Update to Advan Research REI

{
  "name": "void-analysis",
  "description": "Workflow for identifying tenant candidates that would fit a vacancy or underrepresented category at a retail center, using Advan REI's void analysis endpoint enriched with traffic health and expansion signal data. Use this skill whenever a user asks what tenants would work at a center, what's missing from a property's tenant mix, who should fill a vacancy, what categories are underrepresented, or whether a specific retailer type would be a good fit. Trigger on phrases like \"what tenants would work here\", \"who should fill this space\", \"what's missing from this center\", \"void analysis\", \"tenant candidates\", \"what categories make sense here\", or any request about filling a vacancy or improving a center's tenant mix.\n",
  "included_files": [],
  "skill_md_contents": "---\nname: void-analysis\ndescription: >\n  Workflow for identifying tenant candidates that would fit a vacancy or\n  underrepresented category at a retail center, using Advan REI's void\n  analysis endpoint enriched with traffic health and expansion signal data.\n  Use this skill whenever a user asks what tenants would work at a center,\n  what's missing from a property's tenant mix, who should fill a vacancy,\n  what categories are underrepresented, or whether a specific retailer type\n  would be a good fit. Trigger on phrases like \"what tenants would work here\",\n  \"who should fill this space\", \"what's missing from this center\", \"void\n  analysis\", \"tenant candidates\", \"what categories make sense here\", or any\n  request about filling a vacancy or improving a center's tenant mix.\n---\n\n# Void Analysis Workflow\n\nThe void analysis endpoint does the core analytical work — it returns tenant\ncandidates ranked by dynamic distance, cannibalization risk, and demographic\nmatch. This skill's job is to gather the right parameters before calling it,\nfilter out candidates that don't belong in a retail center context, enrich\nthe top results with real-world health and expansion data, and present the\noutput in a way that's actually useful for a leasing decision.\n\n---\n\n## Step 1: Gather Parameters\n\nBefore calling the endpoint, confirm two things. If either is missing from\nthe conversation, ask — these directly affect the quality of the results.\n\n**Vacancy size:** What is the approximate square footage of the space? This\nis the most important filter. A 1,200 sq ft inline space and a 45,000 sq ft\nanchor box should return completely different candidate sets. If the user\nhasn't specified, ask before proceeding.\n\n**Category preferences or exclusions (optional):** Has the user indicated\nthey're looking for a specific category (food & beverage, fitness, soft\ngoods) or want to exclude something? If so, note it — you'll apply it when\nfiltering results. If no preference is stated, proceed with the full results\nand apply the standard retail center filter described in Step 3.\n\nAlso confirm the property using ALI, location name, and company name as\nusual.\n\n---\n\n## Step 2: Call the Void Analysis Endpoint\n\nCall `void-analysis-api` with the resolved property identifiers and vacancy\nsize parameter. Use the date range from the UI or as specified by the user.\n\nThe endpoint returns a ranked list of tenant candidates scored on:\n- **Dynamic distance** — how far the candidate's typical locations are from\n  this trade area's profile\n- **Cannibalization risk** — likelihood of pulling from an existing nearby\n  location of the same brand\n- **Demographic match** — how well the trade area's visitor profile aligns\n  with the candidate's typical customer base\n\n---\n\n## Step 3: Filter for Retail Center Appropriateness\n\nThe endpoint returns candidates across a broad range of categories. Before\npresenting results, remove any candidates that don't belong in a traditional\nretail center context. Categories to omit by default:\n\n- Auto dealers, car washes, and auto service\n- Hotels and lodging\n- Hospitals, urgent care, and large medical facilities (small-format urgent\n  care or dental that fits inline retail is fine)\n- Gas stations and fuel retailers\n- Industrial, warehouse, or self-storage uses\n- Large-format government or civic uses\n\nUse judgment for edge cases. A drive-through-only concept with no inline\npresence, for example, may not fit a traditional center even if it scores\nwell on demographics. If the user has specified a category preference,\napply that filter here too — prioritize their stated criteria over the\ndefault list.\n\n---\n\n## Step 4: Filter by Vacancy Size\n\nFrom the filtered results, narrow to candidates whose average store footprint\nis compatible with the vacancy. A reasonable match range is ±30% of the\nvacancy size unless the user specifies otherwise.\n\nFlag if the vacancy size is unusual — a very large anchor box or a very\nsmall kiosk-scale space may return a thin candidate set, and it's worth\nnoting that upfront rather than presenting a short list without explanation.\n\n---\n\n## Step 5: Present Results\n\n### Lead with a brief framing\n\nOne or two sentences on what the analysis surfaced — is the candidate pool\nstrong, thin, concentrated in a particular category?\n\n> \"The void analysis surfaces eight strong candidates for the 4,200 sq ft\n> space, with the clearest opportunities in specialty food, health & wellness,\n> and value apparel — all categories underrepresented in this trade area\n> relative to the visitor demographic profile.\"\n\n### Candidate table\n\n| Rank | Tenant | Category | Avg Store Size | Demographic Match | Cannibalization Risk |\n|------|--------|----------|---------------|-------------------|----------------------|\n| 1 | | | X sq ft | High/Med/Low | High/Med/Low |\n\nPresent the top 25 from the filtered, size-matched list, or fewer if the\nlist is shorter. Don't pad the table with weak candidates just to fill rows.\n\nAfter the table, offer to expand to the full unfiltered list if the user\nwants to see everything the endpoint returned before category and size\nfiltering was applied.\n\n### Brief narrative\n\nTwo to three sentences on the standout candidates and any patterns worth\nflagging — a category cluster that keeps appearing, a size mismatch that\nlimits the field, or a category that keeps appearing near the top of the\nrankings.\n\n### Cite data vintage\n\n> *Void analysis based on [date range], via Advan's mobile device panel.*\n\n---\n\n## Handling Thin Results\n\nIf filtering by category and size leaves fewer than three candidates, say so\nand offer options: widen the size range, broaden the category filter, or look\nat what the full unfiltered list shows. Don't present a weak list as if it's\ncomprehensive.\n\n---\n\n## Follow-Ups\n\nAfter presenting the candidate table, offer to enrich the top candidates with\ntwo additional signals. This is the natural next step for any candidate the\nuser wants to pursue seriously — don't do it by default, since it requires\nmultiple additional data pulls and web searches.\n\n> \"Want me to dig deeper on the top candidates? I can pull traffic health\n> and expansion signals for each one — that'll tell you which are actively\n> growing and whether any have announced a leasing pause or contraction.\"\n\nWhen the user confirms, enrich up to 5 candidates:\n\n**Traffic health:** Pull `traffic-summary` and `ranking` for each candidate's\nexisting nearby locations. Note each candidate's trajectory — growing, stable,\nor declining — alongside their void score.\n\n**Expansion signals:** Do a targeted web search for each candidate:\n\"[Retailer name] expansion [year]\" or \"[Retailer name] new locations\" or\n\"[Retailer name] leasing activity\". Flag any candidate that has announced\nclosures or a leasing pause — a strong analytical score doesn't matter if\nthey're not actively opening stores.\n\nPresent the enriched results by adding Trajectory and Expansion Signal columns\nto the original table for the enriched rows, then update the narrative.\n\nIf a specific candidate looks strong and the user wants to go deeper beyond\nenrichment, the natural next steps are pulling that retailer's full traffic\nprofile, checking their trade area overlap with the subject property, or\nrunning a co-tenancy check to see how well they'd complement the existing\ntenant mix. Let the\nconversation lead.\n"
}