菜单
Removes signs of AI-generated writing from text, making it sound more natural and human. Based on Wikipedia's comprehensive "Signs of AI writing" guide.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Explains code with visual diagrams and analogies. Use when explaining how code works, teaching about a codebase, or when the user asks "how does this work?"
Install and maintain the upstream Frontend Slides skill from GitHub so agents can create high-quality HTML slide decks and convert PPTX content.
Lifecycle manager for GitHub-based skills. Use this to batch scan your skills directory, check for updates on GitHub, and perform guided upgrades of your skill wrappers.
Generate a static function and method call graph for a Python repository. Use this skill when the user wants a Python call graph, function dependency map, Mermaid call diagram, or static call-chain analysis from a local repo.
Fetch any URL and convert to markdown using Chrome CDP. Supports two modes - auto-capture on page load, or wait for user signal (for pages requiring login). Use when user wants to save a webpage as markdown.
GitHub仓库提交管理技能，用于检查、验证和提交代码到GitHub仓库。当用户需要提交代码到GitHub时使用此技能，包括：1) 检查当前Git仓库状态和远程链接，2) 验证或更新GitHub远程仓库链接，3) 审核代码更改并生成提交消息，4) 创建提交并可选推送到远程仓库。特别适用于需要确保正确提交到指定GitHub仓库的场景。
| name | humanizer |
| description | Removes signs of AI-generated writing from text, making it sound more natural and human. Based on Wikipedia's comprehensive "Signs of AI writing" guide. |
A skill that removes signs of AI-generated writing from text, making it sound more natural and human. Based on Wikipedia's comprehensive "Signs of AI writing" guide.
name: humanizer
version: 1.0.0
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
comprehensive "Signs of AI writing" guide. Detects and fixes patterns including:
inflated symbolism, promotional language, superficial -ing analyses, vague
attributions, em dash overuse, rule of three, AI vocabulary words, negative
parallelisms, and excessive conjunctive phrases.
author: Adapted from blader/humanizer for OpenCode
license: MIT
tags:
- writing
- editing
- ai-detection
- text-processing
- humanization
Invoke the skill with text to humanize:
/humanizer [text to process]
Or use in conversation:
Please humanize this text: [your text]
The skill detects 24 common AI writing patterns across 5 categories:
said "the project" → said "the project"# Example pattern detection logic
patterns = {
"significance_inflation": [
"pivotal moment", "testament to", "underscores its importance",
"symbolizing its ongoing", "marking a shift", "evolving landscape"
],
"ai_vocabulary": [
"additionally", "testament", "landscape", "showcasing", "underscore",
"pivotal", "tapestry", "vibrant", "crucial", "delves", "fostering"
],
"promotional_language": [
"nestled within", "breathtaking", "stunning", "must-visit",
"boasts a", "rich cultural heritage", "natural beauty"
],
"vague_attributions": [
"experts believe", "industry reports", "observers have cited",
"some critics argue", "several sources"
]
}
Before (AI-sounding):
The new software update serves as a testament to the company's commitment to innovation. Moreover, it provides a seamless, intuitive, and powerful user experience—ensuring that users can accomplish their goals efficiently. It's not just an update, it's a revolution in how we think about productivity. Industry experts believe this will have a lasting impact on the entire sector, highlighting the company's pivotal role in the evolving technological landscape.
After (Humanized):
The software update adds batch processing, keyboard shortcuts, and offline mode. Early feedback from beta testers has been positive, with most reporting faster task completion.
/humanizer command or natural language request// Example skill handler
class HumanizerSkill {
constructor() {
this.patterns = this.loadPatterns();
}
async process(text, options = {}) {
const detected = this.detectPatterns(text);
const transformed = this.transformText(text, detected);
return {
original: text,
humanized: transformed,
changes: detected,
summary: this.generateSummary(detected)
};
}
detectPatterns(text) {
// Implement pattern detection logic
return patterns.map(pattern => ({
pattern,
matches: this.findMatches(text, pattern),
severity: this.calculateSeverity(pattern, matches)
}));
}
transformText(text, detectedPatterns) {
// Apply transformations based on detected patterns
let result = text;
detectedPatterns.forEach(pattern => {
result = this.applyTransformation(result, pattern);
});
return result;
}
}
humanizer:
strictness: medium # low, medium, high
preserve_tone: true
add_personality: true
target_audience: general # academic, business, casual, technical
output_format: text # text, markdown, html
Input: "The research serves as a testament to the pivotal role of quantum computing in the evolving landscape of computational science." Output: "The research demonstrates how quantum computing advances computational science."
Input: "Our groundbreaking solution boasts a seamless, intuitive, and powerful interface—ensuring maximum productivity for enterprise users." Output: "Our solution has an interface designed for enterprise productivity."
Input: "Hey there! I hope this helps! Let me know if you need anything else! 😊" Output: "Here's the information. Please ask if you need more details."
MIT License - Based on blader/humanizer (https://github.com/blader/humanizer)
This skill is used when its description in frontmatter matches the user request. Prefer existing scripts under scripts/ over ad-hoc rewrites.
# Run from repository root
python <skill-name>/scripts/<script>.py --help
description