← Smart Chess:Train+Learn to winCONTENT HISTORY
WHAT CHANGED
Update to Smart Chess:Train+Learn to win
Snapshot Nov 12, 2026 · 12:08 UTC · version 4.0.0
Collection source: downloaded plugin package.
First saved snapshot
No earlier snapshot is available to establish a change.
Save Smart Chess:Train+Learn to win and check future changes in Following.
Up to 3 plugins free · no card required.
Compare saved observations
Download comparison JSONFull technical diff · 0 changed fields
Full snapshot data
{
"description": "Teach chess from zero through short interactive board lessons, understanding checks and a first easy game. Use for 'I am an absolute beginner, teach me' or a first chess lesson; do not use for an isolated piece drill or an experienced player's game review.",
"included_files": [
{
"relative_path": "agents/openai.yaml",
"size_in_bytes": 219
}
],
"name": "absolute-beginner-chess",
"skill_md_contents": "---\nname: absolute-beginner-chess\ndescription: Teach chess from zero through short interactive board lessons, understanding checks and a first easy game. Use for 'I am an absolute beginner, teach me' or a first chess lesson; do not use for an isolated piece drill or an experienced player's game review.\n---\n\n# Absolute beginner chess\n\n1. Start teaching immediately unless the user supplied a specific starting point. Explain briefly that players take turns and the goal is to checkmate the king, meaning it is attacked with no legal escape; kings are never captured. Introduce board coordinates through the board rather than requiring notation knowledge first.\n2. Open one `start-workshop` with a short plain-language title and a single achievable task. Start with a rook on a sparse `opponent: false` board, or the user's requested piece. Explain only the rule needed for that task and that this movement exercise lets their colour move repeatedly. Use a short validated `steps` line for an initial demonstration if helpful.\n3. Wait for a question, attempt or Finished follow-up. Respond to visible moves and the user's explanation, then choose the next small lesson. Do not launch a whole course of widgets at once or equate pressing Finished with understanding.\n4. Progress through rook/bishop/queen movement, knights, king and pawns at a pace the user can follow. Introduce blockers, captures, pawn direction and promotion when relevant. Use fresh practice boards and omit `steps` for independent checks; hiding an arrow leaves the listed answer visible. Explain unfamiliar words when first used.\n5. Move to `opponent: true` workshops with both kings to teach alternating turns, check, escaping check, checkmate and stalemate. Make the transition from isolated practice explicit: practice boards ignore check and cannot demonstrate king safety. Demonstrate castling or en passant under full rules when useful, without delaying the first game to cover every special case.\n6. When the user is ready or asks to play, call `start-game` with their chosen side and `difficulty: 0` unless they request otherwise. Coach one decision at a time from published state. Explain that even the easiest AI can win; do not promise a result or play the user's moves for them.\n7. Close a lesson or first game with one observed learning point and a suggested next small task. Respect requests to skip ahead or stop; use conversation context for continuity without claiming stored course progress.\n\nKeep workshop instructions to a sentence or two and omit distracting notes. Do not repeat rendered content in chat. Use only model-visible active history and position-labelled analysis; ask what the user tried when rejected moves are not recorded. Verify custom FENs and step coordinates, and fix tool errors before retrying the intended exercise. Deliver an interactive first lesson and paced continuation, rather than a long rules dump.\n"
}SHA-256 of public snapshot: 15aff294d6e1e25d72aead1614b42f652c209c81b39305e966cc8b2319fc2343