hajekim/agentic-design-patterns-skills
Skill Claude CodeCodex
This skill should be used when the user wants to "self-evaluate output", "iterative refinement", "LLM as critic", "self-correction loop", "quality improvement loop", "review and revise", "agent self-assessment", "critique and improve", "self-improving output", "feedback loop agent", "generate then critique", "refine…
hajekim/agentic-design-patterns-skills
Skill Claude CodeCodex
This skill should be used when the user wants to "optimize agent resource usage", "token budget management", "cost-aware agents", "efficient LLM calls", "agent cost optimization", "reduce API costs", "agent performance optimization", "latency optimization", "token counting", "model selection strategy", "compute budget…
hajekim/agentic-design-patterns-skills
Skill Claude CodeCodex
This skill should be used when the user wants to "route requests", "classify input and delegate", "dynamic decision-making", "conditional agent flow", "dispatch to sub-agents", "intent classification", "triage incoming requests", "agent router", "request dispatcher", "multi-path agent", "semantic routing", "classifier…
hajekim/agentic-design-patterns-skills
Skill Claude CodeCodex
This skill should be used when the user wants to "call external APIs", "use tools in agents", "function calling", "web search integration", "code execution", "database queries", "agent tool integration", "extend agent capabilities", "RAG tool", "external service calls", "give agent tools", "agent with web search"…
hajekim/agentic-design-patterns-extension
Instructions file Gemini CLI
Gemini CLI instructions for hajekim/agentic-design-patterns-extension, covering agentic design patterns — extension context, how this extension works, 28 patterns — quick reference, core patterns and state management.
hajekim/agentic-design-patterns-extension
Agent
Agentic design pattern architect. Recommends the optimal combination of patterns from the 28-pattern library for a given problem. Use when: designing a new AI agent system, choosing patterns, comparing pattern trade-offs, planning multi-pattern architectures.
hajekim/agentic-design-patterns-extension
Agent
Agentic design pattern compliance reviewer. Reviews code to verify it correctly implements agentic design patterns from the 28-pattern library. Use when: reviewing agent code, checking pattern compliance, validating SDK usage, catching deprecated library usage.
hajekim/agentic-design-patterns-extension
Skill Claude CodeCodex
This skill should be used when the user wants to "agent-to-agent communication", "A2A protocol", "inter-agent messaging", "agent network", "agent federation", "cross-agent calls", "distributed agent systems", "agent discovery", "agent cards", "standardized agent communication", "remote agent invocation", "multi-agent…
hajekim/agentic-design-patterns-extension
Skill Claude CodeCodex
This skill should be used when the user wants to "choose agent framework", "compare LangChain vs LangGraph", "compare ADK vs LangGraph", "which framework to use for agents", "LangGraph tutorial", "CrewAI setup", "agentic framework comparison", "framework selection guide", "LangChain LCEL", "Google ADK tutorial"…
hajekim/agentic-design-patterns-extension
Skill Claude CodeCodex
This skill should be used when the user wants to build agents with "Google AgentSpace", "no-code agent builder", "agent designer Google", "AI Applications Google Cloud", "Google Cloud no-code agent", "enterprise agent platform", "no-code AI agent", "AgentSpace prompt gallery", "Google Agent Designer", "Knowledge Graph…
hajekim/agentic-design-patterns-extension
Skill Claude CodeCodex
This skill should be used when the user wants to use "AI CLI agent", "Claude Code", "Claude CLI", "Gemini CLI", "Aider", "GitHub Copilot CLI", "AI terminal agent", "AI coding assistant CLI", "Terminal-Bench", "AI command line coding tool", "agentic coding assistant", "AI pair programmer terminal", "large-scale…
hajekim/agentic-design-patterns-extension
Skill Claude CodeCodex
This skill should be used when the user wants to build a "coding agent team", "AI software development team", "vibe coding", "human-agent team for software", "AI pair programmer team", "scaffolder agent", "coding specialist agent", "augmented development team", "agent-assisted coding workflow", "AI code review agent"…
hajekim/agentic-design-patterns-extension
Skill Claude CodeCodex
