{"id":92748,"plugin_id":"plugin_asdk_app_69c28d6aedac81919502a88c2179e20c","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-11-12T12:08:21.405Z","digest":"1f3e265886350c1f7dd93c4331788cac5e6512636c0cb18eefbb75bab9b11758","against":null,"payload":{"description":"Review a completed or off-track chess workshop and create one focused retry. Use for Finished follow-ups or 'I went off the steps, help me retry'; do not use for a full match review or a new exercise without prior workshop context.","included_files":[{"relative_path":"agents/openai.yaml","size_in_bytes":228}],"name":"workshop-debrief-and-retry","skill_md_contents":"---\nname: workshop-debrief-and-retry\ndescription: Review a completed or off-track chess workshop and create one focused retry. Use for Finished follow-ups or 'I went off the steps, help me retry'; do not use for a full match review or a new exercise without prior workshop context.\n---\n\n# Workshop debrief and retry\n\n1. Read the identified workshop's model-visible title, instructions, notes, initial/current FEN, active moves, rules, completion flag and step progress. If the task or relevant state is unavailable, ask for it; do not inspect private restoration or redo state.\n2. Compare the attempt with the task. For scripted work, distinguish on-track, astray and complete using published progress and first deviation. Going off the line does not establish that a move is bad; Finished does not establish success.\n3. Select one observed difficulty and explain the consequence with position-specific evidence. Use only available evaluations tied to the relevant position, and label inference. Under piece-practice rules, do not infer checkmate or standard-rule legality from completion.\n4. Offer one correction. If the current workshop remains active, explain how the user can Undo or Reset to retry; do not claim to press those controls. A Finished workshop is locked, so use a fresh board for further play.\n5. When a fresh retry is requested or accepted, call `start-workshop` from the original or an appropriate verified intermediate position. Retain the relevant rules and side. Reduce the task to the identified difficulty; omit `steps` for independent testing or use a short guided line when the user needs a demonstration.\n6. After the retry, compare only observed attempts and leave one next action. Keep the deliverable to a brief debrief and a focused practice opportunity.\n\nDo not invent unreported mistakes or a full planned line from progress alone. Use earlier visible tool arguments when a scripted line is needed; if unavailable, request it or design a verified new exercise. Keep mobile instructions short and do not duplicate widget content after rendering.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}