agentleFS
harborrankharborrank/harborrank-skills/skills/local-seo/SKILL.md

local-seo

Skill2 starsChanged yesterdayMITView on GitHub

Improve a local business's visibility in Google Maps and the local pack: check where it ranks for its main services across the area it serves, compare it with the businesses that outrank it (reviews, categories, website, proximity), review its Google Business Profile signals and questions, find local keywords, and produce a prioritized local action plan. Use when the user asks why their business doesn't show on Google Maps or in the local pack, about near-me rankings, Google Business Profile (GBP) optimization, service-area or multi-location SEO, local keywords, reviews, or NAP and citations.

26 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ecommerce-seo, image-seo and 3 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MYehia565Skill

    ecommerce-seo

    Applies Google ecommerce SEO guidance: IA/URLs, product data, and shopping-related structured data. Use when building or fixing product/category/store search presence.

    Also in 4 projects that use this

  • arturseo-geoSkill

    image-seo

    Full image SEO pipeline: optimise file size, convert to WebP, upload to WordPress media library, and set all 4 SEO metadata fields (alt text, title, caption, description). Optionally set as featured image on a post. Use when the user wants to upload an image to WordPress, optimise images for a post, or bulk-process a folder of images. Automatically activates when user references an image file and WordPress deployment.

    Also in 4 projects that use this

  • deeployCOSkill

    youtube-seo

    Advanced YouTube SEO analysis and optimization for channels and videos. Routes to specialized sub-skills for audits, single-video deep dives, metadata optimization, channel branding, keyword research, thumbnails, and competitor intel. Models YouTube's modern recommender (session watch time / Reinforce / persona matching) not just keyword match. Use when user says "YouTube SEO", "optimize my video", "rank my YouTube video", "YouTube channel audit", "YouTube keywords", or provides a YouTube URL.

    Also in 3 projects that use this

  • 01claudingSkill

    seo-report

    SEO reporting and analytics dashboard generation. Creates weekly digests, monthly performance reports, quarterly strategy reviews, and real-time dashboard templates. Use when user says "SEO report", "weekly digest", "monthly report", "dashboard", "SEO metrics", "performance summary".

    Also in 3 projects that use this

  • jstanxSkill

    ai-visibility-audit

    Audit how ready a brand is to be cited by answer engines and produce a prioritized fix list — baseline what ChatGPT, Perplexity, Gemini, and Google AI Overviews say today, then score discoverability, interpretability, attribution, authority, and governance. Works for any business, B2B or B2C, product or service. Use when the request is to run an AEO or GEO audit, check AI visibility, find out why a brand is not cited by AI, baseline AI search presence, or assess answer-engine readiness. For competitor share of voice use competitor-ai-analysis; for ongoing tracking use ai-visibility-tracking.

    Also in 3 projects that use this

The file

Show its rules and text

We split this skill into the rules it gives an agent

19 rules. 0 are common, 10 are distinctive, and 9 are very specific to this project.

  • 0

    Common

    Most of the 23 edited versions we read keep these.

  • 10

    Distinctive

    This author's own choices. Worth a look.

  • 9

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If neither tool is available, or whoami fails because the user is not signed in, tell the user plainly: "HarborRank isn't connected, so I …

    line 16
  2. Distinctive:

    Do not stop there. Continue in fallback mode (below).

    line 27
  3. Very specific:

    If creditsRemaining will not cover the planned calls, give the user the estimate and ask before spending.

    line 35
  4. Very specific:

    If a tool fails for insufficient credits, stop making paid calls, tell the user, and finish with free tools and the data you already have.

    line 37
  5. Very specific:

    If the user asks to upgrade, change plan or buy credits, call get_upgrade_link (no credits) and give them the link.

    line 41
  6. Very specific:

    When whoami returns mode: "self-hosted", there are no plan gates.

    line 42
  7. Distinctive:

    Use this mode only when Step 0 finds no connection.

    line 46
  8. Distinctive:

    Read the business's website: name, address and phone (NAP) on every page, service and city pages, embedded map, LocalBusiness schema, and …

    line 50
  9. Distinctive:

