Agent skill

Local Content Strategy

by garrettjsmith in garrettjsmith/localseoskills

Build a complete local content strategy from keyword research output.

MITAuto-check passedWriting & Content

Install Local Content Strategy

skills CLI
$ npx skills add garrettjsmith/localseoskills --skill local-content-strategy -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install garrettjsmith/localseoskills local-content-strategy --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/garrettjsmith/localseoskills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/local-content-strategy .claude/skills/local-content-strategy && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
local-content-strategy
GitHub stars
120
Token cost
~2.8k tokens
SKILL.md length
1,190 words
Files
1
Skills in repo
38
Repo updated
First seen
Licence
MIT

At a glance

Build a complete local content strategy from keyword research output.

  • Works in 6 steps: Concept Clustering → Content Vehicle Assignment → Coverage Gap Analysis → …
  • The user has completed keyword research and needs to organize keywords into concept clusters
  • SKILL.md covers Purpose, Position in the Workflow, Core Principle: Keywords Are… and Process, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Local Content Strategy is an agent skill from garrettjsmith/localseoskills. Build a complete local content strategy from keyword research output. Use this skill when the user has completed keyword research and needs to organize keywords into concept clusters, assign each cluster to the right content vehicle (location page, GBP service, blog post, FAQ, near-me GBP signal), select geogrid tracking keywords, confirm GBP category and service additions, and design the internal linking architecture. Also trigger when the user asks "what content should I build", "how do I organize these…

Its SKILL.md is about 2.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Writing & Content, covering Content strategy, Keyword research and On-page SEO. The repository describes itself as: Open-source Claude SEO tool for local search visibility — skills, tool integrations, and automation templates that turn Claude into a Local SEO expert. The licence is MIT.

When your agent uses it

  • The user has completed keyword research and needs to organize keywords into concept clusters
  • Assign each cluster to the right content vehicle (location page
  • Near-me GBP signal)
  • Select geogrid tracking keywords

Example prompts

  • “what content should I build”
  • “how do I organize these keywords”
  • “what pages do I need”
  • “/local-content-strategy”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Concept Clustering
  2. Content Vehicle Assignment
  3. Coverage Gap Analysis
  4. Geogrid Tracking Keyword Selection
  5. GBP Confirmation
  6. Internal Linking Architecture

What it can do on your machine

Read from SKILL.md and the folder at commit 405ce20. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Local Content Strategy loads about 2.8k tokens when it runs. Until then it costs about 196 tokens; SKILL.md has 1,190 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~196
When it runs · the whole SKILL.md, loaded when a task matches
~2.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from garrettjsmith/localseoskills at commit 405ce20, republished under its MIT licence (© garrettjsmith). 1,190 words, ~2,773 tokens.

Download SKILL.mdSave it as .claude/skills/local-content-strategy/SKILL.md (or your agent's skills folder).
name
local-content-strategy
description
Build a complete local content strategy from keyword research output. Use this skill when the user has completed keyword research and needs to organize keywords into concept clusters, assign each cluster to the right content vehicle (location page, GBP service, blog post, FAQ, near-me GBP signal), select geogrid tracking keywords, confirm GBP category and service additions, and design the internal linking architecture. Also trigger when the user asks "what content should I build", "how do I organize these keywords", "what pages do I need", "what should I track on geogrids", or provides a keyword list and asks what to do with it. This skill bridges keyword research and content brief production — it is the strategy layer between research and execution.
metadata.version
1.0.0
metadata.author
Garrett Smith

Local Content Strategy Skill

Purpose

Transform a keyword list into a complete local content architecture — organized concept clusters, content vehicle assignments, production priority order, geogrid tracking keyword selection, GBP optimization confirmations, and internal linking structure. This skill turns research into a plan.

Position in the Workflow

local-keyword-research → [THIS SKILL] → local-content-briefs → local-landing-pages

Input: keyword list (from local-keyword-research or provided directly) Output: complete content strategy document ready to brief and execute

Core Principle: Keywords Are the Input, Concepts Are What You Build

A keyword list tells you what people are searching for. A content strategy tells you what to build, where to build it, how deeply to cover each topic, and in what order. The two most common mistakes practitioners make with a keyword list: (1) trying to target each keyword individually instead of grouping related terms into concept clusters, and (2) defaulting to "write a page for this" when many keywords are won through GBP signals and don't need a page at all.

This skill does the organizing work that usually happens in a spreadsheet over several hours — automatically, with reasoning attached to every decision.


Process

Step 1: Concept Clustering

Group the keyword list into concept clusters. A concept cluster is a set of keywords that share the same underlying topic and user intent — they would all be served by the same piece of content or the same GBP optimization.

