Imported from majiayu000/claude-skill-registry (skills/agent/ai-agents/SKILL.md). Install upstream with npx skills add majiayu000/claude-skill-registry --skill ai-agents. Copyright stays with the author.

AI Agents Development — Production Skill Hub

Modern Best Practices (December 2025): deterministic control flow, bounded tools, auditable state, MCP-based tool integration, handoff-first orchestration, multi-layer guardrails, OpenTelemetry tracing, and human-in-the-loop controls (OWASP LLM Top 10: https://owasp.org/www-project-top-10-for-large-language-model-applications/).

This skill provides production-ready operational patterns for designing, building, evaluating, and deploying AI agents. It centralizes procedures, checklists, decision rules, and templates used across RAG agents, tool-using agents, OS agents, and multi-agent systems.

No theory. No narrative. Only what Claude can execute.

When to Use This Skill

Claude should activate this skill whenever the user asks for:

• Designing an agent (LLM-based, tool-based, OS-based, or multi-agent).
• Scoping capability maturity and rollout risk for new agent behaviors.
• Creating action loops, plans, workflows, or delegation logic.
• Writing tool definitions, MCP tools, schemas, or validation logic.
• Generating RAG pipelines, retrieval modules, or context injection.
• Building memory systems (session, long-term, episodic, task).
• Creating evaluation harnesses, observability plans, or safety gates.
• Preparing CI/CD, rollout, deployment, or production operational specs.
• Producing any template in /resources/ or /templates/.
• Implementing MCP servers or integrating Model Context Protocol.
• Setting up agent handoffs and orchestration patterns.
• Configuring multi-layer guardrails and safety controls.
• For prompt scaffolds, retrieval tuning, or security depth, see Scope Boundaries below.

Scope Boundaries (Use These Skills for Depth)

• Prompt scaffolds & structured outputs → ai-prompt-engineering
• RAG retrieval & chunking → ai-rag
• Search tuning (BM25/HNSW/hybrid) → ai-rag
• Security/guardrails → ai-mlops
• Inference optimization → ai-llm-inference

Quick Reference

Decision Tree: Choosing Agent Architecture

What does the agent need to do?
    ├─ Answer questions from knowledge base?
    │   ├─ Simple lookup? → RAG Agent (LangChain/LlamaIndex + vector DB)
    │   └─ Complex multi-step? → Agentic RAG (iterative retrieval + reasoning)
    │
    ├─ Perform external actions (APIs, tools, functions)?
    │   ├─ 1-3 tools, linear flow? → Tool-Using Agent (LangGraph + MCP)
    │   └─ Complex workflows, branching? → Planning Agent (ReAct/Plan-Execute)
    │
    ├─ Write/modify code autonomously?
    │   ├─ Single file edits? → Tool-Using Agent with code tools
    │   └─ Multi-file, issue resolution? → Code/SWE Agent (HyperAgent pattern)
    │
    ├─ Delegate tasks to specialists?
    │   ├─ Fixed workflow? → Multi-Agent Sequential (A → B → C)
    │   ├─ Manager-Worker? → Multi-Agent Hierarchical (Manager + Workers)
    │   └─ Dynamic routing? → Multi-Agent Group Chat (collaborative)
    │
    ├─ Control desktop/browser?
    │   └─ OS Agent (Anthropic Computer Use + MCP for system access)
    │
    └─ Hybrid (combination of above)?
        └─ Planning Agent that coordinates:
            - Tool-using for actions (MCP)
            - RAG for knowledge (MCP)
            - Multi-agent for delegation (A2A)
            - Code agents for implementation

Protocol Selection:

• Use MCP for: Tool access, data retrieval, single-agent integration
• Use A2A for: Agent-to-agent handoffs, multi-agent coordination, task delegation

Core Concepts (Vendor-Agnostic)

Control Flow Options

• Reactive: direct tool routing per user request (fast, brittle if unbounded).
• Workflow (FSM/DAG): explicit states and transitions (default for deterministic production).
• Planner/Executor: plan with strict budgets, then execute step-by-step (use when branching is unavoidable).
• Orchestrated multi-agent: separate roles with validated handoffs (use when specialization is required).

Memory Types (Tradeoffs)

• Short-term (session): cheap, ephemeral; best for conversational continuity.
• Episodic (task): scoped to a case/ticket; supports audit and replay.
• Long-term (profile/knowledge): high risk; requires consent, retention limits, and provenance.

Failure Handling (Production Defaults)

• Classify errors: retriable vs fatal vs needs-human.
• Bound retries: max attempts, backoff, jitter; avoid retry storms.
• Fallbacks: degraded mode, smaller model, cached answers, or safe refusal.

