Citation Source Gap Finder
irinabuht12-oss/marketing-skills
Find the exact pages AI assistants cite when answering questions in your category, and identify which ones you can get into.
When the user wants citation gap analysis, managed citation building, review generation campaigns, or local rank tracking.
$ npx skills add garrettjsmith/localseoskills --skill whitespark-tool -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install garrettjsmith/localseoskills whitespark-tool --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/garrettjsmith/localseoskills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/whitespark-tool .claude/skills/whitespark-tool && rm -rf skills-srcUse ~/.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/
Install the "whitespark-tool" agent skill from https://github.com/garrettjsmith/localseoskills/tree/main/skills/whitespark-tool into .claude/skills/whitespark-tool/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "whitespark-tool", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/garrettjsmith/localseoskills/tree/main/skills/whitespark-toolType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add garrettjsmith/localseoskills --skill whitespark-tool -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install garrettjsmith/localseoskills whitespark-tool --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/garrettjsmith/localseoskills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/whitespark-tool .agents/skills/whitespark-tool && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "whitespark-tool" agent skill from https://github.com/garrettjsmith/localseoskills/tree/main/skills/whitespark-tool into .agents/skills/whitespark-tool/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "whitespark-tool", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add garrettjsmith/localseoskills --skill whitespark-tool -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install garrettjsmith/localseoskills whitespark-tool --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/garrettjsmith/localseoskills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/whitespark-tool .cursor/skills/whitespark-tool && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "whitespark-tool" agent skill from https://github.com/garrettjsmith/localseoskills/tree/main/skills/whitespark-tool into .cursor/skills/whitespark-tool/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "whitespark-tool", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/garrettjsmith/localseoskills.git --path skills/whitespark-tool--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add garrettjsmith/localseoskills --skill whitespark-tool -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install garrettjsmith/localseoskills whitespark-tool --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/garrettjsmith/localseoskills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/whitespark-tool .gemini/skills/whitespark-tool && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "whitespark-tool" agent skill from https://github.com/garrettjsmith/localseoskills/tree/main/skills/whitespark-tool into .gemini/skills/whitespark-tool/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "whitespark-tool", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install garrettjsmith/localseoskills whitespark-toolInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add garrettjsmith/localseoskills --skill whitespark-tool -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/garrettjsmith/localseoskills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/whitespark-tool .github/skills/whitespark-tool && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "whitespark-tool" agent skill from https://github.com/garrettjsmith/localseoskills/tree/main/skills/whitespark-tool into .github/skills/whitespark-tool/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "whitespark-tool", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add garrettjsmith/localseoskills --skill whitespark-tool -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install garrettjsmith/localseoskills whitespark-tool --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/garrettjsmith/localseoskills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/whitespark-tool .opencode/skills/whitespark-tool && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "whitespark-tool" agent skill from https://github.com/garrettjsmith/localseoskills/tree/main/skills/whitespark-tool into .opencode/skills/whitespark-tool/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "whitespark-tool", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
whitespark-toolWhen the user wants citation gap analysis, managed citation building, review generation campaigns, or local rank tracking.
Whitespark Tool is an agent skill from garrettjsmith/localseoskills. When the user wants citation gap analysis, managed citation building, review generation campaigns, or local rank tracking. Trigger on "Whitespark," "citation finder," "where are my competitors listed," "citation gap," "build citations," "review generation tool," or "get more reviews." Note that Whitespark does NOT have an MCP server — it's dashboard-driven with limited API.
Its SKILL.md is about 2.6k 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 Marketing & SEO, covering Citation management and Local SEO. It works with Model Context Protocol. 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.
3 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 405ce20. It shows what the files ask for, not the result of running them.
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.
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.
Links to these hosts (documentation or services it may open):
lrg.whitespark.cawhitespark-api.apidocumentation.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Whitespark Tool loads about 2.6k tokens when it runs. Until then it costs about 98 tokens; SKILL.md has 1,299 words of instructions outside code blocks.
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.
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.
The full file from garrettjsmith/localseoskills at commit 405ce20, republished under its MIT licence (© garrettjsmith). 1,299 words, ~2,586 tokens.
.claude/skills/whitespark-tool/SKILL.md (or your agent's skills folder).Note: Local SEO Data (
localseodata-tool) now covers citation audits viacitation_audit. Use Local SEO Data as default for citation data. Whitespark remains a preferred tool for citation building, rank tracking, and review generation campaigns (Reputation Builder).
