Elimination Research

Purpose

Generate a reproducible elimination-research package: a shortlist dataset, numeric scoring model, quick consumer report, full audit report, raw data JSON, source/domain audit, purchase/info links, contextual images, and ownership-cost estimates.

Use this skill to turn fuzzy "which one should I choose?" requests into a clean decision workflow with explicit criteria and inspectable data.

Workflow

Follow this sequence for new comparisons:

1. Read references/workflow.md for the full operating procedure.
2. Ask the intake questions before researching. Prefer cenno popup questions when available. Use closed choices and include a free-text comment field.
3. Gather candidate, source, price, spec, replacement-part, image, and evidence data.
4. Save all collected data into a dataset JSON matching references/dataset-schema.md.
5. Run scripts/generate_elimination_report.py to generate reports.
6. Verify the quick report and full report in a browser.
7. Preserve raw data and numeric tables; do not hide or discard evidence just because the quick report is simplified.