MLOps
模型部署、评估与运维
pipeline
jwilger
Autonomous build-phase orchestrator. Manages slice queue, TDD pair dispatch, full-team code review, mutation testing, CI integration, and auto-merge with quality gates. Replaces manual coordinator overhead during build phase. Activate when running factory mode with ensemble-team.
codex-review
yelban
跨模型對抗式審查：用 Codex 審查 Claude 的計畫或程式碼產出。 異質模型產生真正的對抗張力，抓住同模型自審遺漏的問題。 自動 VERDICT 迴圈（最多 3 輪），產出結構化 issues 清單。 支援 --model 參數切換模型（預設 gpt-5.3-codex）。 觸發詞：/codex-review、cross-review、對抗審查
hyperparams
uiuc-kang-lab
Guide for hyperparameter selection — learning rate formulas, LoRA rank, batch size, group size, schedules, and model-specific tuning. Use when the user asks about learning rate, batch size, hyperparameter tuning, or how to configure training parameters.
midnight-concepts
mzf11125
Foundational knowledge about Midnight Network zero-knowledge blockchain technology, privacy mechanisms, and architecture. Use when users need to understand zero-knowledge proofs, privacy mechanisms like Zswap and selective disclosure, partner chain architecture, real-world use cases for private DeFi and voting, when to use Midnight for privacy-preserving applications, and core concepts of the Midnight ecosystem.
dlt-extract
dtsong
"Use this skill when building DLT pipelines for file-based or consulting data extraction. Covers Excel/CSV/SharePoint ingestion via DLT, destination swapping (DuckDB dev to warehouse prod), schema contracts for cleaning, and portable pipeline patterns. Common phrases: \"dlt pipeline for files\", \"extract Excel with dlt\", \"portable data pipeline\", \"dlt filesystem source\". Do NOT use for core DLT concepts like REST API or SQL database sources (use data-integration) or pipeline scheduling (use data-pipelines)."
ac-complexity-assessor
adaptationio
Assess feature and project complexity. Use when estimating effort, determining spec pipeline type, calculating cost estimates, or planning resource allocation.
config-management
cklxx
配置管理 — 查询/修改 agent 配置参数（YAML 配置文件）。
autoinfo-manager
wuhongchen
OpenClaw 自动化运营平台总控中心。负责从选题分析、内容改写、AI 生图到微信发布的全链路调度。
ai-orchestration-feedback-loop
creator-hian
Multi-AI engineering loop orchestrating Claude, Codex, and Gemini for comprehensive validation. USE WHEN (1) mission-critical features requiring multi-perspective validation, (2) complex architectural decisions needing diverse AI viewpoints, (3) security-sensitive code requiring deep analysis, (4) user explicitly requests multi-AI review or triple-AI loop. DO NOT USE for simple features or single-file changes. MODES - Triple-AI (full coverage), Dual-AI Codex-Claude (security/logic), Dual-AI Gemini-Claude (UX/creativity).
agent-cost-optimizer
adaptationio
Real-time cost tracking, budget enforcement, and ROI measurement for AI agent operations. Track token usage, predict costs, enforce budget caps ($50-70/month typical), optimize model selection, cache results, measure cost-to-value. Use when tracking AI costs, preventing budget overruns, optimizing spend, measuring ROI, or ensuring cost-effective AI operations.
agentic-development
Exploration-labs
Conversational guidance for building software with AI agents, covering workflows, tool selection, prompt strategies, parallel agent management, and best practices based on real-world high-volume agentic development experience. Use this skill when users ask about setting up agentic workflows, choosing models, optimizing prompts, managing parallel agents, or improving agent output quality.
cnn-vision
levy-n
Implements CNN architectures for computer vision tasks. Covers convolution operations, pooling, CNN design patterns (LeNet, ResNet, VGG), transfer learning, fine-tuning pretrained models, data augmentation, and image preprocessing. Use when building image classifiers, doing object detection, or when user mentions 'CNN', 'convolution', 'pooling', 'ResNet', 'VGG', 'transfer learning', 'fine-tuning', 'image augmentation', 'ImageNet', 'feature maps', 'MNIST', 'image classification', 'multi-modal', 'image captioning', or 'multimodal network'.
deep-learning-core
levy-n
Explains neural network fundamentals: the Three Pillars (Model, Loss, Optimizer), backpropagation, gradient descent variants (SGD, Adam), regularization (Dropout, BatchNorm), and MLP architecture design. Use when learning how neural networks work, debugging training issues, or when user asks about 'backpropagation', 'vanishing gradients', 'learning rate', 'loss function', 'overfitting', 'underfitting', 'activation functions', 'why isn\'t my model learning', 'gradient descent', 'Adam', 'Dropout', 'BatchNorm', 'autoencoder', 'denoising autoencoder', or 'latent space'.
ml-knowledge-index
levy-n
Routes ML/DL questions to specialized skills. Use FIRST when unsure which skill applies, when user asks broad ML questions, or when multiple topics might be relevant. Maps: regression/classification → ml-fundamentals, ensembles/clustering → ml-advanced, TF-IDF/Word2Vec → nlp-classical, training/backprop → deep-learning-core, PyTorch → pytorch-mastery, CNNs/images → cnn-vision, LSTM/time-series → sequence-models, BERT/HuggingFace → transformers-llm, RAG/embeddings → rag-retrieval, APIs/PDF-parsing → data-pipeline, LoRA/QLoRA/PEFT → fine-tuning-peft, MLflow/W&B/Optuna → mlops-experiment, SHAP/Grad-CAM → model-interpretability, Q-learning/PPO/DQN → reinforcement-learning, GAN/VAE/diffusion → generative-models, explanations → ml-teaching-assistant.
