{"id":51026605,"url":"https://github.com/gitstq/taste-guard","last_synced_at":"2026-06-21T20:02:07.020Z","repository":{"id":363223200,"uuid":"1262398625","full_name":"gitstq/taste-guard","owner":"gitstq","description":"🛡️ AI Content Quality Guardian - Evaluate and optimize AI-generated content for uniqueness and engagement","archived":false,"fork":false,"pushed_at":"2026-06-08T00:19:57.000Z","size":18,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-06-08T02:20:31.703Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/gitstq.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-06-08T00:16:49.000Z","updated_at":"2026-06-08T00:19:40.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/gitstq/taste-guard","commit_stats":null,"previous_names":["gitstq/taste-guard"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/gitstq/taste-guard","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gitstq%2Ftaste-guard","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gitstq%2Ftaste-guard/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gitstq%2Ftaste-guard/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gitstq%2Ftaste-guard/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/gitstq","download_url":"https://codeload.github.com/gitstq/taste-guard/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gitstq%2Ftaste-guard/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34623906,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-21T02:00:05.568Z","response_time":54,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2026-06-21T20:02:06.130Z","updated_at":"2026-06-21T20:02:07.015Z","avatar_url":"https://github.com/gitstq.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\n# 🛡️ TasteGuard\n\n**AI Content Quality Guardian**\n\n[![Python](https://img.shields.io/badge/Python-3.8%2B-blue)](https://www.python.org/)\n[![License](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)\n[![Version](https://img.shields.io/badge/Version-1.0.0-orange)](https://github.com/gitstq/taste-guard/releases)\n\n[English](#english) | [简体中文](#简体中文) | [繁體中文](#繁體中文)\n\n\u003c/div\u003e\n\n---\n\n\u003ca name=\"english\"\u003e\u003c/a\u003e\n## 🎉 Introduction\n\n**TasteGuard** is a Python CLI tool that evaluates and optimizes AI-generated content quality. Inspired by the trending [taste-skill](https://github.com/Leonxlnx/taste-skill) project, TasteGuard helps content creators, developers, and writers produce **unique, engaging, and non-generic** text outputs.\n\n### Why TasteGuard?