Update to Horizon Forge

{
  "description": "Model future industry size, adoption, and growth with explicit scenarios, event probabilities, economic ratings, and sensitivity checks. Use to quantify a defined field or compare evidence-backed candidates.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 218
    }
  ],
  "name": "horizon-scenarios",
  "skill_md_contents": "---\nname: horizon-scenarios\ndescription: Model future industry size, adoption, and growth with explicit scenarios, event probabilities, economic ratings, and sensitivity checks. Use to quantify a defined field or compare evidence-backed candidates.\n---\n\n# Scenario and rating analyst\n\nRead [scoring](../horizon-forecast/references/scoring.md), [scenario method](../horizon-forecast/references/scenario-method.md), and [calculation interface](../horizon-forecast/references/calculation-interface.md). Use the established scope when delegated; if standalone, state a plan, metric, geography, and endpoints before modeling.\n\n1. Establish compatible baseline definitions and buyer/capacity constraints. An unknown baseline remains unknown.\n2. Elicit independent initial estimates where actual delegation is available and useful; this skill requests a bounded independent forecasting pass for material comparisons. Supply neutral evidence and event definitions before sharing a preferred number. Follow [orchestration](../horizon-forecast/references/agent-orchestration.md).\n3. Construct coherent downside, central, and upside paths. Use justified subjective probabilities only for an exhaustive, non-overlapping partition of outcomes; otherwise show unweighted exploratory scenarios.\n4. Calculate growth, added annual size, and probability-weighted outcomes with the bundled calculator when inputs qualify. Use the declared economic basis for every candidate.\n5. Apply anchored growth and overlooked-opportunity ratings. Keep evidence confidence and event probability separate. Missing inputs create bounds and provisional status, not neutral imputation.\n6. Test rating-weight sensitivity and the economic assumptions that can reverse the result. Preserve unresolved differences; do not treat majority agreement as accuracy.\n7. Return input assumptions, calculations, scenario table, scorecards with evidence, threshold definitions, reversal conditions, and specific 1–3-year signposts.\n\nDo not imply the 0–100 ratings are calibrated probabilities, expected investment returns, or objectively validated weights. If a quantitative estimate is unsupported, deliver a qualitative scenario and specify the missing measurement.\n"
}