From and-humans
Interactive decision framework for choosing AI agent architectures. Use when someone asks "what agent framework should I use", "how should I architect my AI agent system", "LangGraph vs CrewAI", "which SDK should I pick", "help me choose an agent stack", or any question about comparing agent frameworks, orchestration layers, model selection for agents, or production vs prototype agent architecture decisions. Routes through a four-layer model (orchestration, runtime, models, infrastructure) to produce a concrete, opinionated stack recommendation.
How this skill is triggered — by the user, by Claude, or both
Slash command
/and-humans:agent-architecture-advisorThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
- User is choosing between agent frameworks or SDKs
Read prompts/main.md for the full interaction protocol.
The agent ecosystem has four layers. Most confusion comes from comparing across them.
npx claudepluginhub sjobergfredrik/and-humans-skills --plugin and-humansCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.