\n\nIn the era of AI-generated content, \"AI slop\" — generic, repetitive, and soulless text — is everywhere. TasteGuard acts as your content quality guardian, detecting:\n\n- 🎯 Overused generic phrases (\"in today's world\", \"leverage synergy\")\n- 📉 Weak modifiers that dilute meaning (\"very\", \"really\", \"quite\")\n- 🔄 Repetitive sentence structures and transition words\n- 📊 Overall content engagement and readability metrics\n\n### ✨ Key Features\n\n| Feature | Description |\n|---------|-------------|\n| 🔍 **Generic Phrase Detection** | Identifies 50+ common AI-generated expressions |\n| 📈 **Vocabulary Diversity** | Measures lexical richness and bigram variety |\n| 💬 **Engagement Scoring** | Evaluates sensory words, questions, and active voice |\n| 📖 **Readability Analysis** | Flesch Reading Ease and Grade Level metrics |\n| 💡 **Smart Suggestions** | Actionable recommendations for improvement |\n| 🎨 **Rich CLI Output** | Beautiful terminal formatting with color-coded results |\n\n### 🚀 Quick Start\n\n#### Requirements\n\n- Python 3.8 or higher\n- pip package manager\n\n#### Installation\n\n```bash\npip install taste-guard\n```\n\n#### Usage\n\n```bash\n# Analyze text content\ntaste-guard analyze \"Your text here...\"\n\n# Analyze from file\ntaste-guard analyze -f article.txt --verbose\n\n# Compare two texts\ntaste-guard compare \"Text A...\" \"Text B...\"\n\n# Get optimization suggestions\ntaste-guard optimize \"Your draft text...\"\n\n# Output as JSON\ntaste-guard analyze \"Text...\" --json\n```\n\n### 📖 Detailed Usage Guide\n\n#### Analyze Command\n\nThe `analyze` command provides comprehensive content quality analysis:\n\n```bash\n# Basic analysis\ntaste-guard analyze \"In today's world, we need to leverage synergy.\"\n\n# Verbose mode with detailed detection\ntaste-guard analyze -f blog_post.md --verbose\n\n# JSON output for programmatic use\ntaste-guard analyze \"Text...\" --json\n```\n\n**Output Metrics:**\n\n- **Overall Score**: 0-100 quality rating\n- **Generic Phrases**: Count and density of overused expressions\n- **Vocabulary Diversity**: Unique word ratio and bigram variety\n- **Sentence Variation**: Pattern diversity and length variation\n- **Engagement Score**: Interactive elements and active voice ratio\n- **Readability**: Flesch metrics for comprehension difficulty\n\n#### Compare Command\n\nCompare two pieces of content side-by-side:\n\n```bash\ntaste-guard compare \"AI-generated text...\" \"Human-written text...\"\n```\n\n#### Optimize Command\n\nGet targeted suggestions for improvement:\n\n```bash\ntaste-guard optimize -f draft.txt\n```\n\n### 💡 Design Philosophy\n\nTasteGuard was designed with these principles:\n\n1. **Privacy First**: All analysis runs locally — no data sent to external services\n2. **Fast \u0026 Lightweight**: Pure Python with minimal dependencies\n3. **Actionable Insights**: Not just scores, but specific improvement suggestions\n4. **Developer Friendly**: JSON output mode for CI/CD integration\n\n### 📦 Development \u0026 Deployment\n\n#### From Source\n\n```bash\ngit clone https://github.com/gitstq/taste-guard.git\ncd taste-guard\npip install -e .