Home / Stacks / Agent Engineering Kit
🤝

Agent Engineering Kit

Engineer reliable AI agents — build on the Claude Agent SDK, coordinate teams with multi-agent patterns, give them memory, and keep them safe with mechanical guardrails and evaluation

6 skills · Works with Claude Code, Codex, Cursor & more

⚙️ Engineering
RARE ★

Claude Agent SDK

Build production agents with the Claude Agent SDK. Covers agent architecture, tool design, hooks, skills, MCP server integration, and the patterns for reliable, long-running agentic workflows.

Community 4.6K
Scanned
claude agent-sdk tools
mkdir -p ~/.claude/skills/claude-agent-sdk && curl -fsSL https://raw.githubusercontent.com/diegosouzapw/awesome-omni-skill/HEAD/skills/ai-agents/claude-agent-sdk/SKILL.md -o ~/.claude/skills/claude-agent-sdk/SKILL.md
⚙️ Engineering
RARE

Multi-Agent Orchestration Patterns

Design multi-agent systems with orchestrator, peer-to-peer, and hierarchical patterns. Covers task decomposition, agent handoffs, shared state, and coordination so a team of agents stays reliable instead of looping.

Community 3.3K
Scanned
multi-agent orchestration agents
mkdir -p ~/.claude/skills/multi-agent-patterns && curl -fsSL https://raw.githubusercontent.com/diegosouzapw/awesome-omni-skill/HEAD/skills/ai-agents/multi-agent-patterns/SKILL.md -o ~/.claude/skills/multi-agent-patterns/SKILL.md
⚙️ Engineering
RARE

AI Agent Memory Systems

Architect memory for AI agents — short-term context, long-term vector storage, and the retrieval strategies that decide what an agent actually remembers. Covers chunking, embedding, and recall over storage.

Community 1.9K
Scanned
agent-memory retrieval vector-store
mkdir -p ~/.claude/skills/agent-memory-systems && curl -fsSL https://raw.githubusercontent.com/diegosouzapw/awesome-omni-skill/HEAD/skills/ai-agents/agent-memory-systems/SKILL.md -o ~/.claude/skills/agent-memory-systems/SKILL.md
⚙️ Engineering
RARE

AI Agent Guardrails

Add mechanical guardrails that stop AI agents from bypassing your rules. Enforces policies with git hooks, secret detection, deployment verification, and import registries — born from real production incidents.

Community 1.6K
Scanned
guardrails ai-safety enforcement
mkdir -p ~/.claude/skills/agent-guardrails && curl -fsSL https://raw.githubusercontent.com/diegosouzapw/awesome-omni-skill/HEAD/skills/ai-agents/agent-guardrails/SKILL.md -o ~/.claude/skills/agent-guardrails/SKILL.md
⚙️ Engineering
RARE

AI Agent Evaluation

Test and benchmark LLM agents with behavioral tests, capability assessments, reliability metrics, and production monitoring — catching the failures that pass benchmarks but break in the real world.

Community 1.7K
Scanned
agent-evaluation testing benchmarking
mkdir -p ~/.claude/skills/agent-evaluation && curl -fsSL https://raw.githubusercontent.com/diegosouzapw/awesome-omni-skill/HEAD/skills/ai-agents/agent-evaluation/SKILL.md -o ~/.claude/skills/agent-evaluation/SKILL.md
⚙️ Engineering
RARE ★

MCP Server Builder

Build Model Context Protocol (MCP) servers that give AI agents access to your tools and data. Generates server scaffolding, tool definitions, resource handlers, and transport configurations for Claude, Cursor, and other MCP clients.

Community 3.9K
Scanned
mcp ai-agents protocol
mkdir -p ~/.claude/skills/mcp-server-builder && curl -fsSL https://raw.githubusercontent.com/anthropics/skills/HEAD/skills/mcp-builder/SKILL.md -o ~/.claude/skills/mcp-server-builder/SKILL.md

More Stacks

🤖

AI Builder Stack

Build AI-powered applications with RAG, multi-agent systems, prompt engineering, and MCP integrations
🔬

AI Research Toolkit

Run grounded, cited research at scale — ingest sources with NotebookLM, enforce anti-hallucination guardrails, build RAG pipelines, and transcribe audio into searchable knowledge
📊

Business Intelligence Stack

Ship dashboards and self-service analytics — Metabase and Superset dashboards, a Cube semantic layer for consistent metrics, Evidence BI-as-code reports, and dbt models feeding them all

View all stacks →

Added to wishlist