ai-agent-router

Route AI agent engineering prompts to architecture, orchestration, evaluation, safety, debugging, context, prompt, MCP, persona, local AI, and Compound Engineering skills. Use when prompts mention age

SKILL.md

GitHub

AI Agent Router

Choose the smallest relevant skill set:

  • Architecture/orchestration: agentic-engineering, agentic-os, agent-harness-construction, autonomous-agent-harness, plan-orchestrate, team-agent-orchestration.
  • Operations/debugging: agent-introspection-debugging, continuous-learning, continuous-learning-v2, enterprise-agent-ops, cost-aware-llm-pipeline.
  • Evaluation/safety: agent-eval, eval-harness.
  • Prompt/context: context-budget, token-budget-advisor, prompt-optimizer, strategic-compact, ck.
  • MCP/tooling: mcp-server-patterns, nanoclaw-repl.
  • Compound Engineering: ce-compound, ce-work, ce-plan, ce-polish, ce-ideate, ce-optimize, and related ce-* skills.
  • Persona/local AI: openclaw-persona-forge, foundation-models-on-device.

Read only the selected child skill(s), then execute the user request.