npx skills add https://github.com/rand/cc-polymath --skill anti-slop检测并消除自然语言、代码和设计中的通用 AI 生成模式("泛化")。
AI 泛化指的是那些表明内容质量低下、由 AI 通用生成的典型模式:
此技能有助于识别并移除这些模式,以创建真实、高质量的内容。
在以下情况下应用反泛化技术:
对于文本文件:
python scripts/detect_slop.py <file> [--verbose]
这将分析文本并提供:
手动检测: 阅读相应的参考文件以获取详细模式:
references/text-patterns.md - 自然语言泛化模式广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
references/code-patterns.md - 编程泛化模式references/design-patterns.md - 视觉/UX 设计泛化模式自动清理(仅限文本):
# 预览更改
python scripts/clean_slop.py <file>
# 应用更改(创建备份)
python scripts/clean_slop.py <file> --save
# 激进模式(可能会轻微改变含义)
python scripts/clean_slop.py <file> --save --aggressive
手动清理: 根据检测到的模式,应用参考文件中的策略。
立即移除:
简化冗长的短语:
替换流行语:
直接了当:
具体明确:
真实可信:
重命名通用变量:
data → 命名它代表什么数据result → 命名结果包含什么temp → 命名你暂时存储的是什么item → 命名是什么类型的项目移除显而易见的注释:
# 不好
# 创建用户
user = User()
# 更好 - 让代码自己说话
user = User()
简化过度设计的代码:
改进函数名:
handleData() → 你对数据做什么?processItems() → 具体是什么处理?manageUsers() → 是什么管理操作?清晰胜过巧妙:
有意义的命名:
适当的文档:
视觉泛化:
布局泛化:
文案泛化:
内容优先的设计:
有意识的选择:
真实的声音:
在处理特定领域时,请查阅这些全面的指南:
每个参考文件包括:
分析文本文件中的 AI 泛化模式。
用法:
python scripts/detect_slop.py <file> [--verbose]
输出:
评分:
自动从文本文件中移除常见的泛化模式。
用法:
# 预览更改
python scripts/clean_slop.py <file>
# 保存更改(创建备份)
python scripts/clean_slop.py <file> --save
# 保存到不同文件
python scripts/clean_slop.py <file> --output clean_file.txt
# 激进模式
python scripts/clean_slop.py <file> --save --aggressive
清理内容:
安全性:
.backup 文件创建内容时:
并非所有模式总是泛化:
可接受的上下文:
始终考虑:
脚本是工具,而不是判断的替代品:
# 提交前检查文件
python scripts/detect_slop.py src/documentation.md --verbose
# 自动清理
python scripts/clean_slop.py src/documentation.md --save
创建项目特定的阈值:
脚本仅处理文本:
上下文敏感性:
语言覆盖范围:
# 用户询问:"你能审查这篇文章是否有 AI 泛化吗?"
1. 阅读 references/text-patterns.md 以了解需要注意的模式
2. 运行:python scripts/detect_slop.py article.txt --verbose
3. 审查发现并应用手动清理
4. 可选运行:python scripts/clean_slop.py article.txt --save
5. 对清理后的内容进行最终手动审查
# 用户询问:"帮助我清理代码中的通用 AI 模式"
1. 阅读 references/code-patterns.md
2. 手动审查代码文件中的模式
3. 创建要重命名的通用名称列表
4. 按照 code-patterns.md 中的原则进行重构
5. 移除显而易见的注释和过度抽象
# 用户询问:"这个设计看起来太通用了吗?"
1. 阅读 references/design-patterns.md
2. 检查高置信度的泛化指标
3. 识别具体问题(渐变、布局、文案)
4. 提供来自 design-patterns.md 的具体建议
5. 建议具体的替代方案
# 用户询问:"帮助我为我们的团队创建质量标准"
1. 审查所有三个参考文件
2. 识别与用户领域最相关的模式
3. 创建项目特定的指南
4. 在开发流水线中设置检测脚本
5. 记录可接受的例外情况
对于文本清理:
对于代码清理:
对于设计清理:
通用原则:
每周安装次数
154
代码仓库
GitHub 星标数
83
首次出现
2026 年 1 月 23 日
安全审计
安装于
claude-code120
opencode112
codex111
gemini-cli104
cursor100
github-copilot97
Detect and eliminate generic AI-generated patterns ("slop") across natural language, code, and design.
AI slop refers to telltale patterns that signal low-quality, generic AI-generated content:
This skill helps identify and remove these patterns to create authentic, high-quality content.
