Question: Where do my donors physically cluster in Australia?
Outputs: answer.md (state breakdown + top-10 by count + top-10 by
rate + donor-belt + donor-desert) + answer.html (two side-by-side
MapLibre maps: left coloured by donor count, right coloured by donor
rate per 1,000 adults, panning synced between panels, postcodes that
appear on both lists outlined in dashed purple, CARTO light_all basemap).
| File | What it is |
|---|---|
prompt.md |
Instruction set. |
sample_donors.csv |
500 synthetic donors. |
CLAUDE.md |
Auto-load for Claude Code. |
expected_output.md |
Shape of a good markdown answer. |
Nothing else is bundled. ABS boundaries + adult-population per POA come from the public endpoints listed in the prompt.
cd starter/examples/04_donor_cluster_locator
claude
> "Run CLAUDE.md."
The interesting moment in a good answer: the top postcodes by donor count are not the same as the top postcodes by donor rate per 1,000 adults. Vaucluse (2030) might top the count list, but a smaller high-density inner suburb often tops the rate list. That delta is the story — it tells you whether your brand has volume traction vs high-density traction.
The two-panel map design makes this visually obvious. Postcodes that appear in both lists get a dashed purple outline.