Clustering rules:

  • Geographic variants of the same term belong in the same cluster ("plumber Phoenix" + "plumber Scottsdale" + "plumber near me" are all the same concept at different geographic specificity levels)
  • Service variants belong together ("drain cleaning" + "clogged drain" + "drain backup" = one cluster)
  • A cluster should have one primary concept label — the plain-language name of the topic, not a keyword string
  • Clusters should be mutually exclusive — if a keyword could belong to two clusters, assign it to the one where it represents the core intent

Output per cluster:

  • Cluster name (plain language, not a keyword)
  • Primary keyword (highest volume, most representative)
  • Supporting keywords (variants, long-tail, geo-modified versions)
  • Search volume range across the cluster
  • User intent type (transactional, informational, navigational, near-me)
  • Competitive level (high/medium/low based on available data)
Step 2: Content Vehicle Assignment

For each concept cluster, assign the right content vehicle. This is the most consequential decision in the strategy — the wrong vehicle means the content either doesn't rank or doesn't convert.

Content vehicle decision logic:

Location page — assign when:

  • Cluster has clear transactional local intent
  • Primary keyword includes a city, neighborhood, or service area modifier
  • Search volume justifies a dedicated page (generally 50+ monthly searches)
  • The concept is specific enough to write genuinely unique content for each location

GBP service entry — assign when:

  • Cluster represents a specific service the business offers
  • Keyword has local service intent but lower volume (under 50 MSV)
  • The concept is a service variant rather than a primary service (e.g., "tankless water heater installation" vs. "water heater repair")
  • A dedicated page would be thin — better as a GBP service that expands category coverage

GBP category — assign when:

  • Cluster maps to a GBP secondary category the business should claim
  • Claiming the category expands query eligibility for the entire cluster
  • Note: this is a GBP action, not a content action

Blog post / FAQ content — assign when:

  • Cluster has informational intent (how-to, what-is, comparison, cost questions)
  • User is in the research phase before making a local service decision
  • Content could be cited in AI Overviews or answer PAA questions
  • No transactional local intent — this is awareness/consideration stage content

Near-me / GBP signal only — assign when:

  • Cluster contains near-me variants that can't be targeted with page content
  • These keywords are won through GBP prominence, proximity, and completeness
  • No content action needed — the GBP optimization work covers this cluster
  • Note this explicitly so clients understand why there's no page for these terms

Pillar page — assign when:

  • Cluster represents a broad primary topic the business should own completely
  • Volume and competition justify comprehensive long-form treatment
  • Multiple supporting clusters exist that would link to this as a hub
  • Typically the primary service category for the business

No action required — assign when:

  • Volume is negligible (under 10 MSV) and competition is low for a reason
  • Cluster represents a service the business doesn't offer
  • Keyword is navigational for a competitor
Show full SKILL.md (492 more words)Show less
Step 3: Coverage Gap Analysis

Compare the content vehicle assignments against the business's current content inventory (if provided) or against what would be needed for complete coverage.

Identify:

  • Missing coverage — concept clusters with no current content vehicle
  • Thin coverage — clusters with a page that doesn't fully cover the concept
  • Duplicate coverage — multiple pages targeting the same cluster (cannibalization risk)
  • Misassigned coverage — content in the wrong vehicle (a full page for a term that should be GBP-only, or vice versa)
Step 4: Geogrid Tracking Keyword Selection

From the full concept map, select 3–5 keywords for geogrid tracking. These are not necessarily the highest-volume keywords — they are the keywords that best represent the business's concept coverage and for which geographic ranking variation is most meaningful.

Geogrid keyword selection criteria:

  1. Clear local pack intent (not informational, not navigational)
  2. One keyword per distinct concept cluster (don't track five plumbing variants — pick one per concept)
  3. Competitive enough that current position matters (top 3 vs. position 8 changes lead volume significantly)
  4. Representative of the business's primary revenue services (track what makes the business money)
  5. Distinct geographic coverage (if the business has multiple service areas, select keywords that test coverage in each)

Output: ranked geogrid tracking list with reasoning per keyword selection.