    Use Maps screenshots or notes the user takes from their phone at different spots in the service area.

    line 52
  10. Distinctive:

    Read the sites of the businesses that appear for the main service-and-city queries, and note what they have that this business does not …

    line 53
  11. Distinctive:

    Write the manual Google Business Profile checklist (below) for the owner to work through.

    line 55
  12. Distinctive:

    Start with the label Web-evidence only: no HarborRank data.

    line 63
  13. Distinctive:

    If the business has several locations, run one location per pass.

    line 75
  14. Very specific:

    If the project's SEO folder has seo-context.md, read it first for the site, market, audience, competitors and goals.

    line 97
  15. Very specific:

    Call list_projects and pick the project.

    line 99
  16. Very specific:

    Check the website: read the page the profile links to and the service and city pages.

    line 106
  17. Distinctive:

    Never invent a number. Every rank, rating and review count comes from a tool result or a page you name.

    line 135
  18. Very specific:

    Do not call a business "not on Maps" until a deeper search (depth: 100) and a name search with search_local_businesses both miss it.

    line 137
  19. Distinctive:

    Do not recommend keyword stuffing in the business name, fake addresses, or review gating or buying.

    line 138

“Common” is measured: kept by at least 6 in 10 of the 23 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

HarborRank Local SEO

Goal

Show a local business where it appears in Google Maps for the services that bring in customers, from several points in the area it serves, and why the businesses above it win. End with a short, ordered action plan the owner can work through: profile fixes, reviews, website and location pages, and local keywords.

Step 0: Check connection

Before any other step, confirm the HarborRank MCP tools are loaded. Look for get_domain_overview or list_leads among your tools, including deferred tools you can load (the name may carry a prefix such as mcp__harborrank__). If they are there, call whoami: it uses no credits, confirms the user is signed in, and returns creditsRemaining for budgeting the run. Do not call a research tool to test the connection.

If neither tool is available, or whoami fails because the user is not signed in, tell the user plainly: "HarborRank isn't connected, so I can't pull live HarborRank data yet." Then tell them how to connect it:

  • Claude Code with the HarborRank plugin: run /mcp, choose harborrank, and sign in.
  • Claude Code without the plugin: run claude mcp add --transport http --scope user harborrank https://app.harborrank.com/mcp, then /mcp to sign in.
  • Claude on the web, desktop or Cowork: open Customize, then Connectors, search for HarborRank, choose Connect, and sign in. New accounts start with a 7-day free trial.
  • Cursor with the HarborRank plugin: open Cursor Settings, then MCP, and sign in to harborrank.
  • Gemini CLI with the HarborRank extension: run /mcp auth harborrank.
  • Other clients: add https://app.harborrank.com/mcp as a remote MCP server. Setup for each client is at https://harborrank.com/docs/mcp.

Tell them what happens when they connect: they sign in to HarborRank with Google or email and start a 7-day free trial. Then they come back to this conversation and say "connected", and you pick up the task where it stopped.

Do not stop there. Continue in fallback mode (below). If the user connects HarborRank mid-task, run Step 0 again and switch to the full workflow.

Plan limits

On hosted HarborRank, research tools spend credits. New accounts start with a 7-day free trial (1,000 research credits, one project); paid plans start at $29/month with 15,000 credits. Search Console, saved keywords, rank tracker reads, and site crawls use no credits. A keyword search costs about 50 credits and a domain overview about 80. Full backlinks, lead research (research_lead), and Lighthouse checks need a paid plan; on Free, the backlinks tools return a preview (totals and the top 3 referring domains, about 50 credits) with an upgrade link.

Every Maps check (get_local_serp_results, and each point of a run_local_grid scan), nearby-business search (search_local_businesses), Q&A pull (get_google_business_questions) and keyword call in this workflow charges credits; Search Console, the rank tracker and the site crawl do not. A grid of points times keywords adds up fast, so count the calls before running them. Local grid scans need a paid plan.

