Marketplace
Find the right skill for the job.
Browse the full catalog through outcome-first channels, technical facets, rating filters, and server-side pagination built for a large public marketplace.
cfn-hybrid-routing
Implements hybrid routing strategies for distributed systems with primary-secondary channel switching and load balancing. Supports failover mechanisms with configurable latency thresholds and multiple operational modes including synchronous and asynchronous routing.
deploy-automation
This skill automates deployment to multiple platforms (Vercel, Fly.io, Cloudflare, Netlify) based on project templates. It handles platform-specific configuration, runs pre-deploy checks, and returns production URLs. Supports Next.js, FastAPI, Hono, and static sites.
github-actions-templates
Provides ready-to-use GitHub Actions workflow templates for testing, building Docker images, deploying to Kubernetes, and security scanning. Includes concrete examples with specific action versions and best practices for common CI/CD scenarios.
django-security
Django security best practices, authentication, authorization, CSRF protection, SQL injection prevention, XSS prevention, and secure deployment configurations.
k8s-security-policies
Implement Kubernetes security policies including NetworkPolicy, PodSecurityPolicy, and RBAC for production-grade security. Use when securing Kubernetes clusters, implementing network isolation, or enforcing pod security standards.
local-environment
Local development environment management for Polar using Docker
release
Release a new version of atomic-agents to PyPI and GitHub. Use when the user asks to "release", "publish", "deploy", or "bump version" for atomic-agents.
knowledge-distillation
Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.
serving-llms-vllm
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
azd-deployment
Imported from https://github.com/microsoft/agent-skills.
MLOps Automation
Guide to refine MLOps projects with task automation, containerization, CI/CD pipelines, and robust experiment tracking.
administering-linux
Manage Linux systems covering systemd services, process management, filesystems, networking, performance tuning, and troubleshooting. Use when deploying applications, optimizing server performance, diagnosing production issues, or managing users and security on Linux servers.
github-workflow-skill
Provides concrete GitHub workflow patterns including branch naming conventions, PR templates, and CI/CD setup. Offers specific examples for feature development and hotfixes with clear quality gate requirements. Focuses on enforcing team standards rather than automating complex tasks.
management
Provides type-safe configuration management with JSON schema validation for the Claude Flow Novice project. Supports export/import operations and centralized storage with Redis coordination for distributed environments.
plan-validate-execute-template
Provides a structured template for implementing approval-gated workflows with plan-validate-execute-verify phases. Includes concrete examples for database migrations and clear guidance on when to use it. The template enforces safety checks before irreversible operations.
cost-optimization
Provides concrete cloud cost optimization strategies with specific commands and examples for AWS. Covers reserved instances, spot instances, rightsizing, storage tiering, and tagging practices. Includes actionable bash commands and Terraform snippets for immediate implementation.
moai-foundation-quality
Enterprise code quality orchestrator implementing TRUST 5 validation framework (Testable, Readable, Unified, Secured, Trackable). Provides automated quality gates, proactive issue detection, and Context7 integration for real-time best practices enforcement across 25+ programming languages. Includes quality metrics dashboard and CI/CD pipeline integration.
incident-response
Provides structured incident response procedures with severity levels, escalation paths, and common runbooks for infrastructure issues like high CPU or database slowdowns. It offers clear checklists and communication templates for on-call engineers.
recommendation-system
This skill provides a production-ready architecture for scalable recommendation systems, enabling rapid deployment of personalized APIs with feature stores, multi-tier caching, A/B testing, and comprehensive monitoring for low latency and high quality.
github-project-automation
This skill automates GitHub repository setup with pre-configured CI/CD workflows, security scanning (CodeQL, Dependabot), and structured issue templates, preventing common YAML and configuration errors while ensuring best practices.
backend-dev
This skill orchestrates a complete backend development workflow, transforming business requirements into production-ready systems with expert-led architecture, secure implementation, and automated DevOps pipelines.
dotnet-local-tools
Managing local .NET tools with dotnet-tools.json for consistent tooling across development environments and CI/CD pipelines.
github-multi-repo
This skill coordinates changes across multiple GitHub repositories using swarm intelligence. It synchronizes package versions, manages cross-repo dependencies, and optimizes repository structures. The tool helps teams maintain consistency when working with distributed codebases.
error-tracking
This skill provides detailed patterns for integrating Sentry v8 error tracking and performance monitoring into Node.js services. It includes specific code examples for controllers, routes, workflows, cron jobs, and database operations with clear error handling requirements.