\n```\n\n#### Running Tests\n\n```bash\nmake test\n# or\npytest tests/ -v\n```\n\n#### Building\n\n```bash\nmake build\n```\n\n### 🤝 Contributing\n\nWe welcome contributions! Please follow these guidelines:\n\n1. Fork the repository\n2. Create a feature branch (`git checkout -b feature/amazing-feature`)\n3. Commit your changes (`git commit -m 'feat: add amazing feature'`)\n4. Push to the branch (`git push origin feature/amazing-feature`)\n5. Open a Pull Request\n\n### 📄 License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n---\n\n\u003ca name=\"简体中文\"\u003e\u003c/a\u003e\n## 🎉 项目介绍\n\n**TasteGuard** 是一款 Python CLI 工具，用于评估和优化 AI 生成内容的质量。灵感来源于热门的 [taste-skill](https://github.com/Leonxlnx/taste-skill) 项目，TasteGuard 帮助内容创作者、开发者和写作者产出**独特、引人入胜、非通用**的文本内容。\n\n### 为什么选择 TasteGuard？\n\n在 AI 生成内容的时代，\"AI 垃圾\"——千篇一律、重复乏味、毫无灵魂的文本——无处不在。TasteGuard 作为您的内容质量守护者，能够检测：\n\n- 🎯 过度使用的通用短语（\"在当今世界\"、\"利用协同效应\"）\n- 📉 弱化语义的修饰词（\"非常\"、\"真的\"、\"相当\"）\n- 🔄 重复的句子结构和过渡词\n- 📊 整体内容互动性和可读性指标\n\n### ✨ 核心特性\n\n| 特性 | 描述 |\n|------|------|\n| 🔍 **通用短语检测** | 识别 50+ 种常见 AI 生成表达 |\n| 📈 **词汇多样性** | 测量词汇丰富度和双词组多样性 |\n| 💬 **互动性评分** | 评估感官词汇、疑问句和主动语态 |\n| 📖 **可读性分析** | Flesch 阅读难度和年级水平指标 |\n| 💡 **智能建议** | 提供可操作的改进建议 |\n| 🎨 **丰富的 CLI 输出** | 彩色编码结果的精美终端格式 |\n\n### 🚀 快速开始\n\n#### 环境要求\n\n- Python 3.8 或更高版本\n- pip 包管理器\n\n#### 安装\n\n```bash\npip install taste-guard\n```\n\n#### 使用\n\n```bash\n# 分析文本内容\ntaste-guard analyze \"您的文本内容...\"\n\n# 从文件分析\ntaste-guard analyze -f article.txt --verbose\n\n# 比较两段文本\ntaste-guard compare \"文本 A...\" \"文本 B...\"\n\n# 获取优化建议\ntaste-guard optimize \"您的草稿文本...\"\n\n# 输出 JSON 格式\ntaste-guard analyze \"文本...\" --json\n```\n\n### 📖 详细使用指南\n\n#### Analyze 命令\n\n`analyze` 命令提供全面的内容质量分析：\n\n```bash\n# 基础分析\ntaste-guard analyze \"在当今世界，我们需要利用协同效应。\"\n\n# 详细检测模式\ntaste-guard analyze -f blog_post.md --verbose\n\n# JSON 输出，便于程序化处理\ntaste-guard analyze \"文本...\" --json\n```\n\n**输出指标：**\n\n- **整体评分**：0-100 质量评级\n- **通用短语**：过度使用的表达的数量和密度\n- **词汇多样性**：独特词汇比例和双词组多样性\n- **句子变化度**：模式多样性和长度变化\n- **互动性评分**：互动元素和主动语态比例\n- **可读性**：Flesch 理解难度指标\n\n#### Compare 命令\n\n并排比较两段内容：\n\n```bash\ntaste-guard compare \"AI 生成的文本...\" \"人工编写的文本...\"\n```\n\n#### Optimize 命令\n\n获取针对性的改进建议：\n\n```bash\ntaste-guard optimize -f draft.txt\n```\n\n### 💡 设计理念\n\nTasteGuard 遵循以下设计原则：\n\n1. **隐私优先**：所有分析在本地运行——数据不会发送到外部服务\n2. **快速轻量**：纯 Python 实现，依赖最小化\n3. **可操作洞察**：不仅提供分数，还有具体的改进建议\n4. **开发者友好**：JSON 输出模式，便于 CI/CD 集成\n\n### 📦 开发与部署\n\n#### 从源码安装\n\n```bash\ngit clone https://github.com/gitstq/taste-guard.git\ncd taste-guard\npip install -e .\n```\n\n#### 运行测试\n\n```bash\nmake test\n# 或\npytest tests/ -v\n```\n\n#### 构建\n\n```bash\nmake build\n```\n\n### 🤝 贡献指南\n\n欢迎贡献！请遵循以下准则：\n\n1. Fork 本仓库\n2. 创建功能分支 (`git checkout -b feature/amazing-feature`)\n3. 