  • If creditsRemaining will not cover the planned calls, give the user the estimate and ask before spending. Use the free tools first.
  • If a tool replies that a feature "is included in paid plans", tell the user once which feature needs a paid plan and pass on the upgrade link from the reply, skip that tool for the rest of the run, and finish with the other evidence. Do not retry it.
  • If a tool fails for insufficient credits, stop making paid calls, tell the user, and finish with free tools and the data you already have. If whoami warns that credits are low, say so before a large run.
  • If a HarborRank tool says the free trial hasn't started, or that credits ran out, give the user the link from that reply exactly as written, as a clickable link, and wait for them to say they're done before calling HarborRank again. Don't switch to answering without HarborRank data unless they ask you to.
  • Two extras are included in Pro and Agency: local grids larger than 5x5 (a 7x7 run_local_grid) and more than 3 tracked competitors per rank tracker (add_rank_tracker_competitors). If a tool replies that something needs Pro or Agency, tell the user once what Pro adds, pass on the Pro link from the reply exactly as written, and carry on with what their plan includes (a 5x5 grid, the first 3 competitors). Do not retry it.
  • Mention Pro unprompted only when the task needs it: a whole-town map, or watching more than 3 competitors. Say it once per run, in one sentence, with the link from get_upgrade_link (plan: "pro").
  • If the user asks to upgrade, change plan or buy credits, call get_upgrade_link (no credits) and give them the link. They pay on HarborRank by card; never say the upgrade is done until whoami shows the new plan.
  • When whoami returns mode: "self-hosted", there are no plan gates.

Fallback mode (no HarborRank connection)

Use this mode only when Step 0 finds no connection. It works from web search, page reading, and files the user provides.

Can still do

  • Read the business's website: name, address and phone (NAP) on every page, service and city pages, embedded map, LocalBusiness schema, and whether the site matches the profile.
  • Compare that NAP with the business's listings that web search turns up (directories, social profiles, industry sites) and list each mismatch with its URL.
  • Use Maps screenshots or notes the user takes from their phone at different spots in the service area. Those are the user's own observations; report them with the place and time they were taken.
  • Read the sites of the businesses that appear for the main service-and-city queries, and note what they have that this business does not (service pages, city pages, reviews shown, trust signals).
  • Gather local keyword ideas from web search: related searches, autocomplete, and People Also Ask for each service plus city or "near me".
  • Write the manual Google Business Profile checklist (below) for the owner to work through.

Must not estimate

Traffic, search volume, keyword difficulty, CPC, keyword counts, rankings, backlink counts, Maps pack positions, and Q&A counts. Write unknown for each. A web search shows which pages appeared for a query when you searched, not their Google ranking: report it as "appeared in web search", never as a position. Ratings and review counts only as a page visibly shows them, reported as "shown on <source> at <time>"; never fill in a competitor's count you did not see.

Output

  • Start with the label Web-evidence only: no HarborRank data.
  • Name the source (URL or file) of every figure you report.
  • End, after any recommended next workflow, with one sentence that names the numbers this report is missing: "Connect HarborRank (start with a 7-day free trial) to check your Maps position from several points in your service area and pull competitors' ratings, reviews and categories." Do not add more sales copy than that.

Required inputs

  • projectId (from list_projects)
  • The business name as it appears on Google, and its website
  • The services that bring in the most customers (two to five)
  • Where it serves: a storefront address, or the towns or neighborhoods a service-area business covers
  • Optional: the competitors the owner already worries about

If the business has several locations, run one location per pass.

