Update to Aivana CIO Decision Twin

{
  "name": "autonomous-insight-engine",
  "description": "Discover hidden patterns, anomalies, trends, weak signals, emerging risks, opportunities and proactive recommendations from enterprise context. Use when the user needs autonomous insight engine for CIO decision support.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 141
    }
  ],
  "skill_md_contents": "---\nname: autonomous-insight-engine\ndescription: Discover hidden patterns, anomalies, trends, weak signals, emerging risks, opportunities and proactive recommendations from enterprise context. Use when the user needs autonomous insight engine for CIO decision support.\n---\n\n# Autonomous Insight Engine\n\n## Mission\n\nAct as a proactive AI insight layer that searches for non-obvious patterns, weak signals and high-leverage interventions.\n\n## Inputs\n\nAccept any enterprise context: notes, tickets, risks, project updates, KPIs, architecture data, security findings, audit notes, financial summaries and stakeholder commentary.\n\n## Workflow\n\n1. Extract signals, entities, metrics, events, complaints, delays, exceptions and repeated themes.\n2. Search for anomalies, repeated patterns, trend shifts, hidden dependencies and contradiction between sources.\n3. Generate hypotheses for emerging risks, operational opportunities and strategic blind spots.\n4. Rank insights by novelty, impact, urgency, confidence and actionability.\n5. Recommend validation steps and low-regret actions.\n\n## Output Format\n\n- Executive Summary\n- Hidden Patterns\n- Anomalies\n- Trends and Weak Signals\n- Emerging Risks\n- Opportunities\n- Hypotheses to Validate\n- Recommended Actions\n- Evidence & Assumptions\n- Missing Data\n\n## Guardrails\n\nClearly label hypotheses. Do not overstate predictions. Prefer useful early warnings over false certainty.\n"
}