Run a retrospective on a completed (or stalled) Goals goal to learn from it — critique both the engine/UX friction the CLI created AND the agent's own execution quality, record durable lessons into self-evolution memory, surface cross-goal patterns, and file engine friction upstream. Use after `goals check` reports a goal complete, after a painful or stalled goal, or periodically to learn across every goal you run.
Solve a problem or define/break down a goal using PACERS (Pause, Assess, Choose, Execute, Review, Systemize) and record the reasoning as a traceable building journey in the active Goals goal. Use inside a Goals project when defining a goal, breaking a phase into sub-problems, hunting assumptions before building, or whenever a problem is recurring, costly, unclear, or likely to create second-order effects.
Generate a clean architecture or loop diagram for the active Goals goal as Mermaid or a valid .excalidraw file. Use when the user asks to visualize, diagram, or draw the goal's architecture map or the designed loop.
Show the architecture map of the active Goals goal — what is built, planned, blocked, deferred, or missing. Use inside a Goals project when you need the system shape, a diagram-style overview, or to check recorded changes against the goal's architecture.
Explain a project decision from the active Goals goal in plain language — what needs the user, the recommended reply, and what happens next. Use inside a Goals project when a technical decision, risk, or tradeoff needs a non-technical explanation, or when deciding whether a choice should interrupt the user.