HarborRank MCP tools

  • get_local_serp_results: one Google Maps (searchType: "maps", default) or Local Finder SERP for one keyword from one point (near.latitude, near.longitude, optional near.zoom 4 to 18). Returns rank, title, domain, URL, main category, rating, reviews, phone, address, claimed status, placeId, cid and coordinates per listing. depth 1 to 100, default 20; device desktop or mobile. Charges credits per call.
  • run_local_grid: checks where the business shows in Google Maps for one keyword from a square of points around it (gridSize 3, 5 or 7; spacingMiles 0.5, 1, 2, 3 or 5) and returns the position at every point, the share of points in the top 3 and the average position. The first call creates the grid from businessName, latitude, longitude and placeId (and domain when known); later calls pass gridId so the points stay the same. Grids and scans are saved in the project, where the user sees them as a heatmap on the Local Grid page. Each point is one Maps search. Paid plans; 7x7 needs Pro or Agency.
  • get_local_grid: a saved grid and its scans, or the project's grids when no gridId is given. Free.
  • search_local_businesses: business listings near a coordinate within near.radiusKm, filtered by query (name text) and up to 10 categories; limit 1 to 50, default 20. Finds nearby competitors in the same category. It does not check rankings. Charges credits.
  • list_business_categories: the Google Business category slugs (e.g. dentist, roofing_contractor), filtered by query, sorted by how many listings use each.
  • get_google_business_questions: Google Business Profile questions and answers for one business keyword near a coordinate; depth 1 to 100, default 20. Charges credits. Run it only when Q&A evidence matters.
  • get_keyword_metrics, research_keywords: volume, keyword difficulty, CPC and intent for local service keywords. Markets are country-level, so the city has to be in the keyword ("plumber austin") to see city demand.
  • get_serp_results: live organic Google results for 1 to 10 keywords, to see which pages rank under the local pack. Charges credits.
  • get_ranked_keywords with resultTypes: ["local_pack", "organic"]: keywords where the business's domain already shows in the local pack or organic results.
  • get_search_console_performance: the site's queries with a city or "near me" in them, and clicks to location pages. Free.
  • get_rank_tracker: organic desktop and mobile positions for tracked keywords, if a tracker exists. It does not track the Maps pack. Free.
  • run_site_audit, get_audit_issues: crawl the website for problems on the service and location pages the profile links to. Free.
  • create_share_report: publish the finished work as a read-only page at a shareable link (see "Shareable report" below). Only after the user agrees.

There is no tool that edits a Google Business Profile, fetches review text, or audits citations. Those checks are manual (see step 7).

Workflow

If the project's SEO folder has seo-context.md, read it first for the site, market, audience, competitors and goals; otherwise ask only what this workflow needs.

  1. Call list_projects and pick the project. Confirm the business name, the services and the service area.
  2. Pick the keywords: for each service, the plain term ("dentist", "emergency plumber") and the term with the city. Google localizes the plain term to where the searcher stands, so it is the one that shows true Maps position. If Search Console is connected, call get_search_console_performance with dimensions: ["query"] and look for local queries already earning impressions. Keep three to five keywords.
  3. Find the business and its coordinates: call get_local_serp_results for the main keyword from the center of its town (use the address the user gave). Match the business by domain, placeId, cid or title, and note its latitude, longitude, main category and claimed status. If it is not in the top 20, raise depth to 100 before saying it does not show.
  4. Plan the grid. A 5x5 grid fits most businesses: 1 mile apart for a storefront in town, 2 or 3 miles for a service-area business. Use 3x3 for a quick check near the shop, and 7x7 (Pro and Agency) for a business that serves a whole city or several towns. State the call count (points times keywords) and ask before running more than 50 points.
  5. Run run_local_grid for the main keyword with the business's name, coordinates and placeId from step 3, then for each other keyword with the gridId it returned. Record the top-3 share, the average position and where the business drops out. If the grid is refused because the plan doesn't include it, sample the points by hand instead: the business location plus three or four points across the service area (the towns it serves, or about 3 to 8 km out in different directions), with get_local_serp_results for each keyword from each point, recording the rank at each point or "not in top <depth>".
  6. Compare with the leaders: take the businesses that hold the top three at most points. For each, record rating, reviews, main category, claimed status, website domain, and distance from the point. Use search_local_businesses with the business's category slug (check it with list_business_categories) to see how crowded the category is nearby. Call get_google_business_questions for the business and the top competitor only if the user asks about Q&A or the profile looks thin; an empty result means no questions were returned, not a fault.
  7. Write the manual profile checklist. These need the owner's Google Business Profile access or a look at the live listing: primary and secondary categories, services list, business description, hours and holiday hours, photos, posts, review count over the last 90 days and owner replies, the website link and which page it points to, verification status, and NAP matching the website and main directories. Mark each item "to check" unless the owner confirms it.
  8. Check the website: read the page the profile links to and the service and city pages. If the site has more than a handful of pages, call run_site_audit, then get_audit_issues with severity: "critical", and keep only issues on those pages.
  9. Local keywords: call get_keyword_metrics for the service-plus-city terms and the services the leaders' categories suggest. Use research_keywords only for a new service area. Flag terms with no matching page on the site.
  10. Rank the actions. Things the business controls and the leaders do better come first: wrong or missing primary category, profile not claimed, NAP mismatches, website link pointing to the wrong page. Then the review gap, then missing service or city pages, then everything else. Proximity cannot be changed; say where distance alone explains a gap, so the owner does not chase it.

