发现 devops architecture patterns 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
Model interpretability and explainability using SHAP, LIME, feature importance, and partial dependence plots. Activates for "explain model", "model interpretability", "SHAP", "LIME", "feature importance", "why...
Automated machine learning with hyperparameter optimization using Optuna, Hyperopt, or AutoML libraries. Activates for "automl", "hyperparameter tuning", "optimize hyperparameters", "auto tune model", "neural a...
Natural language processing ML pipelines for text classification, NER, sentiment analysis, text generation, and embeddings. Activates for "nlp", "text classification", "sentiment analysis", "named entity recogn...
Smart work continuation system that detects implementation intent and routes to active increment or creates new one. Activates for implement, complete, build, add, develop, work on, continue, resume, finish, fi...
Detects when user reports issues with recently completed work and suggests reopening relevant tasks, user stories, or increments. Auto-activates on keywords: not working, broken, bug, issue, problem, failing, e...
Prepares ML models for production deployment with containerization, API creation, monitoring setup, and A/B testing. Activates for "deploy model", "production deployment", "model API", "containerize model", "do...
Expert knowledge of Apache Kafka architecture, cluster design, capacity planning, partitioning strategies, replication, and high availability. Auto-activates on keywords kafka architecture, cluster sizing, part...
Time series forecasting with ARIMA, Prophet, LSTM, and statistical methods. Activates for "time series", "forecasting", "predict future", "trend analysis", "seasonality", "ARIMA", "Prophet", "sales forecast", "...
Automated data visualization for EDA, model performance, and business reporting. Activates for "visualize data", "create plots", "EDA", "exploratory analysis", "confusion matrix", "ROC curve", "feature distribu...
Orchestrates complete machine learning pipelines within SpecWeave increments. Activates when users request "ML pipeline", "train model", "build ML system", "end-to-end ML", "ML workflow", "model training pipeli...
Centralized model versioning, staging, and lifecycle management. Activates for "model registry", "model versioning", "model staging", "deploy to production", "rollback model", "model metadata", "model lineage",...
Expert in creating Mermaid diagrams following C4 Model and SpecWeave conventions. Specializes in system architecture, sequence diagrams, ER diagrams, and deployment diagrams. Activates for diagram creation, arc...
System Architect and technical design expert. Creates system architecture, technical specifications, Architecture Decision Records (ADRs), component designs, API contracts, data models, and deployment architect...
Multi-agent orchestration system that coordinates specialized agents (PM, Architect, DevOps, QA, Tech Lead, Security) to work together on complex tasks. Implements hierarchical orchestrator-worker pattern. Acti...
Invoke before designing presenters, modules, or application structure in web applicartion.
Invoke before configuring Nette DI - services, .neon files, autowiring.
Expertise in executing finalized architectural plans. Use when the user asks to "implement the plan", "build the feature", or "execute the strategy".
Expertise in validating that the codebase matches a specific plan. Use when the user asks to "validate the plan", "check implementation", or "audit the code".
Expertise in acting as a Staff Engineer to generate comprehensive implementation plans. Use when the user asks to "plan a feature", "create a new plan", or "design an architecture".
Expertise in deploying the project to a target environment. Use when the user asks to "deploy", "release", or "push to prod".
brainbaseのアーキテクチャパターン（EventBus、Reactive Store、DI Container、Service Layer）への準拠をチェックし、違反箇所を修正提案する4 Phase Orchestrator Skill。
Handle refinement of next actions when user rejects suggestions, wants to change context, defer, delegate, or break down further. Use when a suggested action doesn't fit or circumstances change.
Create Architecture Decision Records through interactive conversation. Use when making technology choices, architecture patterns, or third-party service selections.
Architect planning workflow (Codex CLI). Use to design before build and produce an implementation plan.
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。