← 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": "Turn a specific mistake from a visible chess game into a focused board exercise and independent retry. Use for requests such as 'Turn my missed fork into an exercise'; do not replace a general game review.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 211
    }
  ],
  "name": "mistake-to-practice",
  "skill_md_contents": "---\nname: mistake-to-practice\ndescription: Turn a specific mistake from a visible chess game into a focused board exercise and independent retry. Use for requests such as 'Turn my missed fork into an exercise'; do not replace a general game review.\n---\n\n# Mistake to practice\n\n1. Identify the user's decision from the current board's model-visible active history, initial FEN and side. Clarify the move only if ambiguous. If the position or history is missing, request it rather than reconstructing unseen play.\n2. Select one teachable idea. Use position-labelled engine evidence when available; distinguish a demonstrated error from a plausible improvement. Do not assign centipawn loss without comparable evaluations of the relevant positions.\n3. Reconstruct the position before the decision and verify the proposed moves. Use `start-workshop` with a short title and task. For a demonstrated correction, supply a short legal `steps` line; use `opponent: true` when turns, check or defensive replies matter. Use repeated-colour practice only for isolated movement exercises.\n4. Wait for the user's attempt or Finished follow-up. Review published moves and progress against the idea; an off-line move can still be good. Treat strict step completion as guided practice, not proof of independent understanding.\n5. Offer a fresh attempt from the decision position or a verified variation. When accepted, call `start-workshop` without `steps` and with `strict: false` so the answer is not listed. Compare the observed attempt with the earlier decision and leave one practical reminder.\n\nKeep each workshop's instructions brief and omit spoilers from independent attempts, including titles and notes. Do not repeat the widget's content after rendering. Do not claim to operate Undo, Reset or Finished, access private redo history, or save a permanent training record. Stop after the focused retry unless the user requests more.\n"
}

SHA-256 of public snapshot: a5436e50437c7321b94e4ddca65430f3844378ea1fb84f4d3c4d69125995c930