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.
tensorrt-llm
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.
deploying-vmcp-locally
Deploys a VirtualMCPServer configuration locally for manual testing and verification
tag-manager
A specialized tool for creating and pushing semantic version tags with GPG signing support. It validates tag formats, checks commit existence, handles signing requirements, and delegates to platform-specific Git handlers. Useful for release workflows and CI/CD pipelines.
Delegating to CDN Agent
This skill delegates Fastly CDN queries to a specialized sub-agent to prevent main context pollution. It provides clear recognition patterns, example triggers, and delegation instructions. The approach reduces token usage and isolates CDN-specific knowledge while maintaining clean user-facing responses.
Delegating to New Relic Agent
This skill automatically detects New Relic-related queries and delegates them to a specialized sub-agent. It prevents context pollution in the main assistant and reduces token costs by offloading monitoring-specific tasks. The skill includes clear trigger patterns and example workflows for common New Relic operations like NRQL queries, alert checks, and drop rule management.
mcp
This skill provides Docker container configurations for running MCP servers based on agent types. It maps frontend, backend, and testing agents to specific MCP tools like Playwright, database connectors, and API testing services. The approach separates concerns but requires custom Docker images.
systematic-debugging
A structured debugging methodology that enforces root cause analysis before fixes. Provides four-phase process with specific checklists, red flag warnings, and multi-component system guidance. Prevents guesswork by requiring evidence gathering and hypothesis testing.
recover-from-error
Provides structured recovery procedures for Claude agent execution errors, focusing on build failures, agent crashes, and session interruptions. It offers concrete bash scripts to diagnose issues and decision trees for appropriate actions.
backend-development
Provides structured guidance for backend development with technology selection matrices, implementation checklists, and reference documentation covering APIs, databases, security, testing, and deployment. Offers concrete recommendations for frameworks, authentication methods, and performance optimization techniques.
cfn-context-pruner
A shell script that reduces Claude Flow Novice context size by summarizing previous iterations while keeping current iteration details. It cuts context from 120KB to 15KB across 10 iterations by extracting key feedback themes and tracking deliverables.
security-hardening
Provides security hardening guidance for AWS and Kubernetes with specific CIS benchmark recommendations, YAML examples for pod security and network policies, and scanning commands for containers and infrastructure. Focuses on practical implementation steps rather than theoretical concepts.
deployment-validator
This skill validates release readiness through structured pre-deployment checks across code, database, schedules, and infrastructure. It provides a risk assessment matrix and generates deployment readiness reports with clear approval recommendations.
diagrams-architect
Creates professional Mermaid diagrams following C4 Model conventions for system architecture visualization, specializing in context, container, component, and deployment diagrams with strict syntax validation and proper file placement.
release-coordinator
Coordinates multi-repository releases by managing dependencies, orchestrating release order, and validating cross-repo checks. It supports lockstep, independent, and umbrella versioning strategies to ensure smooth, synchronized deployments across complex software ecosystems.
kafka-iac-deployment
Provides expert Infrastructure as Code (IaC) guidance for deploying Apache Kafka using Terraform across self-hosted KRaft clusters, AWS MSK, and Azure Event Hubs, enabling automated, scalable, and platform-optimized Kafka infrastructure.
ado-resource-validator
This skill validates and automatically creates Azure DevOps projects and resources based on your .env configuration, supporting multiple organizational strategies and prompting for user decisions when needed.
k8s-manifest-generator
This skill generates production-ready Kubernetes manifests for Deployments, Services, ConfigMaps, and Secrets, following security best practices and conventions to ensure reliable, secure, and well-configured cloud-native deployments.
rc-manager
Manages the entire Release Candidate workflow from alpha/beta/RC tagging to final production promotion, including versioning, testing validation, and deployment coordination across multiple stages.
register-twilio-test-audio
This skill provides step-by-step instructions for uploading mulaw audio files to S3 and integrating them with a Twilio call script. It includes conversion commands, S3 upload procedures, and testing steps for voice call audio files.
feedback-handler
Manages human feedback requests within automated workflows by posting structured questions to GitHub issues and tracking responses. Handles six feedback types with clear state management and event emission.
session-start-hook
Configures automatic setup scripts for Claude Code web sessions. Installs dependencies, sets environment variables, and prepares development environments when remote sessions start. Includes templates for Node.js, Python, Ruby, Go, and full-stack projects with environment detection.
farm-monitor
Provides setup and configuration guidance for Braiins Farm Monitor, a free Prometheus/Grafana stack for Bitcoin mining fleet monitoring. Includes Docker commands, config examples, and troubleshooting notes. Documentation is sourced from GitHub README.
cloud-native-checklist
Generates structured checklists and Architecture Decision Records for assessing applications against CNCF and 12-Factor App standards. Provides concrete examples for health endpoints, graceful shutdown, and container security. Includes a shell script for quick assessment.
azure-devops
Complete Azure DevOps automation - boards, repos, pipelines, artifacts