Update to Smart Chess:Train+Learn to win

{
  "description": "Give progressive, Socratic hints for the current Chess app position without revealing the move too early. Use when the user asks for a chess hint, clue, nudge, or guided help and wants to think through the live position themselves. Do not use for direct best-move requests or completed-game reviews.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 239
    }
  ],
  "name": "chess-hint-ladder",
  "skill_md_contents": "---\nname: chess-hint-ladder\ndescription: Give progressive, Socratic hints for the current Chess app position without revealing the move too early. Use when the user asks for a chess hint, clue, nudge, or guided help and wants to think through the live position themselves. Do not use for direct best-move requests or completed-game reviews.\n---\n\n# Chess Hint Ladder\n\n## Inputs\n\nUse only the current game widget's model-visible `modelContent`:\n\n- `fen` and `moves` for the position and its context\n- `phase`, `turn`, and `inCheck` for timing and urgency\n\nUse the conversation to track which hint level the user has already received.\n\n## Workflow\n\n1. Confirm that the state describes an active game and that it is White's turn.\n   - If Black is thinking, ask the user to wait for Black's move.\n   - If the engine is loading or unavailable, explain that a live move hint is premature.\n   - If the game is finished or restarting, offer to discuss the position or review the game instead.\n   - If the state is missing, ask for the current FEN or move sequence.\n2. Check immediate forcing concerns first: whether White is in check, direct threats, loose pieces, checks, captures, and tactical motifs.\n3. Start at the first unrevealed level unless the user requests a stronger hint:\n   1. State the position's main problem or objective without naming a move.\n   2. Identify the relevant board area, piece, or tactical motif without giving the full move.\n   3. Narrow the search to one or two candidate ideas.\n   4. Reveal a concrete candidate move and explain its purpose.\n4. Give only one new level per response. Pause so the user can calculate before offering the next level.\n\n## Output\n\nLabel the response `Hint 1`, `Hint 2`, `Hint 3`, or `Reveal`. Keep it brief, explain what the user should inspect, and end by inviting the next hint level when appropriate.\n\n## Boundaries\n\n- Do not claim access to Stockfish analysis, evaluation scores, principal variations, or its internal reasoning.\n- Present a revealed move as a reasoned candidate, not a guaranteed best move.\n- Do not make a move, control the widget, or call `start-game`.\n- Do not reveal later hint levels unless the user requests them.\n"
}