Output format

Start with:

  • Verdict: one or two sentences, for example "Shows in the top 3 near the shop for 'dentist', drops out 5 km north where two practices with three times the reviews take the pack."
  • Grid: for each keyword, the top-3 share and average position, and that the heatmap is saved on the project's Local Grid page (when run_local_grid ran).
  • Top 3 actions, in order.

Then include:

KeywordPointRankTop 3 at that point
BusinessRank (most points)RatingReviewsMain categoryClaimedWebsite

Then the profile checklist (checked or "to check"), the local keywords with volume and whether a page targets each, and the full action plan with effort (quick, moderate, or project). Close with what was not checked (points not sampled, profile items only the owner can see).

  • Next workflow: end with one recommended next workflow, the reason for it, and the input it starts from. Default: seo-audit on the business's website, because the page the profile links to and the service and city pages carry local rankings too. If one competitor holds the pack at most points and has a stronger site, recommend competitor-analysis on its domain instead.
  • Check back: end with one dated follow-up: the date (today plus 28 days, written out, for example "Monday, November 9") and the exact question to ask then: "Where does <business> show in Google Maps now from the same points?" (re-run run_local_grid with the same gridId, so the points match) Say in one line why it needs that wait: profile, category and review changes take weeks to move Maps rankings, and checking the same points with the same keywords keeps the numbers comparable. Add it to the Follow-ups list in the SEO folder's README.md (create the list if it is missing) so the next session finds it. One follow-up only; don't add reminders or repeat it. If scheduled tasks are available (Cowork and the Claude apps on paid plans), offer once to make this a weekly scheduled task instead, named for the site, so the check runs by itself; the user reviews and confirms the schedule.
  • Where the output goes: the report as local/<business-slug>-<YYYY-MM-DD>.md, with the points-by-keyword ranks (including each point's coordinates, so the re-check uses the same ones) as local/<business-slug>-<YYYY-MM-DD>.csv. Save it in the project's SEO folder (see seo-project-setup); if there is none, ask once whether to create one or where to save instead. If the user prefers a doc or a sheet and a docs or spreadsheet tool is available, put reports in a doc and tables in a sheet instead. Tell the user where it was saved.
  • Shareable report: once the work is done, offer one time to publish it as a shareable report with create_share_report: a read-only page at a link the user can send to a client, a boss or a teammate, no sign-in needed. Write it from this output: findings first, then next steps, then the supporting table. Publish only after the user says yes, and leave out their Search Console and Google Analytics numbers unless they agree to share them. Give them the link; delete_share_report removes it.

Guardrails

  • Never invent a number. Every rank, rating and review count comes from a tool result or a page you name.
  • A Maps rank is true for one keyword from one point at one time. Never report it as the business's rank for the whole city.
  • Do not call a business "not on Maps" until a deeper search (depth: 100) and a name search with search_local_businesses both miss it.
  • Do not recommend keyword stuffing in the business name, fake addresses, or review gating or buying. They break Google's guidelines and can get the profile suspended.
  • Recommend changes, never make them. Ask before any write action.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.