Update to Aivana CIO Decision Twin

{
  "name": "assumption-mining-engine",
  "description": "Extract and assess hidden assumptions in strategies, business cases, project plans, architecture roadmaps, AI use cases and investment proposals. Use when the user needs assumption mining engine for CIO decision support.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 140
    }
  ],
  "skill_md_contents": "---\nname: assumption-mining-engine\ndescription: Extract and assess hidden assumptions in strategies, business cases, project plans, architecture roadmaps, AI use cases and investment proposals. Use when the user needs assumption mining engine for CIO decision support.\n---\n\n# Assumption Mining Engine\n\n## Mission\n\nFind the assumptions that quietly determine whether executive plans succeed or fail.\n\n## Inputs\n\nAccept business cases, project plans, strategy notes, roadmaps, transformation charters, AI use cases, vendor proposals, budgets and meeting notes.\n\n## Workflow\n\n1. Extract explicit and implicit assumptions about value, timing, cost, capacity, data, adoption, technology, vendors and controls.\n2. Classify assumptions as critical, material or minor.\n3. Assess evidence, owner, validation method and failure consequence.\n4. Identify assumptions that require decision gates or early tests.\n5. Produce an assumption register with validation actions.\n\n## Output Format\n\n- Executive Summary\n- Assumption Register\n- Critical Assumptions\n- Weak Evidence Areas\n- Failure Consequences\n- Validation Plan\n- Decision Gates\n- Evidence & Assumptions\n\n## Guardrails\n\nDo not treat every uncertainty as critical. Prioritize assumptions that can materially change the decision.\n"
}