Builds an evidence-traceable comparison of local businesses, categories, attributes, hours, and review themes across matched geographic areas.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install local-competitive-landscape
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install local-competitive-landscape using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Local Competitive Landscape?
Local Competitive Landscape uses Crawlora's Google Maps dataset alongside live Google Maps, Apple Maps, and Yelp to create like-for-like business landscape comparisons. It organizes source coverage, area boundaries, business records, provider identifiers, attributes, ratings, review samples, and retrieval metadata into a traceable analysis.
This Openclaw Skills workflow is designed for observed competitor coverage, category mix, and service comparisons—not lead generation, demand forecasting, revenue estimates, market-share claims, or site-viability decisions. It explicitly separates unknown data, provider disagreements, search omissions, and bounded samples from verified findings.
Local Competitive Landscape Use Cases
- Compare competitor counts and category mix across matched neighborhoods, cities, radii, or polygons.
- Audit local business coverage across Crawlora's indexed Google Maps dataset, live Google Maps, Apple Maps, and Yelp.
- Identify observed differences in hours, services, amenities, business attributes, and operating status.
- Build a source-specific competitor matrix while preserving provider IDs, URLs, and conflicting records.
- Examine a small, disclosed sample of visible review themes by platform and retrieval date.
- Distinguish observed gaps in a bounded search sample from proven service gaps supported by complete eligible-business coverage.
- Produce evidence-aware local market maps without turning directory counts into demand, sales, revenue, or population estimates.
How Local Competitive Landscape Works
- Define each comparable area using an administrative boundary, radius and center coordinates, or an explicit polygon.
- Document the business concept, inclusion rules, closure handling, source mix, filters, retrieval date, pagination or limit budget, and whether collection is exhaustive or bounded.
- Discover exact Crawlora dataset category values through the category facets endpoint and reuse returned values without modification.
- Query the Google Maps business dataset to establish a bounded indexed-corpus baseline, preserving totals, pagination, filters, timestamps, and exhaustion status.
- Run identical live Google searches for every area, then post-filter coordinates or addresses against the defined boundaries.
- Query Apple Maps with matched wording, region, language, viewport span, and limit; record relocation and discard results outside the target boundary.
- Query Yelp using the same term and location convention, paging only to the declared limit.
- Deduplicate within each source by provider ID, then reconcile cross-provider records using name, address, coordinates, phone, or domain evidence.
- Preserve unknown coordinates, null statuses, source disagreements, chain branches, and separate dataset and live-provider identifiers.
- Generate a coverage ledger, business matrix, and area comparison showing deduplicated observed counts, category mix, attributes, unknowns, and omission risks.
- Compare ratings only within the same platform, retain sample sizes, and treat review themes as findings from a dated visible sample rather than population-level evidence.
- Label conclusions as observed gaps unless explicit definitions, complete eligible coverage, and verified attributes support a proven service gap.
Local Competitive Landscape Setup
- Obtain a Crawlora API key and keep it in the environment rather than hard-coding it.
- Run the bundled
scripts/crawlora.shfrom the skill directory or use its absolute path. The wrapper sendsx-api-keyto Crawlora's v1 API. - Review
reference/endpoints.mdfor endpoint parameters and response behavior. - Check both HTTP status and the application response code. Stop on
401or403, back off on429, and retry a transient5xxresponse once. Treat failed requests as unavailable evidence, not empty areas. - Keep Google Maps calls at least one second apart.
export CRAWLORA_API_KEY="your_crawlora_api_key"
scripts/crawlora.sh /datasets/google-map-businesses/facets \\
facet=category q=coffee permanently_closed=false
# Replace CATEGORY with an exact .data.items[].value returned above.
scripts/crawlora.sh /datasets/google-map-businesses/search \\
category="$CATEGORY" lat=42.3736 lon=-71.1097 radius_m=2000 \\
permanently_closed=false sort=distance_asc page=1 page_size=100
scripts/crawlora.sh -X POST /google/map/search \\
'{"keyword":"coffee shop Cambridge Massachusetts","language":"en","country":"us"}'
Use identical category, geography type, dates, status filters, pagination rules, and source mix for every comparison area. Do not equate a Google radius in meters with an Apple viewport span in latitude and longitude degrees.
