Listing search

Skill realtyapi/realtyapi-skills/skills/listing-search

Real estate research skills for AI agents — property briefs, listing search, rentals, CMAs, investment deal screening, and agent finders, powered by RealtyAPI

Install

npx -y skills add realtyapi/realtyapi-skills --skill listing-search

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when the user wants to find for-sale (or sold) homes matching criteria in an area — location, price range, beds/baths, home type, status. Searches the right portal(s) with filters, paginates, and returns a ranked, de-duplicated listings table with source links. Triggers on "find houses in …", "search for 3-bed homes under $500k", "what's for sale in …", "show me recently sold homes near …".

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

3.0 KB, as published. Nobody here has run it

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 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

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.
Pick the portal for the location's market (catalog in realtyapi-api).
Resolve the area — use autocomplete / locations to turn a place name into the id/coordinates/polygon the search endpoint expects.
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.).
Paginate to gather enough results (increment page or follow nextPageCursor) — but cap it and tell the user how many pages/credits you used.
De-dupe and rank by the user's priority (price, $/sqft, newest, size).
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.