agentleFS
gitTerebigitTerebi/seo-content-machine-plugin/skills/local-seo/SKILL.md

local-seo

Skill0 starsChanged 26 days agoMITView on GitHub

Plan and write local service pages for one business with SEO Content Machine. Pulls competitor Google Maps listings, picks services from their review tags, plans a hub page per service with a page per town under it in an SEO Workspace, then has SCM research, write and review each page. Use when asked for local SEO pages, service area pages, city pages, or "every service in every city" for a local business.

23 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ecommerce-seo, seo-project-setup and 10 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

  • JwuthriSkill

    seo-project-setup

    Set up a durable local SEO workspace with project context, notes, goals, positioning, preferences, MCP checks, and Search Console data intake.

    Also in 5 projects that use this

  • JwuthriSkill

    link-prospecting

    Find link prospects, discover contact paths, and draft outreach from SERPs and backlink signals.

    Also in 5 projects that use this

  • akii-technologies-ltdSkill

    keyword-clustering

    Cluster and organize keywords into topical groups for SEO. Use when the user asks to "cluster keywords", "group keywords", "organize keywords", "keyword mapping", "topic clusters", "keyword grouping", "build a content plan", "pillar pages", "topical authority", "semantic clustering", or pastes a list of keywords.

    Also in 6 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

  • MicrosoftSkill

    competitive-landscape

    Use when a branch manager asks something like \"Who are we up against in each metro\"

    Also in 5 projects that use this

  • +1 more from Jwuthri

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 1 is distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 21 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask the user for these, and wait for the answers:

    line 14
  2. Very specific:

    Call local_listings_create with one line such as "plumbers in austin tx", resultsLimit 15, reviewCount 3 and uniqueDomain true.

    line 24
  3. Very specific:

    Call task_results. Its rows point to a CSV file.

    line 26
  4. Very specific:

    Create the Workspace with seo_workspace_create.

    line 33
  5. Very specific:

    Put them on the site plan with workspace_write (sitePlan, insertMany): hubs at the top level, and each town page with parentPageId set to …

    line 39
  6. Very specific:

    Read the drafts with workspace_query on documents, with fields that include body, because the page text is left out otherwise.

    line 45

“Common” is measured: kept by at least 6 in 10 of the 21 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

Local SEO pages

You plan a local business's service pages and hand them to SEO Content Machine (SCM) to write. SCM researches each page, writes it, has fresh reviewers check its facts, and saves it as a draft in an SEO Workspace. The user reviews and publishes from the app. Read the scm skill first if you have not used the SCM tools in this session.

The pages are only as good as two inputs: the business facts you put in the brief, and the city facts SCM can find. Both steps below matter more than the page count.

1. Get the business facts

Ask the user for these, and wait for the answers:

  • Business name, website, main city, and the towns it serves.
  • The services it offers.
  • How it works: response time, pricing approach, free estimates, warranty, who pulls permits, licences.

The writer may claim only what the brief says about the business, so a missing fact becomes a gap the reviewers mark down. Never invent one.

2. See what competitors are known for

  1. Call local_listings_create with one line such as "plumbers in austin tx", resultsLimit 15, reviewCount 3 and uniqueDomain true. Then task_run it.
  2. Poll task_list with the task's name every 30 seconds until its status is done. A run takes about a minute.
  3. Call task_results. Its rows point to a CSV file. Read that file with your own file tool.
  4. Group the reviewTags by job, then count how many places each job appears at. Tags name one job in many ways ("ev charger", "electric car charger installation", "charging"), so an exact count undercounts it. Drop tags that name no job, such as "punctuality", "fair pricing" or "clean".

Show the user the jobs and their counts next to their services, and agree the service list. Leave out a service they do not offer, however often it appears. A service they offer with no matching tag can stay, because customers rarely tag routine work.

3. Plan the Workspace

  1. Create the Workspace with seo_workspace_create.
  2. Fill the brief with workspace_write (brief, updateOne): businessName, targetSite, geo with the main city and the towns, articleGoogleCountry such as "United States:English", and notes with every fact from step 1. Always set articleGoogleCountry, because a new Workspace starts with the user's saved region, which may be another country, and the pages are researched and written for that region.
  3. Show the user the plan as a table of services by towns, with the page count, and get a yes before you write any pages.
  4. Insert the pages with workspace_write (pages, insertMany), with intent "local" and status "planned":
    • One hub per service, topic "<service> <main city>", templateType "Local SEO Hub".
    • One page per service and town, topic "<service> <town> <state>", templateType "Local SEO Service".
  5. Put them on the site plan with workspace_write (sitePlan, insertMany): hubs at the top level, and each town page with parentPageId set to its service's hub.

4. Write a first batch

  1. Pick one hub and two of its town pages. Pass their page ids to workspace_create_pages. SCM writes them with the AI model and effort the user last picked in the app.
  2. Poll task_list with seo_workspace_id set to the Workspace id every minute until the pipeline's status is done. A batch of three takes about 5 to 10 minutes.
  3. Read the drafts with workspace_query on documents, with fields that include body, because the page text is left out otherwise. Read the log once with task_get and include_logs.
  4. For each page, find two log lines. Review scores: gives the last reviewer's scores out of 10. Review done with N rounds gives the writer's last reply, with any blocking fails left open.

Tell the user what each page found about its town, and ask them to open the drafts in the app. When a page has blocking fails left open, it is still saved as a draft, so list those claims for the user to check or remove before publishing.

5. Write the rest

Hand the remaining pages over in batches of 8 to 10. Each page links to its hub and its sibling towns by their site plan addresses, so the order does not matter.

Each page uses roughly 75k to 300k tokens. On a subscription plan, spread a large site over several days.

When a page comes out thin

Some towns publish little, hide their fees and rules in collapsed page sections and old reports, or block SCM's browser, so their pages score lower whatever the effort. Tell the user which towns these are. They can add what they know about the town to the brief, or skip the town.

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.