Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Diagnose and recover CCB communication and reply delivery stalls. Use when a user reports a missing CCB_REPLY, stuck ask, agent stuck busy/delivering, queued work behind an active job, cancelled/incomplete reply, empty artifact, callback not continuing, duplicate retry after success, or a CCB mailbox/communication backend that appears stuck.
Private built-in CCB configuration skill for agentroles.ccb_self. Design, edit, validate, and prepare reloads for .ccb/ccb.config, role bindings, providers, windows, workspaces, tool windows, sidebar, and provider startup inputs. Use only inside ccb_self; non-self agents should delegate CCB config changes to ccb_self.
Use when the user asks to find, search for, or optimize the best quantization recipe for a model, including direct requests like "find the best quantization recipe and generate a PTQ checkpoint." Guides the multi-candidate loop: choose compute-vs-memory success metrics, select ModelOpt recipe baselines, design AutoQuant/manual recipe deltas, interpret sensitivity, and decide next candidates. Do NOT use for a single known PTQ recipe run (use ptq), serving (use deployment), creating/running evals (use evaluation or launching-evals), monitoring jobs (use monitor), MLflow browsing (use accessing-mlflow), or comparing completed baseline-vs-candidate scores only (use compare-results).
High-level umbrella router for navigating broad, cross-substrate architectural ambiguity. Triggers: Use when no narrower pre-flight clearly applies, or when work spans multiple trigger families such as new subsystems, protocols, MCP tools, or cross-substrate refactors.
Authoritative protocol for signaling blocked or input-required task states. Mandates targeted A2A pings using the Task.state envelope rather than global capacity broadcasts. Triggers: Use this skill whenever your execution becomes blocked, requires explicit operator input, or encounters a failure that halts progress.
Post-compaction recovery runbook for reconstructing active lane state from Memory Core recency, semantic recall, session rollups, and A2A. Triggers: Use immediately after context compaction/compression, resuming a summarized session, or noticing the active lane was reconstructed from a lossy summary.
Execute autonomous diagnostics, verify MCP server stability, and treat system degradation using tests and memory core forensics. Triggers: [Healthcheck, run health checklist, diagnose system collapse, MCP infrastructure failure, troubleshoot agent OS, system degraded, Sandman handoff verification failure, self-repair, system recovery]
Authoritative protocol for gracefully terminating an agent session. Mandates structured handover comments, mental-model states, and memory persistence to prevent Zero-State Amnesia. Triggers: When concluding a long-running session, executing the Sunset Protocol, handing over work for the next agent, or terminating an agent cycle.
Edit, update, or remove an existing custom agent. Shows current config and asks what to change. Also handles listing all custom agents. Triggers: EN: "edit my agent", "update agent", "remove agent", "delete agent", "list agents", "show my agents". IT: "modifica il mio agente", "aggiorna agente", "rimuovi agente", "lista agenti", "mostra i miei agenti". FR: "modifier mon agent", "supprimer agent", "lister les agents". ES: "editar mi agente", "eliminar agente", "listar agentes". DE: "Agenten bearbeiten", "Agenten löschen", "Agenten auflisten". PT: "editar meu agente", "remover agente", "listar agentes".