deslop
关于
The deslop skill cleans up AI-generated code by removing unnecessary comments, defensive checks, and type casts from a branch's diff against main. It identifies and fixes style inconsistencies while preserving legitimate code changes. Use it to automatically polish AI-written code to match your codebase's standards.
快速安装
Claude Code
推荐/plugin add https://github.com/davila7/claude-code-templatesgit clone https://github.com/davila7/claude-code-templates.git ~/.claude/skills/deslop在 Claude Code 中复制并粘贴此命令以安装该技能
技能文档
Remove AI Code Slop
Check the diff against main and remove all AI-generated slop introduced in this branch.
What to Remove
- Extra comments that a human wouldn't add or are inconsistent with the rest of the file
- Extra defensive checks or try/catch blocks that are abnormal for that area of the codebase (especially if called by trusted/validated codepaths)
- Casts to
anyto get around type issues - Inline imports in Python (move to top of file with other imports)
- Any other style that is inconsistent with the file
Process
- Get the diff against main:
git diff main...HEAD - Review each changed file for slop patterns
- Remove identified slop while preserving legitimate changes
- Report a 1-3 sentence summary of what was changed
GitHub 仓库
相关推荐技能
sglang
元SGLang是一个专为LLM设计的高性能推理框架，特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术，在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时，能实现极速生成。如果你正在构建智能体或多轮对话系统，并追求远超vLLM的推理性能，SGLang是理想选择。
evaluating-llms-harness
测试该Skill通过60+个学术基准测试（如MMLU、GSM8K等）评估大语言模型质量，适用于模型对比、学术研究及训练进度追踪。它支持HuggingFace、vLLM和API接口，被EleutherAI等行业领先机构广泛采用。开发者可通过简单命令行快速对模型进行多任务批量评估。
llamaguard
其他LlamaGuard是Meta推出的7-8B参数内容审核模型，专门用于过滤LLM的输入和输出内容。它能检测六大安全风险类别（暴力/仇恨、性内容、武器、违禁品、自残、犯罪计划），准确率达94-95%。开发者可通过HuggingFace、vLLM或Sagemaker快速部署，并能与NeMo Guardrails集成实现自动化安全防护。
langchain
元LangChain是一个用于构建LLM应用程序的框架，支持智能体、链和RAG应用开发。它提供多模型提供商支持、500+工具集成、记忆管理和向量检索等核心功能。开发者可用它快速构建聊天机器人、问答系统和自主代理，适用于从原型验证到生产部署的全流程。