Four skills: agent-orchestrator — tool-calling loops, pipelines with checkpoints, provider routing with fallback, memory architecture, plus the wallet side of reselling LLM access; agent-evals — run/trace/thread evals, LLM judges, and fixtures grown from production; agent-interop — MCP servers and clients, A2A agent…
Audit Japanese construction and renovation estimates against the open JCCDB dataset and return Bitcoin-anchored, independently recomputable fair-price receipts. Read-only remote MCP, no API key. Adds /audit, /red-flags, /verify commands.