Property Listings Card Presentation

Present researched property and rental search results, shortlist comparisons, re-rankings and follow-ups as browsable cards in the Hermes desktop transcript.

Hermes Intermediate Copied: 0
1 resource

Requirements

  • A Hermes desktop conversation is needed for native cards; the backend may be local or remote.
  • Property details must be supplied by the user or verified through web_search, web_extract, or the browser tools available in the session.
  • No additional API keys or dependencies are required for card formatting.

How to use

This is a presentation recipe, not a listing search service or an investment valuation.

Outside the desktop app, use ordinary Markdown with source links instead; other clients need not render listing fences.

Install this optional skill through the Skills catalog, or use terminal:

Install this optional skill through the Skills catalog, or use terminal.

hermes skills install official/productivity/property-listings

Load the skill with skill_view(name="property-listings") when presenting listings. Installing does not retrofit the running conversation's skill index: start a new conversation for automatic discovery, or explicitly load the installed skill now.

Emit a fenced code block whose language is listing and whose body is valid JSON, using one object, an array of objects, or { "listings": [...] } for a comparison. Fields: address is a required nonempty street address or property headline; price is a formatted string including currency and rental period if applicable; beds and baths are positive numeric counts, omitting unknown values; size is formatted area including units; note says why the property is worth a look; facts is an array of short verified specs or amenities; catches is an array of risks or questions to verify before a tour; images are direct HTTPS photo URLs in listing order with the first as hero; links is an array of { "label": "Source", "url": "https://..." } detail-page links, not search-result URLs.

Gather the address, price, specs, photos and canonical detail URL.

Distinguish verified facts from unknowns; do not invent prices, amenities, or photo URLs.

Deduplicate portal mirrors of the same property into one card, retaining useful source links, and keep source dates and availability caveats in the surrounding prose.

Emit the listing fence for every property presented, including follow-ups and re-rankings; keep facts short and put unresolved concerns in catches.

Check the JSON before sending; the fictional format example illustrates all fields, so replace its values and example URLs with verified listing data.

{
  "address": "12 Example Lane",
  "price": "$2,400/mo",
  "beds": 3,
  "baths": 2.5,
  "size": "1,600 sqft",
  "note": "Fits the requested space and budget.",
  "facts": ["12-month lease", "Covered parking"],
  "catches": ["Verify pet policy and total move-in fees"],
  "images": ["https://example.com/property/front.jpg", "https://example.com/property/kitchen.jpg"],
  "links": [{"label": "Listing details", "url": "https://example.com/property/12"}]
}

Cards are authored from gathered data, not fetched from a listing URL or embedded portal page.

A sparse card needs only an address; omit unknown fields rather than filling them with guesses.

Use direct remote image URLs, not local paths, data URLs, or search-result pages.

Expired or blocked images disappear from the gallery; the text and links still matter.

Keep a fence to at most 24 properties and 40 images per property.

Facts, catches and links are capped at 12 entries each, and text fields are truncated to 400 characters by the renderer.

Malformed JSON or a card without identity falls back to a plain code block.

A valid card is not proof that the underlying listing is current or accurate.

If the card fails to render, validate the fence language and JSON.

Then preserve a readable Markdown fallback with the same facts and links.

Source: nousresearch/hermes-agent and its contributors. License: MIT.

Copyright (c) 2025 Nous Research

Translation and editorial adaptation by ClawCases.

>Resources

>Related Use Cases

>More at this level: Intermediate