Conventions for an Expo SDK 54+ React Native app targeting iOS + Android. Use when .claude/HARNESS.toml selects mobile/react-native-expo, or when building cross-platform RN UI…
Use to plan server-state caching for mobile — RTK Query or TanStack Query — for fetching, caching, invalidation, retries, and offline behavior.
GPU architecture, precision types, fillrate, overdraw, baked lighting, and LOD optimization for Unity mobile/WebGL shaders
Write and run tests for React Native apps using Jest and React Native Testing Library. Use when creating tests, debugging failures, or setting up test infrastructure.
Detox E2E gray-box testing for React Native - matchers, actions, expectations, waitFor, device API, synchronization, mocking, artifacts, CI integration
Maestro mobile E2E testing - YAML flows, selectors, flow control, environment variables, JavaScript expressions, device interactions, Maestro Studio, Maestro Cloud CI, tags, test…
React Native Paper v5+ - Material Design 3 theming, PaperProvider, key components, dynamic color, accessibility, tree-shaking, custom fonts, navigation integration
Use to plan unit tests for mobile logic — Jest (or Vitest where supported) for pure functions, hooks, reducers, and utilities.
Use skill if you are controlling, automating, or testing a connected Android phone via the mobilerun CLI — tapping, typing, swiping, reading the screen, or running a multi-step…
Use when deciding whether a project belongs at MobiSys — testing whether the core contribution is a mobile or embedded system, application, or service whose on-device behavior is…
Suggest MOC updates and new MOCs based on semantic clustering. Use when asked to "curate MOCs", "update maps", "find clusters", "what MOCs need updating", or "organize my notes".
Generates Mocha tests in JavaScript with Chai assertions and Sinon mocking. Use when user mentions "Mocha", "Chai", "sinon", "describe/it (not Jest)".
Mocha Test Setup - Auto-activating skill for Test Automation. Triggers on: mocha test setup, mocha test setup Part of the Test Automation skill category.
Generate mock data and simulate API endpoints using CLI tools. Use when prototyping APIs or testing integrations.
Use AiMock when an agent needs reproducible tests around LLM APIs, MCP tools, A2A flows, vector stores, search, or moderation services without depending on live providers.
Design a consumer-driven contract testing setup — Pact configuration and CI integration.
Generate realistic mock data for testing using factories, fixtures, and Faker.js. Use when seeding test databases, creating test fixtures, or mocking API responses.
Generates and manages local mock servers based on OpenAPI, GraphQL, or Protobuf specifications.
Guides users on creating mock implementations for testing with traits, providing test doubles, and avoiding tight coupling to test infrastructure.
Generate mock API servers for testing and development with realistic response data. Use when creating mock APIs for development and testing.
Mockoon is the fastest way to run mock REST APIs locally. It provides a desktop application and a CLI for creating mock API servers with dynamic response templates, proxy mode,…
Start or stop the WireMock API mock server for UI testing and E2E verification.
Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or…
Upgrade shared Modal runtime dependencies in kernelbot and verify them end to end. Use when changing torch/CUDA or other shared Modal image dependencies, deploying the Modal app,…
Deploy AI workloads to serverless GPU/CPU with Modal — define @app.function with GPU/memory specs, build custom container images, run batch jobs and web endpoints, schedule cron…
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral).
State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design.
Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy.
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential).
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP).
Use when after a deep neural network model has completed training on LC-MS spectral peak classification data and you need to preserve the learned weights and architecture for…
Use when configuring Model Builder in Salesforce to register external LLMs or select standard models for Agentforce and Einstein features.
Document a deployed ML/AI model so others can use it responsibly. Use when asked to write a model card, document a model's intended use and limitations, or prepare an AI model for…
Debug and diagnose model errors in Pollinations services. Analyze logs, find error patterns, identify affected users. For taking action on user tiers, see tier-management skill.
Esposter model-delegation conventions — the main session does all thinking (specs, proposals, architecture, review); mechanical implementation is delegated to background subagents…
Generates a Jupyter notebook that deploys fine-tuned models from SageMaker Serverless Model Customization to SageMaker endpoints or Bedrock.
Use when you have a pre-trained Keras model and need to deploy it via a Docker-based TensorFlow Serving API (e.g., for molecular classification via SMILES), but the model's layer…
Model Drift Detector - Auto-activating skill for ML Deployment. Triggers on: model drift detector, model drift detector Part of the ML Deployment skill category.
Automated reproduction of comprehensive model evaluation benchmarks following the Benchmark Suite V3.
Automated reproduction of comprehensive model evaluation benchmarks following the Benchmark Suite V3.
Automated reproduction of comprehensive model evaluation benchmarks following the Benchmark Suite V3.
Model interpretability and explainability using SHAP, LIME, feature importance, and partial dependence plots.
Model Export Helper - Auto-activating skill for ML Deployment. Triggers on: model export helper, model export helper Part of the ML Deployment skill category.
Model Export Helper - Auto-activating skill for ML Deployment. Triggers on: model export helper, model export helper Part of the ML Deployment skill category.
Assist with model export helper operations. Auto-activating skill for ML Deployment. Triggers on: model export helper, model export helper Part of the ML Deployment skill…
Fine-tune LLMs and ML models — LoRA, QLoRA, PEFT, Hugging Face. Dataset prep, training, evaluation, deployment
Use when you have a trained baseline GNN model with established hyperparameters (dropout rate, learning rate, epochs, optimizer settings) and want to evaluate whether alternative…
Interpret ML model predictions using SHAP, LIME, attention visualization, and probing techniques. Use when explaining model decisions, debugging model behavior, or building trust…
Use when after starting a TensorFlow Serving instance (e.g., via docker-compose)
Use when after deploying a TensorFlow Serving container (especially within a Dockerized stack like NP-Classifier), before running classification or inference pipelines, to confirm…
Model Pruning Helper - Auto-activating skill for ML Deployment. Triggers on: model pruning helper, model pruning helper Part of the ML Deployment skill category.
Model Quantization Tool - Auto-activating skill for ML Deployment. Triggers on: model quantization tool, model quantization tool Part of the ML Deployment skill category.
Centralized management of machine learning models throughout their lifecycle, including versioning, metadata, and production deployment.
Model Registry Manager - Auto-activating skill for ML Deployment. Triggers on: model registry manager, model registry manager Part of the ML Deployment skill category.
Shape source-backed model and diagram review artifacts for architecture, UML-style, C4, dependency, and workflow views.
Generate a reproducible, runnable PyTorch training repo for a medical-imaging task — segmentation, classification, detection, image-to-image synthesis, self-supervised…
Use when deploying a trained model behind an API. Covers FastAPI inference services, loading artifacts safely, request validation, batching, ONNX/quantization for speed, health…
LLM and ML model deployment for inference. Use when serving models in production, building AI APIs, or optimizing inference.
Deploy ML models as production APIs with vLLM, TGI, ONNX Runtime, batching, autoscaling, and GPU optimization.
Deploy ML models on Kubernetes with KServe (formerly KFServing) and NVIDIA Triton Inference Server. Includes canary deployments, autoscaling, model versioning, A/B testing, and…