Update to 1 Billion Brain Cells

{
  "description": "Build a repeatable weekly Brain Training routine with a game rotation, replay days, and a simple results log. Use when the user asks for a multi-day plan or sustainable practice schedule based on their goals and available time; do not use for a single guided session, automatic reminders, or medical treatment planning.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 271
    }
  ],
  "name": "brain-training-practice-plan",
  "skill_md_contents": "---\nname: brain-training-practice-plan\ndescription: Build a repeatable weekly Brain Training routine with a game rotation, replay days, and a simple results log. Use when the user asks for a multi-day plan or sustainable practice schedule based on their goals and available time; do not use for a single guided session, automatic reminders, or medical treatment planning.\n---\n\n# Brain Training Practice Plan\n\n## Inputs and workflow\n\n1. Use the user's goal, available days, time or rounds per day, preferred games,\n   and any completed results already shared. Ask for a missing constraint only\n   if it materially changes the plan. If no schedule is supplied, state an\n   assumption of five practice days with two rounds per day. Treat the goal as\n   practice at the games rather than a diagnosis or promised cognitive benefit.\n2. Select a rotation from the exact registered tools `color-switch`,\n   `number-sort`, `odd-one-out`, `path-trace`, `pattern-recall`, and `word-run`,\n   using their current descriptions to match the goal. Respect requested games\n   and exclusions. Build in repeat attempts at the same game so comparisons\n   have a clear baseline; use other days for variety or rest as requested.\n3. Estimate each day's time from sixty seconds of gameplay and a three-second\n   countdown per round, allowing extra time for loading, reflection, and breaks.\n   Adjust the number of rounds to the user's budget, not the games' duration or\n   difficulty; neither is configurable through a launch tool.\n4. Assign one simple intention per practice day. Use known prior results to set\n   a measurable target, such as fewer failures while maintaining successes. If\n   there is no baseline, make the first attempt a baseline instead of inventing\n   a score target or a universal success-rate threshold. Describe score goals\n   within a game because scoring differs across games.\n5. Include a compact log format for the user to record date or attempt label,\n   game, successful attempts, failed or rejected attempts, score when known, and\n   a brief strategy note. Use the game's own result labels. Accept completion\n   follow-ups or model-visible saved results during later discussion; leave\n   unavailable fields unknown rather than assuming zero. Do not derive Word\n   Run scores from submission counts.\n6. Add a review point after the planned replay attempts to compare the same\n   game and decide whether to repeat its technique, try a different technique,\n   or change the rotation. Keep the plan flexible if the user changes their\n   available time or preferences.\n7. Deliver the plan without launching a game unless the user also asks to start\n   it. For an authorized first round, call the chosen tool with at most an\n   optional string `reason`; use later conversation turns for further play.\n\n## Deliverable and boundaries\n\nReturn a concise daily table containing the game or games, round count, estimated\ntime, practice intention, and replay or review point, followed by the results-log\ncolumns. Explain the initial assumption or missing baseline only when relevant.\n\nPresent this as a conversational plan. Do not claim to create reminders, schedule\ntool calls, save a durable history, or retrieve results from earlier conversations.\nThe app has no scheduling or cross-session history tool. If the user requests\nautomation, identify that separate dependency and retain the usable plan without\nclaiming the automation is set up. Do not rewrite saved widget results or infer\nprogress from days when the user has not provided a completed result.\n"
}