← Dubai Wealth Index Real EstateCONTENT HISTORY

Update to Dubai Wealth Index Real Estate

Snapshot Oct 24, 2026 · 13:41 UTC · version 1.8.0

Collection source: downloaded plugin package.

WHAT CHANGED

Instructions updated for shortlist-and-compare

Skill instructions — Now says: Resolve named buildings, areas and communities with `search` first. Confirm ambiguous candidates before comparing or filtering on their identities. This...

Observed in instructions or declared skills. Runtime behavior has not been tested.

Save Dubai Wealth Index Real Estate and check future changes in Following.

Up to 3 plugins free · no card required.

All fields and original values.

Skill instructions

Before

Oct 3, 2026 · 06:30 UTC

No removed lines (ordering may have changed)

After

Oct 24, 2026 · 13:41 UTC

Resolve named buildings, areas and communities with `search` first. Confirm ambiguous candidates before comparing or filtering on their identities. This threshold counts sales, not rent contracts. Inspect rent evidence separately; us...

Compare saved observations

Download comparison JSON

SKILL.md text changes

− removed · + added

--- before
+++ after
@@ -7,14 +7,24 @@
 
 Explicit user instructions take priority over this workflow.
 
+Resolve named buildings, areas and communities with `search` first. Confirm
+ambiguous candidates before comparing or filtering on their identities.
+
 ## Shortlist
 
 - Thresholds the user states (budget, minimum gross yield, bedroom type,
   minimum number of sales, areas) go to `screen_buildings`. Set `minEvidence`
   to at least 10 when the user wants robust figures, and say what you used.
+  This threshold counts sales, not rent contracts. Inspect rent evidence
+  separately; use `buildingRentOnly` when building-specific rents are requested.
+  Keep explicit user bounds unchanged, and disclose the result limit. A
+  truncated result is not an exhaustive shortlist.
 - "Best yields in <area>" without thresholds: `get_area` sorted by yield, or a
   published ranking (`list_rankings`, then `get_ranking` with the area).
   A ranking lists outliers and needs ten qualifying buildings; say so.
+- "Best for short term / Airbnb in <area>": `get_ranking` with
+  `best-short-term-premium` and the area — it lists every qualifying building
+  with the lease comparison. Follow the short-term-rental skill.
 - Say plainly that thresholds apply to **registered medians**, not to
   apartments currently for sale, and that buildings below the publication gate
   cannot appear.
@@ -27,6 +37,9 @@
 - Villa communities: call `get_villa_community` once per community, same
   purpose and bedroom count.
 - Areas: `get_area` per area on the same purpose and bedroom type.
+- Offices or shops: `get_commercial` without an area ranks every commercial
+  area (by yield, sales, price, demand or liquidity); `assetClass` picks
+  offices or shops. Commercial has no building grain — say so if asked.
 
