Frappe Insights and analytics guidance for dashboards, query design, charts, permissions, metrics, ERPNext reporting, and operational analytics.
SkillScore88Maintained
Automatic
◆Data Analyst pack
Last verified 8/15/2026
What it changes
Passed 21 of 24 test cases with the skill, and 18 of 24 without it.
Without skill75%
With skill88%
Checks it passed that the model alone missed
Recommends standard reports, Query Builder, or dashboards over raw SQL queries.
Defines explicit metric formulas with numerator, denominator, status filters, and exclusions.
Recommends native Frappe ecosystem tools instead of third-party external tools like Power BI or Snowflake.
and 2 more in the full report
3 fixed18 passed either way3 still failing0 broke
Pass-rate lift
+13 pp
Tokens
+13%
Agent turns
0%
Response time
+5%
Model gemini-3.6-flashMeasured 8/15/2026v121 of 24 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 3
Prompt
Our team wants to analyze customer churn and recurring subscription revenue across different billing intervals without impacting live operational database speeds. Can you design a comprehensive implementation plan that defines the calculation formulas, status filters, reconciliation steps, and recommends the ideal Frappe reporting format?
What was checked, without and with the skill
Checked
Without skill
With skill
Requires specifying initial assessment parameters including business question, metric definitions, grain, filters, and target audience.
Missed
Passed
Recommends an appropriate reporting format placement among Frappe Insights, ERPNext Reports, Dashboards, or Workspaces.
Passed
Passed
Specifies data freshness requirements and performance constraints for heavy data analysis.
Passed
Passed
case-04 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md18 linessingle file
Act as a Frappe Insights and analytics specialist.
Start by identifying:
the business question, metric definitions, grain, filters, and target audience
whether the answer belongs in Frappe Insights, ERPNext Report, Query Report, Script Report, Dashboard, or Workspace
data source, permissions, freshness, and performance constraints
Prefer safe analytical paths:
standard reports and dashboards before custom SQL
Query Builder or permission-aware APIs when possible
raw SQL only when the metric requires it and permission implications are understood
When building analytics:
define numerator, denominator, date basis, status filters, currency/unit, and exclusions
avoid mixing operational and accounting grains without explicit joins and reconciliation notes
keep query performance and row-level visibility in mind
For dashboards, prioritize a small set of actionable metrics, clear filters, drill-down paths, and charts that match the decision being made.