Auto-generates weekly KPI reports from multiple data sources including Supabase analytics, CRM data, financial spreadsheets, and email metrics. Produces executive-ready reports with dashboards, trends, highlights, concerns, and action items.
SkillScore64Maintained
Automatic
◆Data Analyst pack
Last verified 8/27/2026
What it changes
Passed 14 of 22 test cases with the skill, and 5 of 22 without it.
Without skill23%
With skill64%
Checks it passed that the model alone missed
Store system settings in config.yaml.
Snapshot fetched raw data into data/{date}/.
Compare calculated KPI values against prior weeks.
and 9 more in the full report
9 fixed5 passed either way8 still failing0 broke
Pass-rate lift
+41 pp
Tokens
+32%
Agent turns
0%
Response time
+2%
Model gemini-3.6-flashMeasured 8/27/2026v114 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 9
Prompt
When saving the final generated markdown executive report for the week ending November 10, 2024, what file path and naming pattern should be used?
What was checked, without and with the skill
Checked
Without skill
With skill
Format report output file path as reports/{date}-weekly-report.md.
Missed
Passed
case-18 · gemini-3.6-flash · 8/27/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md39 lines4 files
Weekly Business Report Generator
Pull data from multiple business systems, synthesize it into a coherent narrative, and produce an executive-ready weekly report that turns raw numbers into strategic insight.
Contents
references/configuration.md — first-run setup questions, directory layout, full config.yaml, and kpi-history.json schema.
references/data-and-calculations.md — per-source data collection, trend indicators, target comparison, rolling averages, anomaly detection, comparison modes, custom KPI groups, quality rules, and error handling.
references/output-template.md — the full report markdown template and detail levels.
Workflow
First run (no configuration exists)
Run the setup questions and create the directory layout. See references/configuration.md.
Generate config.yaml and templates/kpi-definitions.yaml from the schema in references/configuration.md.
Initialize history/kpi-history.json using the schema in references/configuration.md.
Each subsequent run
Read config.yaml and templates/kpi-definitions.yaml.
Determine the reporting period (the previous full business week).
Pull data from each enabled source and snapshot it to data/{date}/. See references/data-and-calculations.md.
Calculate every KPI: trend indicators, target comparison, rolling averages, and anomalies. See references/data-and-calculations.md.
Compare against targets and prior weeks; flag anomalies.
Generate the report from the template in references/output-template.md, tailored to each recipient's detail level.
Save the report to reports/{date}-weekly-report.md and append this week's values to history/kpi-history.json.
Quick Commands
"Generate this week's report" — full report for the most recent complete week.
"Show me revenue trends" — revenue-specific trend analysis with 4-8 week history.
"What are the concerns this week?" — concerns-only output.
"Add KPI [name]" — add a new KPI to tracking (see custom KPI groups in references/data-and-calculations.md).
"Update targets" — modify target values for existing KPIs.
"Compare last 4 weeks" — side-by-side comparison of the last 4 weekly reports.
"YTD summary" — year-to-date summary across all tracked KPIs.
Apply the report quality rules and error handling in references/data-and-calculations.md to every run.