 ## Optional market context
 
Full technical diff · 1 changed fields

changed /skill_md_contents

BEFORE
"---\nname: shortlist-and-compare\ndescription: Build a shortlist of Dubai buildings from registered prices, yields and evidence thresholds, then compare the finalists side by side, using the Dubai Wealth Index tools. Use when the user asks which Dubai buildings or areas meet a budget, yield or rent target, wants the best buildings in an area for rental yield, or wants two to four named buildings compared.\n---\n\n# Shortlist and compare Dubai buildings\n\nExplicit user instructions take priority over this workflow.\n\n## Shortlist\n\n- Thresholds the user states (budget, minimum gross yield, bedroom type,\n  minimum number of sales, areas) go to `screen_buildings`. Set `minEvidence`\n  to at least 10 when the user wants robust figures, and say what you used.\n- \"Best yields in <area>\" without thresholds: `get_area` sorted by yield, or a\n  published ranking (`list_rankings`, then `get_ranking` with the area).\n  A ranking lists outliers and needs ten qualifying buildings; say so.\n- Say plainly that thresholds apply to **registered medians**, not to\n  apartments currently for sale, and that buildings below the publication gate\n  cannot appear.\n\n## Compare\n\n- Two to four apartment buildings: `compare_buildings` on one bedroom type.\n  It returns only the unit sizes every building publishes — keep that grain,\n  and never compare one building's 1-bed with another's 2-bed.\n- Villa communities: call `get_villa_community` once per community, same\n  purpose and bedroom count.\n- Areas: `get_area` per area on the same purpose and bedroom type.\n\n## Optional market context\n\nWhen the question calls for activity or supply context, use `get_market_activity`\non matching bedroom and ready/off-plan cohorts, or `get_supply_pipeline` for\npending projects. Keep source dates and both growth windows. Activity is not\nsale probability or days on market; planned dates are not forecasts. Show a\nbrief summary first and offer detailed evidence only when useful.\n\n## Report\n\nA table works best: building, area, median price, price per sq ft, median rent,\ngross yield, sales and contracts behind them, data date. A difference between\nyields is in percentage points. Link each building's `canonicalUrl`.\n"
AFTER
"---\nname: shortlist-and-compare\ndescription: Build a shortlist of Dubai buildings from registered prices, yields and evidence thresholds, then compare the finalists side by side, using the Dubai Wealth Index tools. Use when the user asks which Dubai buildings or areas meet a budget, yield or rent target, wants the best buildings in an area for rental yield, or wants two to four named buildings compared.\n---\n\n# Shortlist and compare Dubai buildings\n\nExplicit user instructions take priority over this workflow.\n\nResolve named buildings, areas and communities with `search` first. Confirm\nambiguous candidates before comparing or filtering on their identities.\n\n## Shortlist\n\n- Thresholds the user states (budget, minimum gross yield, bedroom type,\n  minimum number of sales, areas) go to `screen_buildings`. Set `minEvidence`\n  to at least 10 when the user wants robust figures, and say what you used.\n  This threshold counts sales, not rent contracts. Inspect rent evidence\n  separately; use `buildingRentOnly` when building-specific rents are requested.\n  Keep explicit user bounds unchanged, and disclose the result limit. A\n  truncated result is not an exhaustive shortlist.\n- \"Best yields in <area>\" without thresholds: `get_area` sorted by yield, or a\n  published ranking (`list_rankings`, then `get_ranking` with the area).\n  A ranking lists outliers and needs ten qualifying buildings; say so.\n- \"Best for short term / Airbnb in <area>\": `get_ranking` with\n  `best-short-term-premium` and the area — it lists every qualifying building\n  with the lease comparison. Follow the short-term-rental skill.\n- Say plainly that thresholds apply to **registered medians**, not to\n  apartments currently for sale, and that buildings below the publication gate\n  cannot appear.\n\n## Compare\n\n- Two to four apartment buildings: `compare_buildings` on one bedroom type.\n  It returns only the unit sizes every building publishes — keep that grain,\n  and never compare one building's 1-bed with another's 2-bed.\n- Villa communities: call `get_villa_community` once per community, same\n  purpose and bedroom count.\n- Areas: `get_area` per area on the same purpose and bedroom type.\n- Offices or shops: `get_commercial` without an area ranks every commercial\n  area (by yield, sales, price, demand or liquidity); `assetClass` picks\n  offices or shops. Commercial has no building grain — say so if asked.\n\n## Optional market context\n\nWhen the question calls for activity or supply context, use `get_market_activity`\non matching bedroom and ready/off-plan cohorts, or `get_supply_pipeline` for\npending projects. Keep source dates and both growth windows. Activity is not\nsale probability or days on market; planned dates are not forecasts. Show a\nbrief summary first and offer detailed evidence only when useful.\n\n## Report\n\nA table works best: building, area, median price, price per sq ft, median rent,\ngross yield, sales and contracts behind them, data date. A difference between\nyields is in percentage points. Link each building's `canonicalUrl`.\n"
Full snapshot data
{
  "description": "Build a shortlist of Dubai buildings from registered prices, yields and evidence thresholds, then compare the finalists side by side, using the Dubai Wealth Index tools. Use when the user asks which Dubai buildings or areas meet a budget, yield or rent target, wants the best buildings in an area for rental yield, or wants two to four named buildings compared.",
  "included_files": [],
  "name": "shortlist-and-compare",
  "skill_md_contents": "---\nname: shortlist-and-compare\ndescription: Build a shortlist of Dubai buildings from registered prices, yields and evidence thresholds, then compare the finalists side by side, using the Dubai Wealth Index tools. Use when the user asks which Dubai buildings or areas meet a budget, yield or rent target, wants the best buildings in an area for rental yield, or wants two to four named buildings compared.\n---\n\n# Shortlist and compare Dubai buildings\n\nExplicit user instructions take priority over this workflow.\n\nResolve named buildings, areas and communities with `search` first. Confirm\nambiguous candidates before comparing or filtering on their identities.\n\n## Shortlist\n\n- Thresholds the user states (budget, minimum gross yield, bedroom type,\n  minimum number of sales, areas) go to `screen_buildings`. Set `minEvidence`\n  to at least 10 when the user wants robust figures, and say what you used.\n  This threshold counts sales, not rent contracts. Inspect rent evidence\n  separately; use `buildingRentOnly` when building-specific rents are requested.\n  Keep explicit user bounds unchanged, and disclose the result limit. A\n  truncated result is not an exhaustive shortlist.\n- \"Best yields in <area>\" without thresholds: `get_area` sorted by yield, or a\n  published ranking (`list_rankings`, then `get_ranking` with the area).\n  A ranking lists outliers and needs ten qualifying buildings; say so.\n- \"Best for short term / Airbnb in <area>\": `get_ranking` with\n  `best-short-term-premium` and the area — it lists every qualifying building\n  with the lease comparison. Follow the short-term-rental skill.\n- Say plainly that thresholds apply to **registered medians**, not to\n  apartments currently for sale, and that buildings below the publication gate\n  cannot appear.\n\n## Compare\n\n- Two to four apartment buildings: `compare_buildings` on one bedroom type.\n  It returns only the unit sizes every building publishes — keep that grain,\n  and never compare one building's 1-bed with another's 2-bed.\n- Villa communities: call `get_villa_community` once per community, same\n  purpose and bedroom count.\n- Areas: `get_area` per area on the same purpose and bedroom type.\n- Offices or shops: `get_commercial` without an area ranks every commercial\n  area (by yield, sales, price, demand or liquidity); `assetClass` picks\n  offices or shops. Commercial has no building grain — say so if asked.\n\n## Optional market context\n\nWhen the question calls for activity or supply context, use `get_market_activity`\non matching bedroom and ready/off-plan cohorts, or `get_supply_pipeline` for\npending projects. Keep source dates and both growth windows. Activity is not\nsale probability or days on market; planned dates are not forecasts. Show a\nbrief summary first and offer detailed evidence only when useful.\n\n## Report\n\nA table works best: building, area, median price, price per sq ft, median rent,\ngross yield, sales and contracts behind them, data date. A difference between\nyields is in percentage points. Link each building's `canonicalUrl`.\n"
}

SHA-256 of public snapshot: 9b7cddcb38a624b55451c226fd69f90105cf057ff6bb38a31e7843fe5f92c8b4