When to use
Before sharing any analysis output with a stakeholder — dashboard, report, ad-hoc query result, model output, or written findings. Run this every time, not just for big projects. The cost of a post-delivery correction is always higher than the cost of a pre-delivery check.
Process
- Run automated checks — use
scripts/qa_runner.pyagainst the output file to catch numeric, structural, and formatting issues programmatically. - Complete the logic checklist — work through
references/qa_checklist_master.mdsection by section: question framing, data sourcing, transformations, statistical validity, findings, and presentation. - Review for common errors — cross-check against
references/common_analysis_errors.md; pay special attention to the top-frequency mistakes for the analysis type. - Validate assumptions explicitly — for every assumption in the analysis, verify it has a source, is documented, and the output is sensitivity-tested where the assumption is uncertain.
- Check the narrative — confirm the conclusion follows from the data, caveats are stated, and the recommendation is actionable.
- Record sign-off — complete
assets/qa_signoff_template.mdwith reviewer, issues found, resolution status, and delivery decision.
Inputs the skill needs
- Output file to review (CSV, notebook, SQL result, or written doc)
- Original analysis question / brief
- Name of reviewer and intended audience
Output
- QA runner report (automated flags)
- Completed checklist with pass/fail per section
- Signed-off
qa_signoff_template.mdconfirming delivery readiness