy the skill file manually: bash mkdir -p ~/.claude/skills/humanizer cp SKILL.md ~/.claude/skills/humanizer/ ### For OpenCode Clone the repository directly into OpenCode's skills directory: bash mkdir -p ~/.config/opencode/skills git clone https://github.com/blader/humanizer.git ~/.config/opencode/skills/humanizer Or copy the skill file manually if you already have this repo cloned: bash mkdir -p ~/.config/opencode/skills/humanizer cp SKILL.md ~/.config/opencode/skills/humanizer/ **Note:** OpenCode is compatible with Claude Code's skill directory. A single clone into `~/.claude/skills/humanizer/` is sufficient if you use both tools. ## Examples Using Humanizer is simple, offering both direct commands and voice calibration for personalized results. ### Basic Usage To humanize text in Claude Code or OpenCode, use the `/humanizer` command followed by your text: /humanizer [paste your text here] You can also ask the model to humanize text directly: Please humanize this text: [your text] ### Voice Calibration For a truly personalized touch, Humanizer can adapt to your unique writing style. Provide a sample of your own writing to calibrate its output: /humanizer Here's a sample of my writing for voice matching: [paste 2-3 paragraphs of your own writing] Now humanize this text: [paste AI text to humanize] This feature analyzes your sentence rhythm, word choices, and stylistic quirks, applying them to the rewritten text instead of producing generic output. ## Why Use Humanizer In an era where AI-generated content is prevalent, ensuring your writing maintains a human touch is crucial for authenticity and engagement. Humanizer addresses this by systematically removing common "AI-isms" based on extensive research. The skill's methodology is rooted in [Wikipedia's "Signs of AI writing"](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing) guide, maintained by WikiProject AI Cleanup. This comprehensive guide identifies over 30 distinct patterns observed in thousands of instances of AI-generated text. Humanizer detects and corrects these patterns, ranging from "significance inflation" and "promotional language" to "AI vocabulary" and "chatbot artifacts." A key insight from Wikipedia highlights that "LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases." Humanizer counteracts this by introducing natural variation and specificity. The tool even includes a final audit pass and a second rewrite to catch any lingering AI characteristics. Consider this example of Humanizer's impact: **Before (AI-sounding snippet):** > "AI-assisted coding serves as an enduring testament to the transformative potential of large language models, marking a pivotal moment in the evolution of software development. In today's rapidly evolving technological landscape, these groundbreaking tools, nestled at the intersection of research and practice, are reshaping how engineers ideate, iterate, and deliver, underscoring their vital role in modern workflows." **After (Humanized snippet):** > "AI coding assistants can speed up the boring parts of the job. They're great at boilerplate: config files and the little glue code you don't want to write. They can also help you sketch a test, but you still have to read it." This transformation demonstrates how Humanizer shifts text from generic, verbose, and formulaic AI output to concise, direct, and relatable human prose. ## Links * [Humanizer GitHub Repository](https://github.com/blader/humanizer) * [Wikipedia: Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing) * [Wikipedia: WikiProject AI Cleanup](https://en.wikipedia.org/wiki/Wikipedia:WikiProject_AI_Cleanup)