Do / Avoid

Do

• Do keep state explicit and serializable (replayable runs).
• Do enforce tool allowlists, scopes, and idempotency for side effects.
• Do log traces/metrics for model calls and tool calls (OpenTelemetry GenAI semantic conventions: https://opentelemetry.io/docs/specs/semconv/gen-ai/).

Avoid

• Avoid runaway autonomy (unbounded loops or step counts).
• Avoid hidden state (implicit memory that cannot be audited).
• Avoid untrusted tool outputs without validation/sanitization.

Navigation: Core Concepts & Patterns

Governance & Maturity

• Agent Maturity & Governance - resources/agent-maturity-governance.md
  • Capability maturity levels (L0-L4)
  • Identity & policy enforcement
  • Fleet control and registry management
  • Deprecation rules and kill switches

Modern Best Practices

• Modern Best Practices - resources/modern-best-practices.md
  • Model Context Protocol (MCP)
  • Agent-to-Agent Protocol (A2A)
  • Agentic RAG (Dynamic Retrieval)
  • Multi-layer guardrails
  • LangGraph over LangChain
  • OpenTelemetry for agents

Context Management

• Context Engineering - resources/context-engineering.md
  • Progressive disclosure
  • Session management
  • Memory provenance
  • Retrieval timing
  • Multimodal context

Core Operational Patterns

• Operational Patterns - resources/operational-patterns.md
  • Agent loop pattern (PLAN → ACT → OBSERVE → UPDATE)
  • OS agent action loop
  • RAG pipeline pattern
  • Tool specification
  • Memory system pattern
  • Multi-agent workflow
  • Safety & guardrails
  • Observability
  • Evaluation patterns
  • Deployment & CI/CD

Navigation: Protocol Implementation

• MCP Practical Guide - resources/mcp-practical-guide.md Building MCP servers, tool integration, and standardized data access

• MCP Server Builder - resources/mcp-server-builder.md End-to-end checklist for workflow-focused MCP servers (design → build → test)

• A2A Handoff Patterns - resources/a2a-handoff-patterns.md Agent-to-agent communication, task delegation, and coordination protocols

• Protocol Decision Tree - resources/protocol-decision-tree.md When to use MCP vs A2A, decision framework, and selection criteria

Navigation: Agent Capabilities

• Agent Operations - resources/agent-operations-best-practices.md Action loops, planning, observation, and execution patterns

• RAG Patterns - resources/rag-patterns.md Contextual retrieval, agentic RAG, and hybrid search strategies

• Memory Systems - resources/memory-systems.md Session, long-term, episodic, and task memory architectures

• Tool Design & Validation - resources/tool-design-specs.md Tool schemas, validation, error handling, and MCP integration

Skill Packaging & Sharing

• Skill Lifecycle - resources/skill-lifecycle.md Scaffold, validate, package, and share Claude skills with teams (Slack-ready)

• API Contracts for Agents - resources/api-contracts-for-agents.md Request/response envelopes, safety gates, streaming/async patterns, error taxonomy

• Multi-Agent Patterns - resources/multi-agent-patterns.md Manager-worker, sequential, handoff, and group chat orchestration

• OS Agent Capabilities - resources/os-agent-capabilities.md Desktop automation, UI grounding, and computer use patterns

• Code/SWE Agents - resources/code-swe-agents.md SE 3.0 paradigm, autonomous coding patterns, SWE-Bench, HyperAgent architecture

Navigation: Production Operations

• Evaluation & Observability - resources/evaluation-and-observability.md OpenTelemetry GenAI, metrics, LLM-as-judge, and monitoring

• Deployment, CI/CD & Safety - resources/deployment-ci-cd-and-safety.md Multi-layer guardrails, HITL controls, NIST AI RMF, production checklists

Navigation: Templates (Copy-Paste Ready)

Checklists

• Agent Design & Safety Checklist - templates/checklists/agent-safety-checklist.md Go/No-Go safety gate: permissions, HITL triggers, eval gates, observability, rollback

Core Agent Templates

• Standard Agent Template - templates/core/agent-template-standard.md Full production spec: memory, tools, RAG, evaluation, observability, safety

• Specialized Agent Template - templates/core/agent-template-specialized.md Domain-specific agents with custom capabilities and constraints

• Quick Agent Template - templates/core/agent-template-quick.md Minimal viable agent for rapid prototyping

RAG Templates

• Basic RAG - templates/rag/rag-basic.md Simple retrieval-augmented generation pipeline

• Advanced RAG - templates/rag/rag-advanced.md Contextual retrieval, reranking, and agentic RAG patterns

• Hybrid Retrieval - templates/rag/hybrid-retrieval.md Semantic + keyword search with BM25 fusion

Tool Templates

• Tool Definition - templates/tools/tool-definition.md MCP-compatible tool schemas with validation and error handling

• Tool Validation Checklist - templates/tools/tool-validation-checklist.md Testing, security, and production readiness checks

