← Power BI DesktopCONTENT HISTORYWHAT CHANGED · RULE-BASED ANALYSIS
Update to Power BI Desktop
Snapshot Sep 30, 2026 · 23:15 UTC · version 3.0.0+codex.20260829143201
Collection source: not recorded for this historical snapshot.
First saved snapshot
No earlier snapshot is available to establish a change.
Compare saved observations
Download comparison JSONFull technical diff · 0 changed fields
Full snapshot data
{
"name": "powerbi-revenue-rescue-mode",
"description": "Use when turning Power BI sales forecast gaps into operational rescue actions, including backlog acceleration, customer activation, product substitution, delivery escalation, gap closure ranking, and forecast-to-action recommendations.",
"included_files": [
{
"relative_path": "agents/openai.yaml",
"size_in_bytes": 131
}
],
"skill_md_contents": "---\r\nname: powerbi-revenue-rescue-mode\r\ndescription: Use when turning Power BI sales forecast gaps into operational rescue actions, including backlog acceleration, customer activation, product substitution, delivery escalation, gap closure ranking, and forecast-to-action recommendations.\r\n---\r\n\r\n# Power BI Revenue Rescue Mode\r\n\r\nUse this skill when the user asks how to close a forecast gap, secure the month, rescue revenue, or convert forecast findings into actions.\r\n\r\n## Workflow\r\n\r\n1. Identify the gap by month:\r\n - budget gap\r\n - roll gap\r\n - prior-year gap\r\n - AI forecast confidence\r\n2. Split the gap into action classes:\r\n - **accelerate**: open backlog likely billable if delivery or admin blockers are solved\r\n - **validate**: material customer/product deltas where human sales input is needed\r\n - **recover**: segments below seasonal or roll expectation with enough history\r\n - **substitute**: alternative products or customers can offset risk\r\n - **de-risk**: low-confidence, biased, or sparse segments should not carry the plan\r\n3. Rank actions by expected impact, probability, owner, and deadline.\r\n4. Produce a rescue board that can be imported into Power BI or used as a sales operations action list.\r\n\r\n## Action scoring\r\n\r\nUse a simple score unless a better calibrated model exists:\r\n\r\n`impact_score = expected_revenue * confidence_weight * urgency_weight`\r\n\r\nConfidence weights:\r\n\r\n- high: 1.00\r\n- medium: 0.70\r\n- low: 0.35\r\n\r\nUrgency weights:\r\n\r\n- current month: 1.25\r\n- next month: 1.00\r\n- month +2: 0.80\r\n\r\n## Required outputs\r\n\r\n- `forecast_month`\r\n- `action_type`\r\n- `customer`\r\n- `product`\r\n- `expected_revenue_impact`\r\n- `probability`\r\n- `deadline`\r\n- `owner_hint`\r\n- `reason`\r\n- `next_action`\r\n- `risk_flag`\r\n\r\n## Guardrails\r\n\r\n- Never recommend actions on segments with no evidence unless marked as `exploratory`.\r\n- Distinguish revenue that can be pulled forward from revenue that requires new demand.\r\n- Flag actions that may improve revenue but harm margin, cash, or delivery reliability.\r\n"
}SHA-256: 0eb0a9f76c3f3950774930df89297cf55bc185d9880d258e0998f898e24e90a4