Listing Search

Listing Search

Overview

Find homes for sale (or recently sold) that match the user's criteria in a given area, and return a clean, ranked shortlist with links — not raw JSON.

Use [realtyapi-api](../realtyapi-api/SKILL.md) for auth and endpoint discovery.

When to Use

• "Find 3-bed houses under $600k in Austin."
• "What condos are for sale near this zip with a pool?"
• "Show recently sold homes on this street."
• Building a buyer's shortlist or a market scan for an area.

Workflow

1. Clarify criteria if missing the essentials: location, buy vs. rent vs. sold,

price range, beds/baths, home type. Don't over-ask — sensible defaults are fine.

1. Pick the portal for the location's market (catalog in realtyapi-api).
2. Resolve the area — use autocomplete / locations to turn a place name into

the id/coordinates/polygon the search endpoint expects.

1. Search with filters — call search/byaddress | search/bycoordinates |

search/bypolygon | search/bymapbounds. Read the endpoint's openapi.json for the exact filter params (price, beds, baths, status, home type, etc.).

1. Paginate to gather enough results (increment page or follow

nextPageCursor) — but cap it and tell the user how many pages/credits you used.

1. De-dupe and rank by the user's priority (price, $/sqft, newest, size).
2. Present the table below. State the filters applied and the result count.

Output Format

# Listings: {criteria} in {area}

Portal: {portal} · Filters: {beds/baths/price/type/status} · {N} results ({pages} pages)

| # | Address | Price | Beds/Baths | Size | $/sqft | Status | Link |
|--:|---------|------:|-----------|-----:|-------:|--------|------|

## Notes
- Sorted by: {criterion}
- Standouts: {best value / newest / etc.}
- Excluded: {dupes / out-of-range, if any}

Common Pitfalls

• Confirm buy vs. rent vs. sold — the wrong status filter returns the wrong set.
• One search covers one portal/market. Don't claim "all listings" — say which portal.
• Respect credits: each page is a request. Cap pagination and report what you used.
• Keep the source link for every row so the user can open the real listing.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: realtyapi
• Source: realtyapi/realtyapi-skills
• License: MIT

Install and usage instructions live in the source repository linked above.