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.
cloudflare-kv
This skill provides comprehensive guidance for using Cloudflare Workers KV, a global key-value storage service. It covers setup, core operations (put, get, delete, list), best practices, and critical rules for handling consistency, TTL, rate limits, and common errors to optimize edge caching and data management.
cascade-orchestrator
Coordinates multiple Claude micro-skills into sequential or parallel workflows with conditional logic. Integrates Codex sandbox for auto-fixing test failures and routes tasks to different AI models (Gemini/Codex) based on task requirements. Supports swarm coordination via ruv-swarm MCP for parallel execution.
testing-patterns
Provides concrete testing patterns for a specific project (ActionPhase), covering backend Go unit tests, React component tests, and Playwright E2E tests. It enforces a strict workflow where E2E tests are written last, after unit, API, and component tests pass. Includes specific commands, fixture data, and anti-pattern examples.
code-review
This skill enforces strict code review protocols for Claude, banning performative agreement and requiring evidence before completion claims. It provides concrete decision trees for receiving feedback, requesting reviews via subagent, and implementing verification gates. The approach targets common AI pitfalls in technical review processes.
cfn-improvement-recommender
Analyzes sprint retrospective data to identify bottlenecks and suggest improvements in agent selection, feedback processing, and iteration management. Provides confidence scores and tracks recommendation effectiveness over time.
pine-script-generator
Generates TradingView Pine Script code to visualize options positions from CSV data. Creates color-coded horizontal lines for strike prices with labels showing expiration dates and position details. Handles different option types and basic strategies.
model-usage
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
agent-tracing
Agent tracing CLI for inspecting agent execution snapshots. Use when user mentions 'agent-tracing', 'trace', 'snapshot', wants to debug agent execution, inspect LLM calls, view context engine data, or analyze agent steps. Triggers on agent debugging, trace inspection, or execution analysis tasks.
hybrid-search-implementation
Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.
hybrid-cloud-networking
Configure secure, high-performance connectivity between on-premises infrastructure and cloud platforms using VPN and dedicated connections. Use when building hybrid cloud architectures, connecting data centers to cloud, or implementing secure cross-premises networking.
copilot-sdk
Build agentic applications with GitHub Copilot SDK. Use when embedding AI agents in apps, creating custom tools, implementing streaming responses, managing sessions, connecting to MCP servers, or creating custom agents. Triggers on Copilot SDK, GitHub SDK, agentic app, embed Copilot, programmable agent, MCP server, custom agent.
codex-review
Professional code review with auto CHANGELOG generation, integrated with Codex AI
ai-sdk
Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, or tools, (2) Want to build AI agents, chatbots, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, etc.), streaming, tool calling, or structured output.
AgentDB Vector Search
Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.
opik
Imported from https://www.skillhub.club/skills/comet-ml-opik.
ml
Imported from https://github.com/microsoft/mcp-for-beginners.
prompt-engineer
Prompt engineering expert for chain-of-thought, few-shot learning, evaluation, and LLM optimization
dspy-ruby
This skill should be used when working with DSPy.rb, a Ruby framework for building type-safe, composable LLM applications. Use this when implementing predictable AI features, creating LLM signatures and modules, configuring language model providers (OpenAI, Anthropic, Gemini, Ollama), building agent systems with tools, optimizing prompts, or testing LLM-powered functionality in Ruby applications.
phoenix-evals
Build and run evaluators for AI/LLM applications using Phoenix.
mcp-developer
Use when building MCP servers or clients that connect AI systems with external tools and data sources. Invoke for MCP protocol compliance, TypeScript/Python SDKs, resource providers, tool functions.
ml-pipeline
Use when building ML pipelines, orchestrating training workflows, automating model lifecycle, implementing feature stores, or managing experiment tracking systems.
atomic-context
This skill should be used when the user asks to "create context provider", "dynamic context", "inject context", "BaseDynamicContextProvider", "share data between agents", or needs guidance on context providers, dynamic prompt injection, and sharing information across agents in Atomic Agents applications.
pytorch-fsdp2
Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with DeviceMesh.
pikaboard
Interact with PikaBoard task management API. Use when creating, updating, listing, or managing tasks. Agent-first kanban for AI teams. Triggers on: tasks, kanban, board, todo, backlog, sprint.