doanchienthangdev/omgkit

design-system-context

Automatic design system context injection for UI consistency

Langue du texte source : anglais

developing-test-driven

AI agent practices test-first development with the Red-Green-Refactor cycle for confident, well-designed code. Use when implementing features, fixing bugs, or establishing testing practices.

Langue du texte source : anglais

test-enforcement

The agent enforces mandatory test completion before any task or feature can be marked as done, ensuring code quality through strict validation gates and evidence-based completion criteria.

Langue du texte source : anglais

test-task-generation

The agent automatically generates comprehensive test tasks from feature requirements, ensuring every implementation task has corresponding test coverage with proper acceptance criteria.

Langue du texte source : anglais

workflow-config-system

The agent implements a centralized workflow configuration system for Git workflows, enabling set-once-use-everywhere automation for trunk-based development, gitflow, and github-flow patterns with integrated testing automation.

Langue du texte source : anglais

git-hooks-integration

The agent implements Git hooks that integrate with the workflow config system, automating pre-commit checks, commit message validation, pre-push tests, and post-merge actions.

Langue du texte source : anglais

dora-metrics-and-devops-performance

The agent implements DORA metrics tracking for measuring and improving software delivery performance. Use when establishing engineering metrics, benchmarking teams, or driving DevOps transformation.

Langue du texte source : anglais

feature-flags-and-progressive-delivery

The agent implements feature flag systems for trunk-based development, canary releases, and A/B testing. Use when implementing gradual rollouts, kill switches, or experiment-driven development.

Langue du texte source : anglais

stacked-diffs-workflow

The agent implements stacked diffs (stacked PRs) for breaking large changes into reviewable chunks. Use when working on complex features, managing dependent changes, or optimizing code review flow.

Langue du texte source : anglais

chaos-engineering-and-resilience-testing

The agent implements chaos engineering practices for building resilient systems. Use when testing fault tolerance, designing game days, or validating system recovery.

Langue du texte source : anglais

testingchaos-testing

Chaos engineering and fault injection patterns for testing system resilience, failure recovery, and graceful degradation

Langue du texte source : anglais

testingcomprehensive-testing

Comprehensive 4D testing methodology covering Accuracy, Performance, Security, and Accessibility for production-ready quality assurance

Langue du texte source : anglais

testingmutation-testing

Mutation testing with Stryker to verify test quality by introducing code mutations and measuring detection rates

Langue du texte source : anglais

testingperformance-testing

Performance testing patterns including load testing, stress testing, benchmarking, and profiling for optimal application performance

Langue du texte source : anglais

testingproperty-testing

Property-based testing with Fast-Check for finding edge cases through automated input generation and invariant verification

Langue du texte source : anglais

testingsecurity-testing

Security testing patterns covering OWASP Top 10, injection prevention, authentication, and vulnerability scanning

Langue du texte source : anglais

ai-accelerators

AI hardware accelerators including GPUs, TPUs, custom silicon, and hardware-aware optimization strategies for ML workloads.

Langue du texte source : anglais

data-engineering

ML data engineering covering data pipelines, data quality, collection strategies, storage, and versioning for machine learning systems.

Langue du texte source : anglais

deep-learning-primer

Deep learning foundations including neural network basics, backpropagation, optimization, regularization, and training best practices.

Langue du texte source : anglais

deployment-paradigms

ML deployment paradigms including batch vs real-time inference, online vs offline serving, edge deployment, and serverless ML.

Langue du texte source : anglais

dnn-architectures

Deep neural network architectures including CNNs, RNNs, Transformers, and modern architectures for vision, NLP, and multimodal tasks.

Langue du texte source : anglais

edge-deployment

Edge deployment strategies including mobile optimization, embedded systems, TFLite, Core ML, and resource-constrained inference.

Langue du texte source : anglais

efficient-ai

Efficient AI techniques including model compression, quantization, pruning, knowledge distillation, and hardware-aware optimization for production systems.

Langue du texte source : anglais

feature-engineering

Feature engineering techniques including feature extraction, transformation, selection, and feature store management for ML systems.

Langue du texte source : anglais

ml-frameworks

ML framework best practices for PyTorch, TensorFlow, scikit-learn, and modern ML libraries including training patterns and optimization.

Langue du texte source : anglais

ml-serving-optimization

ML serving optimization techniques including batching, caching, model compilation, and latency reduction for production ML systems.

Langue du texte source : anglais

ml-systems-fundamentals

Core ML systems concepts including ML lifecycle, system architecture, requirements, and design principles for production ML.

Langue du texte source : anglais

ml-workflow

ML development workflow covering experiment design, baseline establishment, iterative improvement, and experiment tracking best practices.

Langue du texte source : anglais

mlops

MLOps practices including CI/CD for ML, experiment tracking, model monitoring, pipeline orchestration, and production ML operations.

Langue du texte source : anglais

model-deployment

Model deployment strategies including serving infrastructure, containerization, model packaging, versioning, and production deployment patterns.

Langue du texte source : anglais

model-development

Model development practices including model selection, training pipelines, hyperparameter tuning, evaluation, and model selection strategies.

Langue du texte source : anglais

model-optimization

Model optimization techniques including hyperparameter tuning, architecture search, training optimization, and performance profiling for ML systems.

Langue du texte source : anglais

robust-ai

Building robust AI systems including model monitoring, drift detection, reliability engineering, and failure handling for production ML.

Langue du texte source : anglais

ml-systems

Machine Learning Systems - comprehensive knowledge for building production ML systems from data engineering through deployment and operations. Based on Harvard ML Systems course and Designing ML Systems by Chip Huyen.

Langue du texte source : anglais

training-data

Training data management including labeling strategies, data augmentation, handling imbalanced data, and data splitting best practices.

Langue du texte source : anglais

contract-testing

Consumer-driven contract testing with Pact, schema validation, provider verification, and CI/CD integration.

Langue du texte source : anglais

distributed-tracing

Comprehensive distributed tracing with Jaeger, Zipkin, OpenTelemetry, correlation IDs, and span design.

Langue du texte source : anglais

service-discovery

Service discovery patterns with Consul, Kubernetes DNS, Eureka, health checks, and client-side load balancing.

Langue du texte source : anglais

service-mesh

Advanced service mesh implementation with Istio, Linkerd, traffic management, mTLS, and observability.

Langue du texte source : anglais

project-orchestration

Orchestrate autonomous project development through state-driven execution

Langue du texte source : anglais