Focus: Designing, evaluating, and implementing Autonomous AI Agents, ReAct loops, planning, and tool use.
Triggers: agent architecture, multi-agent systems, react loop, tool calling, autonomous agent
2. Advanced Technical Patterns
The agent acts as an AI Architect, specializing in agentic workflows beyond simple RAG or zero-shot generation.
ReAct (Reason + Act) Loop
Mechanics: The model is prompted to output a "Thought" (reasoning) followed by an "Action" (tool call). It then receives an "Observation" (tool result) and continues.
Optimization: Forcing strict JSON output schemas for tool calls to prevent parsing errors. Pre-filling the assistant message to guide the thought process.
Multi-Agent Orchestration
Hierarchical: A Router/Manager agent analyzes the task and delegates sub-tasks to specialized worker agents (e.g., Code Writer, Code Reviewer).
Debate/Consensus: Two agents generate different solutions and a third agent acts as a judge to combine the best parts.
Memory Structures
Short-term Memory: The immediate context window (chat history). Often requires summarization when approaching token limits.
Long-term Memory: Semantic search over past interactions (Vector DBs) or updating a structured user profile (Entity-based memory).
3. Output Format
Provide the system prompt architecture.
Explain the tool-calling schema (OpenAI format or Anthropic format).
Use Mermaid sequence diagrams to map out the agent workflow.
1---2name: ai-agents3description: AI Agent Architectures4---5# AI Agent Architectures67## 1. Skill Context8**Focus**: Designing, evaluating, and implementing Autonomous AI Agents, ReAct loops, planning, and tool use.9**Triggers**: agent architecture, multi-agent systems, react loop, tool calling, autonomous agent1011## 2. Advanced Technical Patterns12The agent acts as an AI Architect, specializing in agentic workflows beyond simple RAG or zero-shot generation.1314### ReAct (Reason + Act) Loop15- **Mechanics**: The model is prompted to output a "Thought" (reasoning) followed by an "Action" (tool call). It then receives an "Observation" (tool result) and continues.16- **Optimization**: Forcing strict JSON output schemas for tool calls to prevent parsing errors. Pre-filling the assistant message to guide the thought process.1718### Multi-Agent Orchestration19- **Hierarchical**: A Router/Manager agent analyzes the task and delegates sub-tasks to specialized worker agents (e.g., Code Writer, Code Reviewer).20- **Sequential (Chain)**: Agent A's output becomes Agent B's input.21- **Debate/Consensus**: Two agents generate different solutions and a third agent acts as a judge to combine the best parts.2223### Memory Structures24- **Short-term Memory**: The immediate context window (chat history). Often requires summarization when approaching token limits.25- **Long-term Memory**: Semantic search over past interactions (Vector DBs) or updating a structured user profile (Entity-based memory).2627## 3. Output Format28- Provide the system prompt architecture.29- Explain the tool-calling schema (OpenAI format or Anthropic format).30- Use Mermaid sequence diagrams to map out the agent workflow.
Run npx skillmds@latest add j4flmao/ai-agents in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
AI Agent Architectures It is listed under AI & ML on SkillMD.
This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
j4flmao (@j4flmao) published this skill. Their other Agent Skills are listed on their SkillMD profile.
j4flmao