Apply anti-slop techniques when:
For text files:
python scripts/detect_slop.py <file> [--verbose]
This analyzes text and provides:
Manual detection: Read the appropriate reference file for detailed patterns:
references/text-patterns.md - Natural language slop patternsreferences/code-patterns.md - Programming slop patternsreferences/design-patterns.md - Visual/UX design slop patternsAutomated cleanup (text only):
# Preview changes
python scripts/clean_slop.py <file>
# Apply changes (creates backup)
python scripts/clean_slop.py <file> --save
# Aggressive mode (may slightly change meaning)
python scripts/clean_slop.py <file> --save --aggressive
Manual cleanup: Apply strategies from the reference files based on detected patterns.
Remove immediately:
Simplify wordy phrases:
Replace buzzwords:
Be direct:
Be specific:
Be authentic:
Rename generic variables:
data → name what data it representsresult → name what the result containstemp → name what you're temporarily storingitem → name what kind of itemRemove obvious comments:
# Bad
# Create a user
user = User()
# Better - let code speak
user = User()
Simplify over-engineered code:
Improve function names:
handleData() → what are you doing with data?processItems() → what processing specifically?manageUsers() → what management action?Clarity over cleverness:
Meaningful names:
Appropriate documentation:
Visual slop:
Layout slop:
Copy slop:
Content-first design:
Intentional choices:
Authentic voice:
Consult these comprehensive guides when working on specific domains:
text-patterns.md - Complete catalog of natural language slop patterns with detection rules and cleanup strategies
code-patterns.md - Programming antipatterns across languages with refactoring guidance
design-patterns.md - Visual and UX design slop patterns with improvement strategies
Each reference includes:
Analyzes text files for AI slop patterns.
Usage:
python scripts/detect_slop.py <file> [--verbose]
Output:
Scoring:
Automatically removes common slop patterns from text files.
Usage:
# Preview changes
python scripts/clean_slop.py <file>
# Save changes (creates backup)
python scripts/clean_slop.py <file> --save
# Save to different file
python scripts/clean_slop.py <file> --output clean_file.txt
# Aggressive mode
python scripts/clean_slop.py <file> --save --aggressive
What it cleans:
Safety:
.backup file when overwritingWhen creating content:
Not all patterns are always slop:
Acceptable contexts:
Always consider:
The scripts are tools, not replacements for judgment:
# Check files before committing
python scripts/detect_slop.py src/documentation.md --verbose
# Clean up automatically
python scripts/clean_slop.py src/documentation.md --save
Create project-specific thresholds:
Scripts only handle text:
Context sensitivity:
Language coverage:
# User asks: "Can you review this article for AI slop?"
1. Read references/text-patterns.md for patterns to watch
2. Run: python scripts/detect_slop.py article.txt --verbose
3. Review findings and apply manual cleanup
4. Optionally run: python scripts/clean_slop.py article.txt --save
5. Do final manual review of cleaned content
# User asks: "Help me clean up generic AI patterns in my code"
1. Read references/code-patterns.md
2. Review code files manually for patterns
3. Create list of generic names to rename
4. Refactor following principles in code-patterns.md
5. Remove obvious comments and over-abstractions
# User asks: "Does this design look too generic?"
1. Read references/design-patterns.md
2. Check against high-confidence slop indicators
3. Identify specific issues (gradients, layouts, copy)
4. Provide specific recommendations from design-patterns.md
5. Suggest concrete alternatives
# User asks: "Help me create quality standards for our team"
1. Review all three reference files
2. Identify patterns most relevant to user's domain
3. Create project-specific guidelines
4. Set up detection scripts in development pipeline
5. Document acceptable exceptions
For text cleanup:
For code cleanup:
For design cleanup:
General principles:
Weekly Installs
154
Repository
GitHub Stars
83
First Seen
Jan 23, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
claude-code120
opencode112
codex111
gemini-cli104
cursor100
github-copilot97
AI 代码实施计划编写技能 | 自动化开发任务分解与 TDD 流程规划工具
49,000 周安装
PPTX文件创建、编辑与分析指南:Python脚本处理.pptx文件XML内容
159 周安装
DOCX 文件创建、编辑与分析指南 - 使用 Pandoc、OOXML 与 docx-js 处理 Word 文档
158 周安装
事件驱动架构设计指南:消息代理、事件溯源、CQRS、AsyncAPI 最佳实践
149 周安装
UX Researcher技能指南:用户研究方法、可用性测试与数据分析框架
157 周安装
Tilt开发工具使用指南:Kubernetes本地开发、错误排查与自动化部署
133 周安装
动画时序函数选择指南:Spring动画与缓动函数决策框架与代码检查规则
152 周安装