This skill should be used when the user wants to build "GUI agent", "computer use agent", "browser automation agent", "desktop automation", "visual agent", "screen interaction agent", "web automation agent", "agent computer interaction", "ACI agent", "click automation", "multimodal agent with vision", "Project Mariner…
hajekim/agentic-design-patterns-extension
Skill Claude CodeCodex
This skill should be used when the user wants to learn "prompt engineering", "few-shot prompting", "zero-shot prompting", "chain of thought prompting", "structured output prompting", "role prompting", "system prompt design", "prompt best practices", "CoT prompting", "Pydantic structured output", "prompt iteration"…
hajekim/agentic-design-patterns-extension
Skill Claude CodeCodex
This skill should be used when the user wants to understand "reasoning models", "thinking tokens", "extended thinking", "LLM internal reasoning", "o1 style reasoning", "Gemini thinking model", "chain of thought internally", "reasoning vs standard models", "when to use reasoning models", "inference-time compute…
hajekim/agentic-design-patterns-extension
Skill Claude CodeCodex
This skill should be used when the user wants to "evaluate agent performance", "agent benchmarking", "LLM evaluation", "agent testing", "measure agent quality", "agent metrics", "hallucination detection", "answer quality scoring", "agent monitoring in production", "LLM observability", "agent evals", "test agent…
hajekim/agentic-design-patterns-extension
Skill Claude CodeCodex
This skill should be used when the user wants to "handle agent errors", "graceful degradation", "agent fault tolerance", "retry logic for agents", "error recovery strategies", "fallback mechanisms", "agent robustness", "exception management", "agent failure handling", "circuit breaker pattern", "tool error handling"…
hajekim/agentic-design-patterns-extension
Skill Claude CodeCodex
This skill should be used when the user wants to "agent exploration", "exploitation vs exploration", "bandit algorithms for agents", "curiosity-driven agents", "agent discovery", "novel solution finding", "try new approaches", "epsilon-greedy agents", "UCB agents", "agent experimentation", "adaptive sampling"…
hajekim/agentic-design-patterns-extension
Skill Claude CodeCodex
This skill should be used when the user wants to "agent goal management", "define agent objectives", "goal decomposition", "goal tracking", "monitor agent progress", "OKR for agents", "success criteria for agents", "goal-oriented agents", "agent performance monitoring", "task completion tracking", "hierarchical goal…
hajekim/agentic-design-patterns-extension
Skill Claude CodeCodex
This skill should be used when the user wants to "agent safety", "guardrails for AI agents", "prevent harmful outputs", "content moderation for agents", "safe agent behavior", "output filtering", "input validation", "jailbreak prevention", "agent constraints", "responsible AI agents", "safety layers", "bias detection…
hajekim/agentic-design-patterns-extension
Skill Claude CodeCodex
This skill should be used when the user wants to "human approval for agents", "agent oversight", "human-in-the-loop", "HITL", "human intervention", "agent confirmation", "interrupt agent for review", "human feedback during execution", "agent escalation", "require human approval", "agent checkpoints", "pause agent for…
hajekim/agentic-design-patterns-extension
Skill Claude CodeCodex
This skill should be used when the user wants to "agents that improve over time", "self-improving agents", "reinforcement learning", "few-shot learning", "online learning", "agent fine-tuning", "adapt from experience", "learn from feedback", "update agent behavior", "self-modifying agents", "RLHF", "DPO", "agent that…
hajekim/agentic-design-patterns-extension
Skill Claude CodeCodex
This skill should be used when the user wants to "Model Context Protocol", "MCP server", "MCP client", "standardized tool integration", "JSON-RPC agent tools", "LLM tool protocol", "connect agents to external tools", "MCP primitives", "FastMCP", "ADK MCPToolset", "plug-and-play agent tools", "MCP integration", "tool…
hajekim/agentic-design-patterns-extension
Skill Claude CodeCodex
This skill should be used when the user wants to "persist agent state", "remember past conversations", "short-term memory", "long-term memory", "session management", "vector database for agents", "agent memory", "context window management", "store user preferences", "recall previous interactions", "stateful agents"…