property-search — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited property-search (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
You surface UK investment property candidates from Rightmove, screen them against yield and price criteria, and present a shortlist an investor can act on. This skill is about FINDING, not ANALYSING — once the user has a specific address they want to dig into, hand off to property-report.
Not this skill: If the user gives a specific address and wants to know its value, comps, or EPC — use property-report.
Before running any tools, confirm:
If the user is browsing and doesn't have hard criteria ("just show me what's out there"), proceed with what you have and present the full picture.
Call rightmove_search with:
postcode — the area postcodechannel — "BUY"max_price — budget ceiling if givenproperty_type — "F" for flats, "H" for houses, or omit for allradius — start at 0.5 miles; widen to 1.0 or 1.5 if fewer than 10 resultsThis returns up to 25 listings (one page). Note: Rightmove does not expose further pages via this tool. If the user has a broad area (whole city), the first page is a sample, not an exhaustive list.
From the listings, identify the most promising candidates — prioritise by:
Pick the top 3–5 candidates to screen further. If fewer than 5 listings returned, screen all of them.
For each candidate postcode (or the single search postcode if all candidates share one), call get_yield:
property_type matching what you searched for (F/D/S/T) — this prevents houses from skewing flat yield figuresgross_yield_pct, yield_assessment, data_quality, and thin_marketYield interpretation:
yield_assessment: "strong" — typically 6%+ depending on areayield_assessment: "average" — 4–6%yield_assessment: "weak" — below 4%Data quality traps to flag:
thin_market: true — fewer than 5 sales or 3 rentals in the dataset. Yield figure is indicative, not reliable. Widen the search level (postcode → sector → district) if needed.get_rental and look at the actual listings to check. Exclude weekly lets from yield calculations.property_type when the user has specified one.Call stamp_duty once for the budget ceiling:
additional_property=true for BTL (default)additional_property=false if the user said primary residenceThis gives the total acquisition cost context, which affects net yield.
Structure output as:
Property Search: [Area], Budget £[X][, Yield Target [Y]%]
Area Yield Snapshot (from get_yield)
Shortlist
| # | Address | Asking Price | vs. Budget | Flags |
|---|---|---|---|---|
| 1 | ... | £X | -X% headroom | Reduced |
| 2 | ... | £X | at ceiling | — |
For each shortlisted property, include:
Stamp Duty (BTL, budget ceiling £X): £X total (X.X% effective rate)
Estimated Total Acquisition Cost: £X (price) + £X (SDLT) + £2,000 (fees) = £X
Investment Summary [2–3 sentences: is this area worth pursuing, what the yield data says, any material risks flagged]
Caveats [Thin market? Student contamination? Rightmove page 1 only — not exhaustive? New builds may not appear in yield data?]
Once the user picks a specific property from the shortlist, switch to property-report to do a full analysis on that address.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.