Explore AI skills for development, content, data and productivity. Compare the description and repository popularity before opening a skill.
AI agent completes development branches with comprehensive quality gates, clean git history, and thorough PR preparation. Use when wrapping up features, preparing for merge, or finalizing PRs.
Methods for evaluating AI model outputs - exact match, semantic similarity, LLM-as-judge, comparative evaluation, ELO ranking. Use when measuring AI quality, building eval pipelines, or comparing models.
End-to-end AI system evaluation - model selection, benchmarks, cost/latency analysis, build vs buy decisions. Use when selecting models, designing eval pipelines, or making architecture decisions.
AI agent applies a 5-phase systematic framework for tackling complex problems when conventional approaches fail. Use when stuck, blocked, or troubleshooting issues.
Builds high-performance FastAPI applications with async/await, Pydantic v2, dependency injection, and SQLAlchemy. Use when creating Python REST APIs, async backends, or microservices.
The agent implements Prisma ORM for type-safe database access with schema design, migrations, and queries. Use when building database layers, designing relational schemas, implementing type-safe queries, or man...
AI agent performs database administration tasks including backup/restore, monitoring, replication, security hardening, and maintenance operations. Use when managing production databases, troubleshooting perform...
Service discovery patterns with Consul, Kubernetes DNS, Eureka, health checks, and client-side load balancing.
AI agent structures complex reasoning through numbered thought sequences with explicit dependencies. Use when facing multi-step problems, complex debugging, or architectural decisions.
Enterprise monorepo patterns with Turborepo and Nx including task orchestration, caching, and CI/CD optimization
Claude builds responsive web layouts with mobile-first CSS, fluid typography, and container queries. Use when creating adaptive UIs that work across all device sizes.
MLOps practices including CI/CD for ML, experiment tracking, model monitoring, pipeline orchestration, and production ML operations.
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.
Claude implements WCAG 2.1 AA compliant web interfaces with proper ARIA, keyboard navigation, and screen reader support. Use when building accessible components or auditing existing UIs.
Security testing patterns covering OWASP Top 10, injection prevention, authentication, and vulnerability scanning
Advanced service mesh implementation with Istio, Linkerd, traffic management, mTLS, and observability.
ML data engineering covering data pipelines, data quality, collection strategies, storage, and versioning for machine learning systems.
Applies 7 systematic thinking modes for breakthrough problem-solving and 10x improvements. Use when tackling complex problems, seeking transformative insights, or escaping conventional thinking traps.
Multi-layer caching with Redis, CDN, and browser caching for optimal application performance
Efficient AI techniques including model compression, quantization, pruning, knowledge distillation, and hardware-aware optimization for production systems.
Mutation testing with Stryker to verify test quality by introducing code mutations and measuring detection rates
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...
Python development with type hints, async patterns, testing, and modern best practices
AI agent creates structured implementation plans with task breakdown, dependency mapping, risk assessment, and file-level detail. Use when planning features, projects, or complex implementations.
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.