shortlist-and-compare
Skill0 starsChanged 41 days agoMITView on GitHub
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.
In this repository8 other files it gives its agents.
- building-reportSkill
- check-a-claimSkill
- check-asking-priceSkill
- cite-dubai-property-figuresSkill
- get-startedSkill
- request-infoSkill
- short-term-rentalSkill
- track-saved-buildingsSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 20
Keep explicit user bounds unchanged, and disclose the result limit.
- Very specific: line 46
When the question calls for activity or supply context, use get_market_activity on matching bedroom and ready/off-plan cohorts, or …
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Shortlist and compare Dubai buildings
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. SetminEvidenceto 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; usebuildingRentOnlywhen 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_areasorted by yield, or a published ranking (list_rankings, thenget_rankingwith the area). A ranking lists outliers and needs ten qualifying buildings; say so. - "Best for short term / Airbnb in
<area>":get_rankingwithbest-short-term-premiumand 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.
Compare
- Two to four apartment buildings:
compare_buildingson one bedroom type. It returns only the unit sizes every building publishes — keep that grain, and never compare one building's 1-bed with another's 2-bed. - Villa communities: call
get_villa_communityonce per community, same purpose and bedroom count. - Areas:
get_areaper area on the same purpose and bedroom type. - Offices or shops:
get_commercialwithout an area ranks every commercial area (by yield, sales, price, demand or liquidity);assetClasspicks offices or shops. Commercial has no building grain — say so if asked.
Optional market context
When the question calls for activity or supply context, use get_market_activity
on matching bedroom and ready/off-plan cohorts, or get_supply_pipeline for
pending projects. Keep source dates and both growth windows. Activity is not
sale probability or days on market; planned dates are not forecasts. Show a
brief summary first and offer detailed evidence only when useful.
Report
A table works best: building, area, median price, price per sq ft, median rent,
gross yield, sales and contracts behind them, data date. A difference between
yields is in percentage points. Link each building's canonicalUrl.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