agentic-ui-contract
phrazzld
Design and implement agentic product flows using the contract: model decides what to do, tools decide how it is done, UI schema decides how it is rendered. Use for chat-first apps, tool-calling agents, generative UI systems, and planner/tool architecture decisions. Keywords: agentic UX, tool calling, planner, generative UI, function tools.
ml-fundamentals
levy-n
Implements classical ML algorithms for regression and classification. Covers Linear/Polynomial/Logistic Regression, Decision Trees, Ridge/Lasso regularization, train/test splits, cross-validation, and evaluation metrics (R², RMSE, Precision, Recall, F1, ROC-AUC, Confusion Matrix). Use when building predictive models on tabular data, comparing baseline algorithms, handling imbalanced data, or when user mentions 'regression', 'classification', 'overfitting', 'cross-validation', 'confusion matrix', 'feature importance', 'precision/recall', or 'regularization'.
nlp-classical
levy-n
Implements traditional NLP techniques before transformers. Covers text vectorization (TF-IDF, Bag-of-Words), word embeddings (Word2Vec, FastText, GloVe, Doc2Vec), topic modeling (LDA, Gensim), and text similarity (Jaccard, Cosine, FuzzyWuzzy, record linkage). Use when building text classifiers without deep learning, doing topic extraction, entity matching, or when user mentions 'TF-IDF', 'Word2Vec', 'topic modeling', 'LDA', 'text similarity', 'n-grams', 'document clustering', 'GloVe', 'Doc2Vec', 'FuzzyWuzzy', or 'record linkage'.
ml-dl-expert
levy-n
Expert ML/DL teaching assistant for Hebrew University AI Engineering course. Activates for ANY machine learning or deep learning question: neural networks, PyTorch, TensorFlow, transformers, BERT, GPT, RAG, embeddings, CNNs, RNNs, LSTM, NLP, computer vision, clustering, regression, classification, training loops, backpropagation, loss functions, optimization, HuggingFace, vector stores, FAISS, ChromaDB, recommender systems, matrix factorization, transfer learning, data augmentation, autoencoders, Word2Vec, TF-IDF, topic modeling, prompt engineering, fine-tuning, LoRA, QLoRA, PEFT, quantization, sentiment analysis, image classification, object detection, time series, XGBoost, Random Forest, PCA, t-SNE, DBSCAN, K-Means, data pipeline, PDF parsing, chunking, function calling, AI agents, MLflow, W&B, experiment tracking, hyperparameter tuning, Optuna, SHAP, feature importance, Grad-CAM, model interpretability, reinforcement learning, Q-learning, DQN, PPO, policy gradient, GANs, VAE, diffusion models, Stable Diffusion, generative AI, model deployment, MLOps, synthetic data, data sourcing, Kaggle, dataset, data augmentation, SMOTE. Routes to 17 specialized sub-skills and provides code examples, visual diagrams, and Hebrew explanations when needed.
Model Patterns
Kaakati
"Entity and model patterns with JSON serialization, immutability, and equality"
reinforcement-learning
levy-n
Reinforcement learning fundamentals and practical implementations. Covers RL concepts (agent, environment, reward, policy), Q-Learning, Deep Q-Network (DQN), Policy Gradient methods, PPO, Actor-Critic, Gymnasium environments, Stable-Baselines3, reward shaping, and exploration-exploitation trade-off. Use when user asks about 'reinforcement learning', 'RL', 'Q-learning', 'DQN', 'PPO', 'policy gradient', 'reward function', 'agent', 'environment', 'Gym', 'Gymnasium', 'exploration', 'exploitation', 'Stable-Baselines3', 'Actor-Critic', 'SARSA', 'Bellman equation', or 'Markov decision process'.
ml-advanced
levy-n
Implements ensemble learning (Random Forest, XGBoost, CatBoost, Stacking) and unsupervised methods (K-Means, DBSCAN, Hierarchical clustering, PCA, t-SNE, UMAP), and recommender systems (Matrix Factorization, NeuMF). Use when comparing gradient boosting algorithms, doing customer segmentation, anomaly detection, dimensionality reduction, building recommender systems, or when user mentions 'ensemble', 'boosting', 'bagging', 'random forest', 'XGBoost', 'clustering', 'K-Means', 'DBSCAN', 'elbow method', 'silhouette score', 'PCA', 't-SNE', 'dimensionality reduction', 'feature importance', 'matrix factorization', 'NeuMF', 'recommender system', or 'collaborative filtering'.
ml-teaching-assistant
levy-n
Explains ML/DL concepts with analogies, visual diagrams, and progressive complexity. Covers backpropagation, gradient descent, attention mechanisms, neural networks, ML project methodology, and 50+ other concepts. Also provides the 5-step ML workflow, anti-patterns checklist, and model selection decision trees. Use when user says 'explain', 'I don\'t understand', 'how does X work', 'teach me', 'why does', 'what is the intuition', 'how should I approach', 'best practice', 'common mistakes', 'workflow', 'methodology', or asks conceptual 'why' questions about any ML topic. Provides intuitive explanations before math, ASCII visualizations, everyday analogies, and corrects common misconceptions.
video-agent
founderjourney
AI content generation suite with 35+ models. Image generation, video creation, audio processing via FAL AI, Google Vertex AI, ElevenLabs. Pipeline orchestration and cost management.
Repository Patterns
Kaakati
"Repository interface and implementation patterns with offline-first strategies"