Turn task boards into exec-ready metrics and narratives that drive decisions
Many teams can track tasks but struggle to generate credible progress reporting for complex projects. This recipe creates a reporting layer on top of your existing tools: KPIs, progress logic, and an interpretation narrative that executives can act on.
Create a skill called "Reporting Upgrade Layer". Goal: transform task-tracking data into executive-usable reporting. When I provide a board snapshot (export or summary), you will: - Ask what "progress" means in this context (deliverables/tasks/points). - Define 5–7 KPIs that are computable from available data. - Produce: (1) Executive digest, (2) KPI appendix, (3) Risks/asks derived from metrics. - Explicitly flag when metrics are unreliable due to missing data. Guardrails: - Don't invent percent complete. If unknown, propose a measurement approach. - Prefer simple, explainable metrics over complex analytics.
Export or summarize your current board (Kanban, backlog, sprint view) and this recipe
builds a metrics layer on top: 5–7 KPIs computed from available data, a health
narrative explaining what the numbers mean this week, and explicit flags for misleading
signals like false greens, hidden WIP, or stale tasks.
Fix slow Looker Studio dashboards without losing critical signal
Looker Studio dashboards can become painfully slow as complexity and blended sources grow. This recipe diagnoses likely causes (too many charts, heavy sources, blends/joins, formatting) and produces a performance-first redesign plan (including caching and pre-aggregation strategies).
Stop KPI arguments by defining metrics once and reusing everywhere
Many reporting conflicts come from undefined or inconsistent KPIs (what counts as a lead, which revenue number, what window, etc.). This recipe builds a KPI dictionary and maps each KPI to source systems and owners, including "confidence levels" and known limitations.
Verify dashboards before you trust them
A sanity-check workflow for broker performance charts, retirement projections, and portfolio analytics that may be misleading, incomplete, or just buggy.
Wikipedia-grade AI pattern removal
Comprehensive AI writing cleanup based on Wikipedia's WikiProject AI Cleanup guidelines. Catches 24+ distinct patterns including inflated symbolism, em dash overuse, rule of three, copula avoidance, and sycophantic tone.