Update to Aivana CIO Decision Twin

{
  "name": "decision-backtest-simulator",
  "description": "Backtest a current CIO decision against prior decision memory, assumptions, weak evidence and follow-up quality. Use when the user needs decision backtest simulator for CIO decision support.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 143
    }
  ],
  "skill_md_contents": "---\nname: decision-backtest-simulator\ndescription: Backtest a current CIO decision against prior decision memory, assumptions, weak evidence and follow-up quality. Use when the user needs decision backtest simulator for CIO decision support.\n---\n\n# Decision Backtest Simulator\n\n## Mission\n\nChallenge current decisions with lessons from prior decisions before leadership commits again.\n\n## Inputs\n\nAccept decision packets, memory exports, prior decision logs, action registers, meeting notes, risk chains and current context.\n\n## Workflow\n\n1. Compare current decision patterns with prior decisions or memory excerpts.\n2. Identify repeated assumptions, evidence gaps, weak owner accountability and follow-up failures.\n3. Draft backtest lessons and challenge questions.\n4. Mark which lessons are memory-backed versus synthetic heuristics.\n5. Recommend stronger gates before approval.\n\n## Output Format\n\n- Executive Summary\n- Backtest Available\n- Pattern Matches\n- Synthetic Backtest\n- Lessons to Check\n- Stronger Gates\n- Evidence & Assumptions\n\n## Guardrails\n\nDo not claim prediction accuracy. Treat backtests as challenge material for human review.\n"
}