← 1 Billion Brain CellsCONTENT HISTORY
WHAT CHANGED
Update to 1 Billion Brain Cells
Snapshot Oct 28, 2026 · 12:08 UTC · version 2.0.0
Collection source: downloaded plugin package.
First saved snapshot
No earlier snapshot is available to establish a change.
Save 1 Billion Brain Cells and check future changes in Following.
Up to 10 plugins free · no card required.
Compare saved observations
Download comparison JSONFull technical diff · 0 changed fields
Full snapshot data
{
"description": "Guide a short Brain Training practice session through several games, launching one widget at a time and ending with a result recap. Use when the user wants a time-limited warm-up, a mixed-game circuit, or a guided multi-round session; do not use for a weekly plan or analysis of one completed round alone.",
"included_files": [
{
"relative_path": "agents/openai.yaml",
"size_in_bytes": 252
}
],
"name": "guided-brain-training-session",
"skill_md_contents": "---\nname: guided-brain-training-session\ndescription: Guide a short Brain Training practice session through several games, launching one widget at a time and ending with a result recap. Use when the user wants a time-limited warm-up, a mixed-game circuit, or a guided multi-round session; do not use for a weekly plan or analysis of one completed round alone.\n---\n\n# Guided Brain Training Session\n\n## Inputs and session setup\n\nUse the user's goal, available time or requested round count, game preferences,\nand any results already shared in this conversation. Ask only for choices that\nmaterially affect the session. If the user supplies no count or time budget,\npropose a three-round session and state that assumption.\n\nChoose games from the registered tools using their current descriptions:\n\n- `color-switch`: attention to changing word/ink rules.\n- `number-sort`: ascending number sequencing.\n- `odd-one-out`: spotting a rotated emoji.\n- `path-trace`: spatial route recall.\n- `pattern-recall`: cell-sequence recall.\n- `word-run`: words formed from adjacent letters.\n\nBuild a short sequence matched to the goal, balancing variety with any requested\nrepeat attempt. Allow sixty seconds of gameplay and a three-second countdown\nper round, plus loading, discussion, and optional breaks. Give an estimate rather\nthan promise an exact wall-clock duration. For a text-only or plan-only request,\ndeliver the sequence without launching widgets.\n\n## Run the session\n\n1. Present the sequence and one simple practice intention for the first game.\n2. For an authorized playable session, call the first game's exact tool. Send\n only an optional string `reason`; duration, difficulty, board seeds, and\n sequence lengths are not tool arguments. Launch one widget at a time because\n each widget starts its own countdown.\n3. Wait for a real completion follow-up, a model-visible completed result, or\n the user's result report. A launch output with `result: null` does not finish\n a round. Do not infer completion just because sixty seconds have elapsed.\n4. Keep a compact record in the conversation of the game, visible completion\n timestamp or round label, known score, and available success/failure counts.\n Count the same widget completion once, including if its result is restored\n after a remount. Keep missing values unknown and identify user-reported data.\n5. Give brief feedback tied to the practice intention, then launch the next\n game in the already requested session. Do not ask the user to authorize each\n planned round again. Follow steering to change, skip, or stop; mark a skipped\n round as skipped without inventing a result. Stop advancing when the user\n pauses, but do not claim to pause a running widget's timer.\n6. End after the requested sequence. Summarize completed rounds and suggest one\n practice focus for a later session. Offer extra play rather than starting an\n unrequested additional round.\n\n## Deliverable and boundaries\n\nProvide the sequence, concise feedback between games, and a final table of known\nresults with one useful takeaway. Discuss each game's performance separately;\ndifferent scoring rules make raw scores unsuitable for ranking games or producing\na combined cognitive score.\n\nKeep session progress in the conversation. Do not claim to save a cross-session\nprofile, retrieve older results, change game settings, or control taps, dragging,\nsound, and display modes for the user. If the launch tool is unavailable, explain\nthat limitation and retain the proposed session rather than claiming it started.\n"
}SHA-256 of public snapshot: db9757413ef7b10e80d605b1e2610308902e9ca130ec7f0dd19d8857b297050b