Update to Advan Research REI

{
  "description": "Structured workflow for evaluating one or more candidate retail locations using Advan REI foot traffic, trade area, competitive, and cross-shopping data. Use this skill whenever a user is assessing whether a site is a good fit for a retailer or tenant, comparing multiple candidate locations, evaluating market demand at a specific address, or analyzing cannibalization risk from a nearby existing store. Trigger on phrases like \"should we open here\", \"evaluate this site\", \"compare these locations\", \"is this market viable\", \"how does this site stack up\", \"would this cannibalize our existing store\", \"what's the co-tenancy like\", or any request that frames a location decision. Also trigger when a broker, retailer, or developer asks about a site's potential without using explicit site selection language.\n",
  "included_files": [],
  "name": "site-selection",
  "skill_md_contents": "---\nname: site-selection\ndescription: >\n  Structured workflow for evaluating one or more candidate retail locations\n  using Advan REI foot traffic, trade area, competitive, and cross-shopping\n  data. Use this skill whenever a user is assessing whether a site is a good\n  fit for a retailer or tenant, comparing multiple candidate locations,\n  evaluating market demand at a specific address, or analyzing cannibalization\n  risk from a nearby existing store. Trigger on phrases like \"should we open\n  here\", \"evaluate this site\", \"compare these locations\", \"is this market\n  viable\", \"how does this site stack up\", \"would this cannibalize our\n  existing store\", \"what's the co-tenancy like\", or any request that frames\n  a location decision. Also trigger when a broker, retailer, or developer\n  asks about a site's potential without using explicit site selection language.\n---\n\n# Site Selection Workflow\n\nSite selection answers a decision question: is this a good location, and for\nwhom? The workflow is data-driven but ends with a directional take — not just\na data dump, but a read on what the numbers mean for the decision at hand.\n\nThe workflow has two modes depending on what the user is evaluating:\n\n- **Single site:** Full analysis of one candidate location.\n- **Multi-site comparison:** Run the same analysis for each site, then\n  synthesize a side-by-side at the end.\n\nBoth modes follow the same stages. For multi-site, run all stages for each\nlocation before moving to synthesis.\n\n---\n\n## Before You Start: Orient the Request\n\nBefore pulling data, make sure you understand three things. You may already\nhave them from context — if so, proceed. If not, ask one focused question\nrather than a list.\n\n1. **What location(s) are being evaluated?** An address, a named property, a\n   market area?\n2. **Is there a specific retailer or tenant in mind?** This drives the\n   co-tenancy and cannibalization steps. If no retailer is specified, those\n   steps are still useful but framed more generally.\n3. **What's the decision?** Opening a new store, evaluating a lease, advising\n   a client, underwriting a development? The answer shapes what you emphasize\n   in the synthesis.\n\n---\n\n## Stage 1: Resolve the Location(s)\n\nIf the user named a specific existing property, use ALI, location name, and\ncompany name as usual. If they provided an address or a general description\nof a candidate site, use `search` to find the closest matching property or\nreference location. Confirm before proceeding if there's any ambiguity.\n\nFor multi-site comparisons, resolve all locations before moving to Stage 2.\n\n---\n\n## Stage 2: Subject Site Performance\n\nIf the candidate site is an existing property with traffic data (an occupied\ncenter, a current tenant location), pull `traffic-summary` for it. This\nestablishes baseline performance at this specific location and gives the user\na sense of what the site has historically attracted.\n\nIf the site is vacant, a raw address, or a new development with no existing\ntraffic history, skip this step and note it. The trade area and competitive\ncontext in later stages will carry the location assessment.\n\nUse the date range from the UI or as specified by the user.\n\n---\n\n## Stage 3: Trade Area\n\nCall `trade-area` using the same parameters established in any current session\ntrade area settings, or default to the closest 70% of visitors if no setting\nis available and the user hasn't specified otherwise.