Step 5: GBP Confirmation

Confirm the GBP actions that fall out of the concept map:

  • Secondary categories to add (each should correspond to a concept cluster)
  • Services to add to the GBP service menu (each should be a cluster with a GBP service assignment)
  • Attributes to claim (which attributes support which concept clusters)
  • Description keywords (which concept clusters should appear naturally in the business description)
Step 6: Internal Linking Architecture

Design the internal link structure that connects the content vehicles into a coherent topic cluster:

  • Hub page — the pillar page or primary location page that all supporting pages link to
  • Spoke pages — location pages and blog posts that link to the hub and to each other where topically relevant
  • GBP-to-website links — which pages should receive the GBP website link (usually the primary location page or homepage depending on the query)
  • Anchor text guidance — what concept-based anchor text to use for each internal link

Output Format

# Local Content Strategy: [Business Name] — [Market]

## Concept Clusters (N total)

### Cluster 1: [Concept Name]
Primary keyword: [keyword] | MSV: [X]
Supporting keywords: [list]
Intent: [Transactional / Informational / Near-me]
Competition: [High / Medium / Low]
Content vehicle: [assignment]
Reasoning: [1-2 sentences explaining the assignment]

[repeat for all clusters]

---

## Content Vehicle Summary

### Location Pages to Build (N)
| Page | Primary Concept | Primary Keyword | Priority |
|------|----------------|-----------------|----------|
| [page slug] | [concept] | [keyword] | P1/P2/P3 |

### GBP Actions
Categories to add: [list]
Services to add: [list]
Attributes to confirm: [list]

### Blog / FAQ Content to Create (N)
| Topic | Primary Concept | Format | Priority |
|-------|----------------|--------|----------|

### Near-Me Clusters (GBP signal only, no content needed)
[list]

---

## Geogrid Tracking Keywords

1. [keyword] — reasoning: [why this represents the concept well for geogrid]
2. [keyword] — reasoning:
3. [keyword] — reasoning:
[4-5 total]

---

## Coverage Gaps (Priority Order)

1. [Gap description] — [impact on visibility if unaddressed]
2. [Gap description]
[continues]

---

## Internal Linking Architecture

Hub: [page] — receives links from all spokes
Spokes: [list of pages with their hub connection]
Cross-links: [relevant spoke-to-spoke connections]

---

## Production Priority Order

Phase 1 (immediate — GBP actions, no content needed):
[GBP changes that can be made today]

Phase 2 (first 30 days — high-impact content):
[Location pages and GBP services for primary concept clusters]

Phase 3 (30-90 days — supporting content):
[Blog/FAQ content, secondary location pages]

Phase 4 (ongoing):
[Long-tail content, content refresh, gap filling]

Usage Notes

When keyword list is not provided: Run local-keyword-research first, then pass the output directly into this skill. The two skills chain naturally.

When business context is limited: Ask for: business type, primary services, locations served, and one or two competitors currently outranking them. This context improves cluster assignments significantly.

When client has existing content: Request a URL list or sitemap. The skill will audit current coverage against the concept map and identify gaps, duplicates, and misassigned pages before recommending new content builds.

Connection to local-content-briefs: This skill produces the strategy. The local-content-briefs skill takes each content vehicle assignment from this output and produces a full semantic content brief. The two skills are designed to chain: run local-content-strategy first, then run local-content-briefs for each piece identified.

© garrettjsmith, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/local-content-strategy of garrettjsmith/localseoskills.

Open the folder on GitHubat commit 405ce20

Compare with similar skills

Local Content Strategy next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Local Content Strategy compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Local Content Strategy this skillgarrettjsmith/localseoskills120—~2.8kAutomated safety check: PassMIT
Content Brief Factorygooseworks-ai/goose-skills1.2k1 repos~3.1kAutomated safety check: PassMIT
SEO Keyword ClusteringAgriciDaniel/claude-seo19k2 repos~3.3kAutomated safety check: PassMIT
SEO Content Brief GeneratorAgriciDaniel/claude-seo19k2 repos~2.6kAutomated safety check: PassMIT
SEO Keyword Clusterseranking/seo-skills160—~2.5kAutomated safety check: PassMIT
Content Brief Authoringrampstackco/claude-skills941—~5.6kAutomated safety check: PassMIT

Similar skills

  • Content Brief Factory

    gooseworks-ai/goose-skills

    Generate detailed, differentiated content briefs at scale. An agent skill from gooseworks-ai/goose-skills.

    1.2k GitHub starsUsed in 1 repo~3.1k tokens
    Writing & ContentAuto-check passed
  • SEO Keyword Clustering

    AgriciDaniel/claude-seo

    Clusters keywords by how much their search results overlap and designs a hub-and-spoke content plan with an internal link matrix and an interactive cluster map.

    19k GitHub starsUsed in 2 repos~3.3k tokens
    Marketing & SEOAuto-check passed
  • SEO Content Brief Generator

    AgriciDaniel/claude-seo

    Builds research-backed SEO content briefs with competitor scoring, per-section word counts and page-type templates, for new pages or improving existing ones.

    19k GitHub starsUsed in 2 repos~2.6k tokens
    Marketing & SEOAuto-check passed
  • SEO Keyword Cluster

    seranking/seo-skills

    Build a content cluster plan from seed keywords — intent-grouped clusters, pillar+spokes architecture with H1/H2 suggestions per spoke, prioritised build order, and an internal-linking map.