提交更改 (`git commit -m 'feat: add amazing feature'`)\n4. 推送到分支 (`git push origin feature/amazing-feature`)\n5. 开启 Pull Request\n\n### 📄 开源协议\n\n本项目采用 MIT 协议 - 详情请查看 [LICENSE](LICENSE) 文件。\n\n---\n\n\u003ca name=\"繁體中文\"\u003e\u003c/a\u003e\n## 🎉 專案介紹\n\n**TasteGuard** 是一款 Python CLI 工具，用於評估和優化 AI 生成內容的品質。靈感來源於熱門的 [taste-skill](https://github.com/Leonxlnx/taste-skill) 專案，TasteGuard 幫助內容創作者、開發者和寫作者產出**獨特、引人入勝、非通用**的文字內容。\n\n### 為什麼選擇 TasteGuard？\n\n在 AI 生成內容的時代，「AI 垃圾」——千篇一律、重複乏味、毫無靈魂的文字——無處不在。TasteGuard 作為您的內容品質守護者，能夠檢測：\n\n- 🎯 過度使用的通用短語（「在當今世界」、「利用協同效應」）\n- 📉 弱化語義的修飾詞（「非常」、「真的」、「相當」）\n- 🔄 重複的句子結構和過渡詞\n- 📊 整體內容互動性和可讀性指標\n\n### ✨ 核心特性\n\n| 特性 | 描述 |\n|------|------|\n| 🔍 **通用短語檢測** | 識別 50+ 種常見 AI 生成表達 |\n| 📈 **詞彙多樣性** | 測量詞彙豐富度和雙詞組多樣性 |\n| 💬 **互動性評分** | 評估感官詞彙、疑問句和主動語態 |\n| 📖 **可讀性分析** | Flesch 閱讀難度和年級水平指標 |\n| 💡 **智能建議** | 提供可操作的改進建議 |\n| 🎨 **豐富的 CLI 輸出** | 彩色編碼結果的精美終端格式 |\n\n### 🚀 快速開始\n\n#### 環境要求\n\n- Python 3.8 或更高版本\n- pip 套件管理器\n\n#### 安裝\n\n```bash\npip install taste-guard\n```\n\n#### 使用\n\n```bash\n# 分析文字內容\ntaste-guard analyze \"您的文字內容...\"\n\n# 從檔案分析\ntaste-guard analyze -f article.txt --verbose\n\n# 比較兩段文字\ntaste-guard compare \"文字 A...\" \"文字 B...\"\n\n# 獲取優化建議\ntaste-guard optimize \"您的草稿文字...\"\n\n# 輸出 JSON 格式\ntaste-guard analyze \"文字...\" --json\n```\n\n### 📖 詳細使用指南\n\n#### Analyze 命令\n\n`analyze` 命令提供全面的內容品質分析：\n\n```bash\n# 基礎分析\ntaste-guard analyze \"在當今世界，我們需要利用協同效應。\"\n\n# 詳細檢測模式\ntaste-guard analyze -f blog_post.md --verbose\n\n# JSON 輸出，便於程式化處理\ntaste-guard analyze \"文字...\" --json\n```\n\n**輸出指標：**\n\n- **整體評分**：0-100 品質評級\n- **通用短語**：過度使用的表達的數量和密度\n- **詞彙多樣性**：獨特詞彙比例和雙詞組多樣性\n- **句子變化度**：模式多樣性和長度變化\n- **互動性評分**：互動元素和主動語態比例\n- **可讀性**：Flesch 理解難度指標\n\n#### Compare 命令\n\n並排比較兩段內容：\n\n```bash\ntaste-guard compare \"AI 生成的文字...\" \"人工編寫的文字...\"\n```\n\n#### Optimize 命令\n\n獲取針對性的改進建議：\n\n```bash\ntaste-guard optimize -f draft.txt\n```\n\n### 💡 設計理念\n\nTasteGuard 遵循以下設計原則：\n\n1. **隱私優先**：所有分析在本地運行——資料不會發送到外部服務\n2. **快速輕量**：純 Python 實現，依賴最小化\n3. **可操作洞察**：不僅提供分數，還有具體的改進建議\n4. **開發者友好**：JSON 輸出模式，便於 CI/CD 整合\n\n### 📦 開發與部署\n\n#### 從原始碼安裝\n\n```bash\ngit clone https://github.com/gitstq/taste-guard.git\ncd taste-guard\npip install -e .\n```\n\n#### 執行測試\n\n```bash\nmake test\n# 或\npytest tests/ -v\n```\n\n#### 建置\n\n```bash\nmake build\n```\n\n### 🤝 貢獻指南\n\n歡迎貢獻！請遵循以下準則：\n\n1. Fork 本倉庫\n2. 建立功能分支 (`git checkout -b feature/amazing-feature`)\n3. 提交更改 (`git commit -m 'feat: add amazing feature'`)\n4. 推送到分支 (`git push origin feature/amazing-feature`)\n5. 開啟 Pull Request\n\n### 📄 開源協議\n\n本專案採用 MIT 協議 - 詳情請查看 [LICENSE](LICENSE) 檔案。\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgitstq%2Ftaste-guard","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgitstq%2Ftaste-guard","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgitstq%2Ftaste-guard/lists"}