\n\nThis tells you who is realistically accessible from this location. Capture:\n- Approximate size (radius or drive time)\n- The geographic shape — is it symmetric, or constrained by highways, water,\n  or dense competition on one side?\n\nYou don't need to run the full demographic deep-dive here unless the user\nasked for it — that's covered in a standalone trade-area-analysis. For site\nselection, the key output is the catchment footprint and a top-line\ndemographic read (median HHI, dominant age cohort) to assess fit with the\nintended tenant.\n\n---\n\n## Stage 4: Competitive Landscape\n\nUse `ranking` and/or `performers-list` to identify how competing properties\nin the area are performing. Then pull `traffic-summary` for the most relevant\ncompetitors — typically the 2–3 strongest nearby alternatives that would be\ndrawing from the same trade area.\n\nWhat you're looking for:\n- Is there a dominant competitor already capturing the majority of foot\n  traffic in this catchment?\n- Are there underperforming competitors that might signal market weakness —\n  or an opportunity if the right tenant fills the gap?\n- How does traffic at nearby properties trend? Growing markets tend to lift\n  well-positioned sites; declining markets carry more risk regardless of\n  individual site quality.\n\nFlag the competitive intensity plainly. A site surrounded by strong\nperformers in the same category is a much harder entry than one where\ncompetition is fragmented or underperforming.\n\n---\n\n## Stage 5: Co-Tenancy and Cross-Shopping\n\nUse `shared-customers` or `shared-customers-retailer` to understand what\nother retailers the visitors in this trade area frequent.\n\nIf a specific retailer or tenant is in mind, this step answers: are the\ncustomers already here aligned with that retailer's typical shopper? Look for\nstrong affinity with anchor tenants or complementary categories that would\nsupport the intended use.\n\nIf no specific retailer is named, use this step to characterize the trade\narea's retail DNA — what categories and brands dominate customer behavior —\nand flag whether the site has the co-tenancy to support the type of use the\nuser is evaluating.\n\n**Co-tenant health check:** For the most significant co-tenants at or near\nthe candidate site, pull `traffic-summary` and `ranking` to assess whether\nthey are strong performers. A site with declining or underperforming anchors\nis a materially different proposition than one with healthy, growing\nco-tenants. Look for:\n- YoY traffic trend for key co-tenants — growing, flat, or declining?\n- Ranking within their submarket or category — are they top performers or\n  laggards?\n- Any co-tenant weakness that could signal a future anchor departure or\n  reduced draw\n\nFlag co-tenant risk directly if the data shows it. A retailer opening next to\na struggling anchor takes on indirect risk that isn't visible in the site's\nown trade area data.\n\n---\n\n## Stage 6: Cannibalization Check (Conditional)\n\nRun this step only if both of the following are true:\n- A specific retailer or brand is identified as the potential tenant.\n- That retailer has one or more existing locations within a plausible draw\n  distance from the candidate site (typically within the trade area or\n  overlapping trade area).\n\nIf both conditions are met:\n1. Pull `traffic-summary` for the existing nearby location(s) of the same\n   brand.\n2. Pull `trade-area` for the existing location(s) and compare the geographic\n   overlap with the candidate site's trade area.\n3. Estimate the degree of overlap: do the two trade areas share significant\n   geography? If the candidate site's trade area is largely contained within\n   the existing location's trade area, cannibalization risk is high. If\n   there's limited overlap — the sites serve distinct neighborhoods or the\n   candidate site extends reach into a new population — risk is lower.\n\nPresent the cannibalization finding clearly and without burying it. If the\noverlap is significant, the user needs to know before making a decision.\n\n> \"The candidate site's trade area overlaps substantially with the existing\n> [Brand] at [Location] — roughly [X]% of the potential customer base is\n> already being served. That doesn't rule out this site, but it means the\n> incremental opportunity is smaller than the raw trade area would suggest.\"\n\nIf the conditions aren't met, skip this step entirely — don't raise\ncannibalization as a concern if there's no nearby same-brand location to\nevaluate against.