← Smart Chess:Train+Learn to winCONTENT HISTORY

Update to Smart Chess:Train+Learn to win

Snapshot Nov 12, 2026 · 12:08 UTC · version 4.0.0

Collection source: downloaded plugin package.

WHAT CHANGED

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 JSON
Full technical diff · 0 changed fields
Full snapshot data
{
  "description": "Teach and practise one chess endgame technique using a short demonstration and a fresh attempt against Stockfish. Use for requests such as practising king-and-rook mate or pawn promotion; do not claim tablebase-perfect verification.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 210
    }
  ],
  "name": "endgame-technique-lab",
  "skill_md_contents": "---\nname: endgame-technique-lab\ndescription: Teach and practise one chess endgame technique using a short demonstration and a fresh attempt against Stockfish. Use for requests such as practising king-and-rook mate or pawn promotion; do not claim tablebase-perfect verification.\n---\n\n# Endgame technique lab\n\n1. Choose one technique from the user's goal and experience. Use their visible position if suitable; otherwise construct a small legal position with both kings. Verify side to move, king safety, material and the intended objective before calling a tool.\n2. Define a concrete task, such as reducing the king's space or reaching a promotion square. Distinguish practising a method from proving a forced win; avoid a claim of winning against every defence without evidence.\n3. If a demonstration is useful, call `start-workshop` with `opponent: true` and a short verified `steps` line. Explain the technique briefly in the instructions or notes. Scripted replies illustrate that line and need not be the strongest defence.\n4. When the user is ready, open a fresh full-rule workshop without `steps`, using `strict: false` and an appropriate difficulty from 0–20. State the task and when to press Finished; Stockfish chooses the opponent's replies.\n5. On questions or completion, use model-visible active history, outcome and position-labelled analysis to discuss the technique. Check for stalemate and draw outcomes before calling an attempt successful. Give one specific correction and offer a retry from the original or a verified related position.\n\nDo not use kingless practice rules for mate, opposition or draw lessons. The app has no tablebase lookup or automatic custom-goal grader; never treat missing analysis as a completed evaluation or promise Stockfish will cooperate. Keep each board concise and avoid repeating its instructions. Do not claim a lasting mastery score or saved training history.\n"
}

SHA-256 of public snapshot: fbf7a40e6ef89a019168d10ee110ed17edacd6f68b3efc6ec6a035e3c7d54478