Loading...
Loading...
Found 8 Skills
Strategies for managing LLM context windows effectively in AI agents. Use when building agents that handle long conversations, multi-step tasks, tool orchestration, or need to maintain coherence across extended interactions.
Build production-ready MCP clients in TypeScript or Python. Handles connection lifecycle, transport abstraction, tool orchestration, security, and error handling. Use for integrating LLM applications with MCP servers.
Use when the workflow needs multi-step processing with sequential, parallel, or conditional tool compositions and proper data flow.
Develop agentic software and multi-agent systems using Google ADK in Python
Generate complete launch asset package by composing primitives. Runs: /product-hunt-kit, /og-hero-image, /announce, /app-screenshots (if mobile). Use when: preparing full launch, generating all marketing assets at once. Keywords: launch, assets, marketing, bundle, all assets.
Optimize Claude Code prompts for Opus 4.6, Sonnet 4.5, and Haiku 4.5 with model-aware reasoning settings, context control, safe tool use, and concise output shaping.
Comprehensive knowledge of Claude Agent SDK architecture, tools, hooks, skills, and production patterns. Auto-activates for agent building, SDK integration, tool design, and MCP server tasks.
Use when any Maestro command is invoked — provides foundational workflow design principles across prompt engineering, context management, tool orchestration, agent architecture, feedback loops, knowledge systems, and guardrails.