Multi-Agent Templates

• Manager-Worker Template - templates/multi-agent/manager-worker-template.md Orchestration pattern with task delegation and result aggregation

• Evaluator-Router Template - templates/multi-agent/evaluator-router-template.md Dynamic routing with quality assessment and domain classification

Service Layer Templates

• FastAPI Agent Service - ../dev-api-design/templates/fastapi/fastapi-complete-api.md Auth, pagination, validation, error handling; extend with model lifespan loads, SSE, background tasks

External Sources Metadata

• Curated References - data/sources.json Authoritative sources spanning standards, protocols, and production agent frameworks

Shared Utilities (Centralized patterns — extract, don't duplicate)

• ../software-clean-code-standard/utilities/llm-utilities.md — Token counting, streaming, cost estimation
• ../software-clean-code-standard/utilities/error-handling.md — Effect Result types, correlation IDs
• ../software-clean-code-standard/utilities/resilience-utilities.md — p-retry v6, circuit breaker for API calls
• ../software-clean-code-standard/utilities/logging-utilities.md — pino v9 + OpenTelemetry integration
• ../software-clean-code-standard/utilities/observability-utilities.md — OpenTelemetry SDK, tracing, metrics
• ../software-clean-code-standard/utilities/testing-utilities.md — Test factories, fixtures, mocks
• ../software-clean-code-standard/resources/clean-code-standard.md — Canonical clean code rules (CC-*) for citation

Related Skills

This skill integrates with complementary Claude Code skills:

Core Dependencies

• ../ai-llm/ - LLM patterns, prompt engineering, and model selection for agents
• ../ai-rag/ - Deep RAG implementation: chunking, embedding, reranking
• ../ai-prompt-engineering/ - System prompt design, few-shot patterns, reasoning strategies

Production & Operations

• ../qa-observability/ - OpenTelemetry, metrics, distributed tracing
• ../software-security-appsec/ - OWASP Top 10, input validation, secure tool design
• ../ops-devops-platform/ - CI/CD pipelines, deployment strategies, infrastructure

Supporting Patterns

• ../dev-api-design/ - REST/GraphQL design for agent APIs and tool interfaces
• ../ai-mlops/ - Model deployment, monitoring, drift detection
• ../qa-debugging/ - Agent debugging, error analysis, root cause investigation

Usage pattern: Start here for agent architecture, then reference specialized skills for deep implementation details.

Usage Notes for Claude

• Modern Standards: Default to MCP for tools, agentic RAG for retrieval, handoff-first for multi-agent
• Lightweight SKILL.md: Use this file for quick reference and navigation
• Drill-down resources: Reference detailed resources for implementation guidance
• Copy-paste templates: Use templates when the user asks for structured artifacts
• External sources: Reference data/sources.json for authoritative documentation links
• No theory: Never include theoretical explanations; only operational steps

Key Modern Migrations

Traditional → Modern:

• Custom APIs → Model Context Protocol (MCP)
• Static RAG → Agentic RAG with contextual retrieval
• Ad-hoc handoffs → Versioned handoff APIs with JSON Schema
• Single guardrail → Multi-layer defense (5+ layers)
• LangChain agents → LangGraph stateful workflows
• Custom observability → OpenTelemetry GenAI standards
• Model-centric → Context engineering-centric

AI-Native SDLC Pattern (Delegate → Review → Own)

• Plan: Have the agent draft PLAN.md or use a planning tool; require code-path trace, dependency map, and risk/edge-case list before build starts.
• Design: Convert mocks to components; enforce design tokens/style guides; surface accessibility gaps; keep MCP-linked component libraries in context.
• Build: Let the agent scaffold end-to-end (models/APIs/UI/tests/docs); enforce long-run guardrails (time cap, allowed commands/tools, commit/PR gating, kill switch).
• Test: Demand failing test first; agent generates and runs suites; require coverage deltas and flaky-test notes; human reviews assertions and fixtures.
• Review: Agent runs first-pass review tuned for P0/P1; human focuses on architecture, performance, safety, and migration risk; always own final merge.
• Document: Agent drafts PR summaries, module/file notes, and mermaid diagrams; require doc updates in the same run; human adds “why” and approvals.
• Deploy & Maintain: Agent links logs/metrics via MCP for triage; propose hotfixes with rollback plans; human approves rollouts; track drift/regressions with evals.

Executive Briefing (Optional)

• Value: Coding agents compress SDLC time; delegate mechanical work, keep humans on intent/architecture; measurable gains come from tight guardrails plus eval loops.
• Cost & Risk: Training vs inference economics; long runs need caps/kill switches; data/secret handling and supply-chain policies stay human-owned.
• Governance: Multi-layer guardrails (policy prompt, tool allowlist, auth scopes, eval gates, audit logs); require human sign-off for deploys and safety-sensitive changes.