MLOps
模型部署、评估与运维
mlops-pipelines
Logos-Liber
Model deployment strategies, monitoring and drift detection, CI/CD for ML models, feature store concepts, and model versioning
ml-best-practices
Logos-Liber
Model selection guidelines, feature engineering techniques, hyperparameter tuning strategies, evaluation metrics, and common ML frameworks
evaluator
SimHacker
Independent assessment without debate context — adversarial loop prevents gaming
leela-ai
SimHacker
"Manufacturing Intelligence â Leela AI develops MOOLLM for practical use and industrial exploration"
ai-ml-development
travisjneuman
AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.
Local LLM Integration Skill
markus41
Timeout errors Increase client timeout, use streaming
Ollama Mastery Skill
markus41
Ollama Model Library
aspnet-middleware
claude-dev-suite
ASP.NET Core custom middleware, pipeline order, exception handling middleware, and request/response manipulation. USE WHEN: user mentions "middleware", "request pipeline", "exception middleware", "ASP.NET middleware", "UseMiddleware", "pipeline order" DO NOT USE FOR: Express middleware - use express, NestJS middleware - use nestjs
bubbletea-code-review
existential-birds
Reviews BubbleTea TUI code for proper Elm architecture, model/update/view patterns, and Lipgloss styling. Use when reviewing terminal UI code using charmbracelet/bubbletea.
data-science
travisjneuman
Data science and analytics expertise for statistical analysis, machine learning pipelines, data governance, business intelligence, predictive modeling, and analytics strategy. Use when building ML models, analyzing data, creating dashboards, or designing data architectures.
deepagents-implementation
existential-birds
Implements agents using Deep Agents. Use when building agents with create_deep_agent, configuring backends, defining subagents, adding middleware, or setting up human-in-the-loop workflows.
pydantic-ai-model-integration
existential-birds
Configure LLM providers, use fallback models, handle streaming, and manage model settings in PydanticAI. Use when selecting models, implementing resilience, or optimizing API calls.
🕸 协同编排秘典
telagod
☠️ 一键为 Claude Code / Codex CLI 注入邪修人格与 40+ 安全工程秘典 npx code-abyss
rag
sjtu-sai-agents
Retrieval-Augmented Generation (RAG) system for semantic search and knowledge retrieval. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases. Supports vector-based similarity search using FAISS and transformer embeddings.
result-integrator
GongLingRui
整合多情点分析结果为综合报告，通过去重、分类、排序、总结生成高质量分析。适用于整合多分析源、生成统一报告
character-relationships
GongLingRui
分析故事人物关系，识别类型、特点及发展变化。适用于深度理解人物关系网络、分析关系对情节推动作用、为情节设计提供关系支撑
web-search
GongLingRui
使用联网搜索获取最新市场信息和行业动态。适用于获取竖屏短剧市场趋势、热门题材分析、成功案例研究
knowledge-query
GongLingRui
专注于竖屏短剧知识库查询和信息检索，提供专业知识服务。适用于查询剧本桥段、高能情节、创作技巧、商业运营等专业知识
novel-evaluator
GongLingRui
严格细致判断与评分故事文本，从市场潜力、创新属性、内容亮点维度分析质量。适用于小说初筛选、多维度评估打分
series-analyzer
GongLingRui
分析已播剧集，包括信息获取、拉片分析、五元素分析及联网搜索。适用于深度分析剧集创作技法、学习情节设计
story-type-analyzer
GongLingRui
分析故事题材类型，提炼创意元素与故事特色。适用于识别题材定位、提炼创意、分析市场受众
novel-summarizer
GongLingRui
阅读理解小说文本，总结成流畅的故事大纲。适用于小说初筛选、生成500-800字故事大纲
detailed-plot-analyzer
GongLingRui
基于大情节点，深入分析并生成详细情节点描述及情节发展说明。适用于细化故事大纲、指导剧本写作、分析情节内在逻辑
script-evaluator
GongLingRui
从思想性、艺术性、观赏性三维度评估影视剧本并打分。适用于剧本开发质量评估、修改方向确定、项目立项前审查