Simular localmente los extractores del swarm (skills/voice/soul) con Claude Code como el LLM gemelo — sin EM, sin USDC, sin créditos LLM. Usar cuando el usuario diga "process all extractors for <user>", "process voice|skill|soul extractor for <user>", "procesa los extractores para <user>", "simula la compra de skills/voice/soul de <user>", o pida sincronizar los prompts del lab con los remotos ("sincroniza los extractores con los remotos") o traer los remotos al lab.
Build and deploy the KarmaCadabra Claude Agent SDK agents on Fargate. Use this skill whenever the user says "deploy", "build and push", "push to ECR", "redeploy", "rebuild Docker", or wants new code running on the KK swarm. Also use when discussing SDK agent Docker builds, ECR pushes, or the scheduled Fargate stack. Proactively use this after committing code changes that affect agent behavior (agents_sdk/, services/, lib/, scripts/kk/).
Execution Market API operations and escrow flow for KarmaCadabra agents. Use this skill when the user asks about "EM tasks", "escrow flow", "publish tasks", "buy/sell on EM", "browse marketplace", "debug EM", "assign a worker", "approve a submission", "agent purchases", "bounties", or any Execution Market API interaction. Also use when debugging 401/402/403/409/410/422/429 errors from the EM API, understanding the buyer/seller flow, or wiring escrow payments.
Sincroniza feedback operativo bidireccional entre KarmaCadabra y los equipos de sus dependencias (Execution Market + MeshRelay) sobre #agents en IRC. Usar cuando el usuario diga "KKFeedback", "KKFeedbackSync", "corre KKFeedback", "sincroniza feedback", "dales feedback a EM/meshrelay", "coge el feedback de KarmaCadabra". KarmaCadabra es la fuente de verdad. Bidireccional y auto-detecta dirección: desde el repo de KK DA el feedback; desde execution-market/meshrelay lo COGE.
Monitor and diagnose KarmaCadabra agent swarm health. Use this skill when the user asks to "check agents", "monitor swarm", "check logs", "are agents running", "agent health", "check heartbeats", "view agent status", "what are agents doing", "check IRC", "check balances", or any question about agent operational status. Also use proactively after deployments to verify agents are healthy, or when debugging agent behavior issues.