Agent finder

Skill realtyapi/realtyapi-skills/skills/agent-finder

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 agent-finder

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 or evaluate real estate agents in an area or for a property — search agents, pull their profile, recent listings/sales, and reviews, then return a vetted shortlist. Triggers on "find a realtor in …", "who are the top agents for …", "who listed this house", "best selling agents near …", "agent reviews for …".

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

2.8 KB, as published. Nobody here has run it

Agent Finder

Overview

Find the right real estate agent for an area or property and back the recommendation with evidence — recent activity, specialization, and reviews — as a ranked shortlist.

Use realtyapi-api for auth and endpoint discovery.

When to Use

"Find me a top buyer's agent in {area}."
"Who are the most active listing agents for {neighborhood}?"
"Who listed this property?"
"Pull reviews for this agent."

Workflow

Pick the portal that has agent data for the market (US portals like redfin, realtor, zillow have agent search/details/reviews; check llms.txt for agent* endpoints on the relevant portal).
Search agents for the area/criteria (agent/search, agentsearch), or get the listing's agent (owner-agent, agentInfo) when starting from a property.
Enrich each candidate: profile/details, recent listings & sales, and reviews (agentdetails, agentforsale/agentsold, agentreviews).
Score for fit — recent activity/volume in the user's area and price band, buyer-vs-seller focus, property-type match, and review signal.
Shortlist with reasoning and contact/profile links.

Output Format

# Agent Shortlist: {area / property}

Portal: {} · {N} candidates

| # | Agent | Brokerage | Recent sales (12mo) | Area/price focus | Rating | Profile |
|--:|-------|-----------|--------------------:|------------------|-------:|---------|

## Recommendations
1. {agent} — fit because {recent activity in area + price band + reviews}
2. …

## Notes
- Ranked by: {criterion}
- Caveats: activity counts are from public portal data and may be partial.

Common Pitfalls

Match the agent to the user's side (buyer vs. seller) and price band — raw sale counts alone don't equal fit.
Reviews can be sparse or skewed; treat them as one signal, not the verdict.
Don't expose private contact info beyond what the public profile provides.
Note that activity figures reflect public portal data and may undercount.