analysis-retrospective
When to use
Within one week of completing a significant analysis project — while the details are still fresh. Also use after an analysis that went wrong (late delivery, stakeholder rejection, data error discovered post-delivery) to prevent recurrence. Run team retros quarterly even without a specific incident.
Process
- Time-box the retro — 30 minutes for solo, 60 minutes for team. Use the structured format in
references/retro_frameworks.mdto stay focused (Start/Stop/Continue or 4Ls: Liked/Lacked/Learned/Longed for). - Review the project against plan — compare actual timeline, scope, and effort to what was planned; note the gaps.
- Identify what went well — capture at least two things that worked and should be repeated; these are as important as problems.
- Identify root causes of issues — for each problem, apply 5-whys to find the actual cause rather than the symptom.
- Capture reusable learning — use
references/learning_capture.mdto decide which learnings belong in: templates, reference docs, checklists, or team norms. - Record and track actions — fill in
assets/retrospective_template.mdwith owners and due dates; log durable learnings inassets/learnings_log_template.md.
Inputs the skill needs
- Completed analysis project (name, scope, timeline)
- Original plan or brief (for comparison)
- Participants (solo or team members involved)
Output
- Completed retrospective (
retrospective_template.md) with what-went-well, issues, root causes, and action items - Learnings log entry (
learnings_log_template.md) for reusable insights
More from nimrodfisher/data-analytics-skills
funnel-analysis
Conversion funnel analysis with drop-off investigation. Use when analyzing multi-step processes, identifying conversion bottlenecks, comparing segments through a funnel, or optimizing user journeys.
39insight-synthesis
Transform data findings into compelling insights. Use when converting analysis results into actionable insights, connecting findings to business impact, or preparing insights for stakeholder communication.
33dashboard-specification
Design specifications for effective dashboards. Use when planning new dashboards, improving existing ones, or documenting dashboard requirements before development starts.
32metric-reconciliation
Cross-source metric validation and discrepancy investigation. Use when metrics from different sources don't match, investigating data quality issues between systems, or validating data migration accuracy.
32time-series-analysis
Temporal pattern detection and forecasting. Use when analyzing trends over time, detecting seasonality, identifying anomalies in time series, or building simple forecasting models for planning.
32executive-summary-generator
Create concise executive summaries from detailed analysis. Use when preparing board decks, executive briefings, or condensing complex analysis into decision-ready formats for senior audiences.
32