Local Competitive Landscape Data Schema & Taxonomy
The workflow produces three linked analytical outputs:
| Output | Core fields | Purpose |
|---|---|---|
| Coverage ledger | Area, source, query or category, geometry, filters, page or limit range, retrieved count, in-area count, unknown-location count, relocation status, bounded or exhausted status, failure status, retrieval time | Documents what each provider and area actually covered |
| Business matrix | Area membership, canonical branch, provider IDs, source names, categories, address, coordinates, status, hours, attributes, rating, review count, source URLs, retrieval time, match confidence | Preserves reconciled business-level evidence |
| Comparison | Deduplicated observed counts, category mix, attribute mix, unknowns, disagreements, and source limitations | Supports matched-area interpretation without unsupported market claims |
Important data rules:
- Store area geometry and boundary type explicitly: administrative boundary, radius with center, or polygon.
- Preserve source-specific IDs, categories, names, URLs, attributes, timestamps, and disagreements after reconciliation.
- Keep Crawlora dataset update or crawl timestamps separate from request retrieval timestamps.
- Use the raw dataset
place_idfor stored-item lookups and resolve live Google records by name and address unless identifier compatibility is established. - Keep confirmed closures distinct from null status;
permanently_closed=falsedoes not certify that a business is open. - Store unknown coordinates and unknown status in explicit unknown buckets.
- Treat null ratings and null review counts as unknown, not numeric zero.
- Keep rating scales separate by platform and never blend Google, Apple, and Yelp averages.
- Record review-theme counts with source, date, visible sample size, and the reviewed business set.
- Maintain separate coverage rows when provider geometry differs, including Apple's viewport behavior and Yelp's search area.
- Assign a business to every area whose boundary contains it, but do not sum overlapping-area counts as a unique total.
Local Competitive Landscape Advanced Features
- Multi-source reconciliation across Crawlora's Google Maps dataset, live Google Maps, Apple Maps, and Yelp.
- Matched-area protocols with identical categories, filters, dates, query wording, and collection budgets.
- Provider-specific geometry handling, including radius filtering, polygon or administrative boundaries, Apple viewport spans, and relocated-result detection.
- Coverage accounting that distinguishes returned, in-area, unknown-location, bounded, exhausted, failed, and relocated results.
- Conservative evidence labels separating proven service gaps from observed sample gaps with search omission risk.
- Cross-provider deduplication with branch-level chain handling, canonical records, match confidence, and retained source disagreements.
- Targeted detail refreshes for ambiguous or representative rows through Google place, Google review, and Yelp business endpoints.
- Small, disclosed review-theme sampling that preserves platform and retrieval-date context.
- API resilience controls for authentication failures, rate limits, transient server errors, and request spacing.
- Openclaw Skills-compatible documentation structure that supports repeatable, auditable local competitive research without unsupported demand or revenue modeling.
SKILL.md
Loading
Related Openclaw Skills
Xiaohongshu Record Organizer
A Node.js-powered Openclaw Skills integration that retrieves and organizes public Xiaohongshu notes, creator posts, comments, and engagement metrics for research and decision-making.
Infinite Creation
Infinite Creation orchestrates a local AI workflow that transforms novels, scripts, or ideas into voiced comic dramas and short videos.
List Your Series
Help independent creators get their manga, webcomic, webtoon, light novel or anime discovered by listing or claiming it in AnimeHunt’s free directory.
Stockpile Market
Stockpile connects OpenClaw agents to e-commerce tools for managing storefronts, products, collectible appraisals, and customer orders.
FreeCAD CADPilot
FreeCAD CADPilot connects OpenClaw to a local FreeCAD instance through CADPilot’s stdio MCP server and guides safe, advertised-tool-only CAD workflows.
Cinema Suite
Cinema Suite maps cinema identities and ticket channels to installable OpenClaw mode capabilities for reliable ticket capture, replay, coupon binding, and failure handling.