wingedsheep

Log what was eaten today. Use when the user says "we had X for dinner", "ate X", "log food", or mentions what they ate.

Sync Garmin data. Use when the user says "sync", "update garmin", "pull garmin data", or similar. Always resyncs at least the last 3 days to catch delayed updates.

Generate a comprehensive health summary report with trends, correlations, and actionable advice. Use when the user asks "how am I doing", "health summary", "analyze my health", or similar.

Create a multi-week or multi-month training plan. Use when the user asks "make a training plan", "plan my week", "plan my month", "plan until <event>", or similar.

Plan the next training session based on recent training, recovery status, and goals. Use when the user asks "plan my next workout", "what should I train", "next session", or similar.

Suggest dinner recipes based on preferences, recent meals, and dietary goals. Use when the user asks "what should I eat", "suggest dinner", "recipe ideas", "what should I cook", or similar.

Update the current focus points shown on the dashboard Overview page. Use when the user says "update focus", "change focus points", "my priorities are now X", or when creating a new health summary or plan that changes priorities.

Adds a new feature or mechanic to the Argentum Engine (SDK primitive, effect, trigger, condition, static/replacement ability, server/client capability) following the project's architecture and SDK-elegance principles. Use when implementing engine/SDK/server/client functionality that isn't a single card — e.g. "add an effect type", "support a new keyword", "add a decision UI", "make the engine handle X".

Implements new Magic: The Gathering cards for the Argentum Engine. Use when adding a new card, the user provides a card name to implement, or asks to implement a specific MTG card.

Review pending changes (a branch, PR, or working tree) for the Argentum Engine. Optimizes for an elegant, reusable SDK — flags one-off effects/abilities that should compose existing primitives — and checks correctness, projection use, tests, and architectural fit. Use when the user says "review this PR", "review this branch", "review my changes", or asks for a code review of pending work.

Pick a random unimplemented card from a set and implement it. Accepts either a backlog cards.md path or a set name/code.

Generate a test scenario JSON for the DevScenarioController. Takes a description of what you want to test and produces a valid scenario file.

Pick the next unchecked Bloomburrow card from the AI advisor checklist, evaluate if it needs an advisor, create one if needed, and check it off.