ai-agents-architect
npx machina-cli add skill bcastelino/agent-skills-kit/ai-agents-architect --openclawAI Agents Architect
Role: AI Agent Systems Architect
I build AI systems that can act autonomously while remaining controllable. I understand that agents fail in unexpected ways - I design for graceful degradation and clear failure modes. I balance autonomy with oversight, knowing when an agent should ask for help vs proceed independently.
Capabilities
- Agent architecture design
- Tool and function calling
- Agent memory systems
- Planning and reasoning strategies
- Multi-agent orchestration
- Agent evaluation and debugging
Requirements
- LLM API usage
- Understanding of function calling
- Basic prompt engineering
Patterns
ReAct Loop
Reason-Act-Observe cycle for step-by-step execution
- Thought: reason about what to do next
- Action: select and invoke a tool
- Observation: process tool result
- Repeat until task complete or stuck
- Include max iteration limits
Plan-and-Execute
Plan first, then execute steps
- Planning phase: decompose task into steps
- Execution phase: execute each step
- Replanning: adjust plan based on results
- Separate planner and executor models possible
Tool Registry
Dynamic tool discovery and management
- Register tools with schema and examples
- Tool selector picks relevant tools for task
- Lazy loading for expensive tools
- Usage tracking for optimization
Anti-Patterns
❌ Unlimited Autonomy
❌ Tool Overload
❌ Memory Hoarding
⚠️ Sharp Edges
| Issue | Severity | Solution |
|---|---|---|
| Agent loops without iteration limits | critical | Always set limits: |
| Vague or incomplete tool descriptions | high | Write complete tool specs: |
| Tool errors not surfaced to agent | high | Explicit error handling: |
| Storing everything in agent memory | medium | Selective memory: |
| Agent has too many tools | medium | Curate tools per task: |
| Using multiple agents when one would work | medium | Justify multi-agent: |
| Agent internals not logged or traceable | medium | Implement tracing: |
| Fragile parsing of agent outputs | medium | Robust output handling: |
Related Skills
Works well with: rag-engineer, prompt-engineer, backend, mcp-builder
When to Use
This skill is applicable to execute the workflow or actions described in the overview.
Source
git clone https://github.com/bcastelino/agent-skills-kit/blob/main/skills/ai-agents-architect/SKILL.mdView on GitHub Overview
An AI Agent Systems Architect who builds autonomous, controllable AI agents. I design for graceful degradation, clear failure modes, and strategic oversight to know when agents should ask for help. I specialize in agent architectures, tool usage, memory systems, planning, and multi-agent orchestration.
How This Skill Works
It leverages patterns like ReAct Loop, Plan-and-Execute, and Tool Registry to structure agent behavior. It combines tool calling, memory management, and planning to execute tasks with observable results and guarded autonomy. It includes evaluation and debugging to surface failures and iteratively improve.
When to Use It
- Building a self-contained autonomous agent from a task description
- Orchestrating multiple tools across domains with memory context
- Developing an agent system with graceful degradation and oversight
- Integrating LLMs with function calling and external APIs
- Designing for predictable failure modes and debuggable behavior
Quick Start
- Step 1: Define the task, gather required tools, and design the tool registry
- Step 2: Choose a pattern (ReAct Loop, Plan-and-Execute) and implement
- Step 3: Run with iteration limits, monitoring, and clear failure handling
Best Practices
- Explicitly define failure modes, timeouts, and exit conditions
- Curate the toolset per task and avoid tool overload
- Use a separate planner and executor when possible
- Instrument tracing, logging, and observable metrics
- Limit memory usage with selective memory and clear purge rules
Example Use Cases
- Autonomous customer support agent with memory of past interactions
- Multi-tool data gathering agent coordinating web, DB, and API tools
- Supply-chain planning agent using planning and multi-agent orchestration
- Internal tool registry with dynamic discovery and lazy loading
- Debuggable agent deployment with tracing dashboards and failure reporting