\n\n---\n\n## Stage 7: Comparable Benchmarking\n\nUse `ranking` to benchmark the candidate site — or the most comparable\nexisting property at or near it — against similar properties in the market.\nThis establishes whether this location is performing at, above, or below what\nyou'd expect for the submarket.\n\nFor a multi-site comparison, this is where you start to see which site sits\nin the stronger performing market and which has the better trajectory.\n\n---\n\n## Stage 8: Retailer Footprint Fit (Conditional)\n\nRun this stage only if a specific retailer is named. Skip it if the analysis\nis general or the tenant is unspecified.\n\nInvoke the **retailer footprint skill** in site comparison mode, using the\ncandidate site as the subject property and the named retailer as the\ncomparison target. That skill handles all data pulls and interpretation —\ndon't re-implement the logic here.\n\nFor a multi-site comparison, run the retailer footprint skill for each\ncandidate site and carry the fit assessment (strong / moderate / weak) into\nthe Stage 9 synthesis. This stage frequently produces the clearest\ndifferentiation between sites: which one's behavioral and demographic profile\nmost closely matches where the retailer already succeeds.\n\n---\n\n## Stage 9: Synthesize and Present\n\n### Search for real-world context\n\nDo a targeted web search before writing the synthesis. Useful angles for\nsite selection:\n- Recent retail openings, closings, or announced deals in the submarket\n- Development pipeline — new supply coming that could affect the competitive\n  picture\n- Local economic conditions, employment base, population growth\n- Any news specific to the retailer being evaluated (expansion plans,\n  category performance, brand momentum)\n- Infrastructure changes — new transit, road projects, or access changes\n  that could affect the catchment\n\nWeave in what's relevant. Skip what isn't.\n\n### Lead with the directional take\n\nDon't open with a table. Open with a clear read on what the data says about\nthis site.\n\n> \"Based on the data, [Location] looks like a credible opportunity for\n> [Retailer/Use]. The trade area is well-populated and the competitive set is\n> fragmented — no dominant player is locking up this catchment. The main\n> risk is [X].\"\n\nOr if the picture is mixed:\n\n> \"[Location] has a strong trade area but faces meaningful competitive\n> pressure from [Competitor], which is already capturing a large share of\n> foot traffic in the immediate catchment.\"\n\nBe direct. The user is making or informing a decision — they need a clear\nsignal, not just a list of considerations.\n\n### Summary table\n\n| Factor | Finding |\n|--------|---------|\n| Subject site traffic | [X visits / period, +/-Y% YoY — or N/A if vacant] |\n| Trade area size | ~X miles / Y-min drive (Z% threshold) |\n| Trade area HHI | $X median |\n| Competitive intensity | [Low / Moderate / High] — [brief note] |\n| Top cross-shopping affinity | [Brand/category] |\n| Cannibalization risk | [Low / Moderate / High — or N/A] |\n| Submarket rank | #X of Y comparable properties |\n| Retailer footprint fit | [Strong / Moderate / Weak — or N/A] |\n\nFor multi-site comparisons, run this table with one column per site so the\nuser can compare directly.\n\n### Supporting narrative\n\nTwo to four sentences covering what the numbers mean together. Highlight\nconvergent signals (multiple data points pointing the same direction) and\nflag any divergence (e.g., strong trade area demographics but high\ncompetitive saturation). If external context from the web search adds\nsomething meaningful, work it in here.\n\n### Cite data vintage\n\n> *Analysis based on [date range], via Advan's mobile device panel.*\n\n---\n\n## Handling Gaps\n\n**No traffic data for the candidate site:** Common for vacant or new\nlocations. Note it, skip Stage 2, and let the trade area and competitive\ndata carry the assessment.\n\n**No nearby same-brand locations for cannibalization:** Skip Stage 6 without\ncomment — don't raise it as a concern when there's nothing to evaluate.\n\n**Partial competitive data:** Present what's available, note what's missing,\ndon't fill gaps with speculation.\n\n---\n\n## Follow-Ups\n\nLet the conversation lead. The most natural next steps from a site selection\nanalysis are usually a full demographic breakdown of the trade area, a void\nanalysis to identify which tenant categories would fit the customer base, or\na deeper competitive pull on a specific competitor that came up in the data.\nMention one if it's obviously relevant — otherwise let the user direct.\n"
}