{"id":19224,"plugin_id":"plugins_6a92f40359bc81919e5b41b1451ec501","kind":"skill","collection_source":null,"comparison_source":null,"observed_at":"2026-09-30T23:15:23.885Z","digest":"cbe23d9c10203664764eb53afa2c63af78def21312945a2f0801231afed49ac7","against":null,"payload":{"description":"Use when building a Power BI forecast war room or control tower for executive revenue review, forecast risk triage, top deltas, action ownership, gap closure status, confidence monitoring, and daily forecast operating rhythm.","included_files":[{"relative_path":"agents/openai.yaml","size_in_bytes":136}],"name":"powerbi-forecast-war-room","skill_md_contents":"---\r\nname: powerbi-forecast-war-room\r\ndescription: Use when building a Power BI forecast war room or control tower for executive revenue review, forecast risk triage, top deltas, action ownership, gap closure status, confidence monitoring, and daily forecast operating rhythm.\r\n---\r\n\r\n# Power BI Forecast War Room\r\n\r\nUse this skill when the user wants a management control tower around the forecast rather than only CSV outputs.\r\n\r\n## Operating rhythm\r\n\r\n1. Daily or weekly refresh of forecast outputs.\r\n2. Review month-level gap to budget, roll, and prior year.\r\n3. Open top deltas as action items.\r\n4. Assign owner hints by customer hierarchy, product line, sales group, or region when available.\r\n5. Track status:\r\n   - open\r\n   - validated\r\n   - escalated\r\n   - rescued\r\n   - lost\r\n   - ignored due to low data confidence\r\n6. Review model quality and override trust after actuals land.\r\n\r\n## War room views\r\n\r\n- executive gap summary\r\n- top risk customers/products\r\n- backlog at risk\r\n- rescue action board\r\n- agent council dissent\r\n- trust score by source\r\n- model quality by horizon\r\n- counterfactual scenarios\r\n\r\n## Required outputs\r\n\r\n- `forecast_month`\r\n- `issue_type`\r\n- `customer`\r\n- `product`\r\n- `revenue_at_risk`\r\n- `recommended_action`\r\n- `owner_hint`\r\n- `status`\r\n- `due_date`\r\n- `confidence`\r\n- `evidence`\r\n\r\n## Guardrails\r\n\r\n- Every red item needs an action or an explicit reason to ignore.\r\n- Do not mix unvalidated AI recommendations with committed management numbers.\r\n- Keep action status separate from model forecast values so reporting remains auditable.\r\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}