    160 GitHub stars~2.5k tokensUpdated 3 mo ago
    Marketing & SEOAuto-check passed
  • Content Brief Authoring

    rampstackco/claude-skills

    How to author a content brief that actually guides a writer (human or AI) to produce a piece that ranks, converts, or both.

    941 GitHub stars~5.6k tokensUpdated 2 days ago
    Marketing & SEOAuto-check passed
  • Ink Cluster

    jeremylongshore/tons-of-skills-marketplace

    Topic cluster architecture builder — takes a core topic and maps the full cluster with 1 pillar page, 6-10 supporting posts, internal linking map, keyword targets, and estimated monthly search…

    2.8k GitHub stars~1.3k tokensUpdated today
    Marketing & SEOAuto-check: notes

More from garrettjsmith/localseoskills

All 38 skills in this repo
  • Gbp API Automation

    garrettjsmith/localseoskills

    When the user wants to programmatically manage Google Business Profiles at scale via API, automate GBP updates, build GBP management tools, or integrate GBP data into their systems.

    120 GitHub stars~2.1k tokensUpdated 1 mo ago
    Auto-check passed
  • Gbp Posts

    garrettjsmith/localseoskills

    When the user wants to create, schedule, or optimize Google Business Profile posts.

    120 GitHub stars~1.6k tokensUpdated 1 mo ago
    Auto-check passed
  • Local Content Briefs

    garrettjsmith/localseoskills

    Generate complete semantic content briefs for local SEO content — location pages, service pages, blog posts, FAQ content, and pillar pages.

    120 GitHub stars~3.5k tokensUpdated 1 mo ago
    Auto-check passed
  • Brief

    garrettjsmith/localseoskills

    Manages persistent work state (briefs) for local SEO engagements.

    120 GitHub stars~1.9k tokensUpdated 1 mo ago
    Auto-check: warnings
  • Local Falcon Tool

    garrettjsmith/localseoskills

    When the user wants to run a geogrid scan, check existing scan reports, track ranking trends over time, monitor GBP changes via Falcon Guard, or analyze reviews.

    120 GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed
  • Local Keyword Research

    garrettjsmith/localseoskills

    When the user wants to research keywords for a local business, find local search opportunities, build a keyword map for location pages, or understand local search intent.

    120 GitHub stars~4.7k tokensUpdated 1 mo ago
    Auto-check passed

Questions about Local Content Strategy

What does Local Content Strategy do?

Build a complete local content strategy from keyword research output. Local Content Strategy is an agent skill from garrettjsmith/localseoskills. Build a complete local content strategy from keyword research output.

When should I use Local Content Strategy?

Local Content Strategy fits situations like: the user has completed keyword research and needs to organize keywords into concept clusters; assign each cluster to the right content vehicle (location page; near-me GBP signal); select geogrid tracking keywords.

How do I install Local Content Strategy in Claude Code?

Run `npx skills add garrettjsmith/localseoskills --skill local-content-strategy -a claude-code`. Or copy the skill folder (skills/local-content-strategy in garrettjsmith/localseoskills) into .claude/skills/local-content-strategy in your project. Claude Code loads it when a task matches its description.

How do I install Local Content Strategy in Codex?

Run `npx skills add garrettjsmith/localseoskills --skill local-content-strategy -a codex`. Or copy the skill folder (skills/local-content-strategy in garrettjsmith/localseoskills) into .agents/skills/local-content-strategy in your project. Codex loads it when a task matches its description.

Can I use Local Content Strategy in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add garrettjsmith/localseoskills --skill local-content-strategy -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/local-content-strategy, .gemini/skills/local-content-strategy, .github/skills/local-content-strategy and .opencode/skills/local-content-strategy in your project.

What does Local Content Strategy need to run?

SKILL.md names no scripts, command-line tools or credentials: Local Content Strategy is instructions for the agent only.

Does Local Content Strategy access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Local Content Strategy safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Local Content Strategy use?

Local Content Strategy is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Local Content Strategy use?

About 2.8k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Local Content Strategy?

Skills that share tags, products or a category with Local Content Strategy: Content Brief Factory (gooseworks-ai/goose-skills, 1.2k stars), SEO Keyword Clustering (AgriciDaniel/claude-seo, 19k stars), SEO Content Brief Generator (AgriciDaniel/claude-seo, 19k stars) and SEO Keyword Cluster (seranking/seo-skills, 160 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Local Content Strategy?

garrettjsmith (a GitHub user) maintains it in garrettjsmith/localseoskills, which has 120 GitHub stars. The repository holds 38 skills in this directory. The repository was last updated on August 15, 2026.

Source: garrettjsmith/localseoskills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.