Whitespark does NOT have an MCP server. Two of its products now expose REST APIs — the Local Rank Tracker and Local Ranking Grids (geogrids), both in beta — so an agent can pull ranking and grid data directly for those. Its citation products have no API and remain dashboard/managed, so for citations the agent's role is to guide what to do in Whitespark and interpret data the user provides. See the Whitespark APIs section below.
| You Need | Use Whitespark | Use Instead |
|---|---|---|
| Citation gap analysis (competitor vs you) | ✅ Local Citation Finder | BrightLocal (also does this, has MCP) |
| Managed citation building (done-for-you) | ✅ Best quality service | BrightLocal (also offers this) |
| Review generation campaigns (email/SMS) | ✅ Reputation Builder | — |
| Review monitoring | ✅ | BrightLocal (has MCP, may be better for agent access) |
| Local rank tracking | ✅ | Local SEO Data, Local Falcon (geogrid is superior for local) |
| Citation accuracy audit | ⚠️ Can do it | BrightLocal (better for NAP accuracy scoring) |
| Keyword research | ❌ | Local SEO Data, Semrush, Ahrefs |
| Backlink analysis | ❌ | Local SEO Data, Ahrefs |
| Technical audit | ❌ | Screaming Frog |
| Geogrid rankings | ✅ | Local SEO Data, Local Falcon |
These two overlap significantly. Here's when to use which:
| Feature | Whitespark | BrightLocal |
|---|---|---|
| Citation building quality | ✅ Higher quality (manual review) | Good but more automated |
| Citation gap finder | ✅ More thorough | ✅ Also good |
| NAP accuracy scoring | Basic | ✅ Better scoring system |
| MCP server available | ❌ No | ✅ Yes |
| Review generation | ✅ Reputation Builder | ✅ Also has this |
| White-label reports | Basic | ✅ Better reporting |
| Industry reputation | ✅ Citation specialists | ✅ All-in-one local SEO |
| Pricing | Per-service | Subscription |
Recommendation: If MCP connectivity matters (agent can pull data directly), use BrightLocal. If citation building quality is the priority and the user is willing to use the dashboard, Whitespark's managed service is excellent.
When: User wants to find directories where competitors are listed but they aren't.
What to do in Whitespark:
What the agent can do:
Citation priority framework:
When: Citation gaps identified and user wants help building them.
What Whitespark does:
What to tell the user:
When: User needs to systematically generate more Google reviews.
How Reputation Builder works:
What the agent should guide:
Review velocity targets by business type:
| Business Type | Monthly Review Target | Rationale |
|---|---|---|
| Restaurant | 15-30 | High transaction volume |
| Medical practice | 8-15 | Moderate patient volume |
| Home services | 5-10 | Lower transaction frequency |
| Legal | 3-5 | Fewer clients, harder to ask |
| B2B services | 2-4 | Low volume, high value |
When: User uses Whitespark's rank tracker.
Whitespark's rank tracker is point-based (single location), not geogrid.
What the agent should know:
Two Whitespark products expose REST APIs. Both are beta — endpoints and response shapes may change — and neither is an MCP server, so calls are made directly or via a custom integration, not through an agent connector. There is no citation API; citation building and audits stay in the dashboard/managed service.
For citation data, LocalSEOData (citation_audit) is the default. For geogrid depth beyond what the grids API exposes, LocalSEOData (geogrid_scan) or Local Falcon give point-level data.
Reference: https://lrg.whitespark.ca/api-docs
Built for reporting integration — pulling grid summaries and embedding grid visuals into reports/dashboards. It does not expose the underlying grid data points.
Auth: Bearer token in the Authorization header. Generate the token in-app under profile dropdown → API Access.
Endpoints:
GET /grids — paginated list of your ranking grids with summary metrics: visibility score, average rank, and review score. Pagination via page (default 1) and per_page (default 50, max 100). Response is data plus a meta object (current_page, last_page, per_page, total).GET /grid/{grid_id}/download-screenshot/{mode} — returns the most recent screenshot for a grid; mode is with-metrics or without-metrics. grid_id is the UUID from the grid's URL. Returns 404 if no screenshot exists. Embeddable via <img>. Enable Automatic screenshots on the API access page so every completed scan refreshes this URL.Not available via the API (dashboard only): individual data points within a grid, competitor data points, creating grids, and modifying grids or run schedules.
Use it for: embedding an always-current geogrid image and pulling visibility score / average rank / review score into a monthly report or portfolio rollup. Don't reach for it when you need per-point rankings or competitor grids — use geogrid_scan (LocalSEOData) or Local Falcon.
Reference: https://whitespark-api.apidocumentation.com/rank-tracker-api-reference
Beta (v1.0.0, OpenAPI 3.0.0), with separate live and test base URLs. Auth: API key passed as a header.
Organized around three resource groups:
The underlying tracker covers Google and Bing across Local Pack, Maps, and organic, desktop and mobile, up to 100 positions, with geo-targeting and a weighted Visibility Score. Verify exact paths, parameters, and response schemas in the API reference above — the beta docs are the source of truth, and the "Download OpenAPI Document" link there provides the full schema. Beta questions go to troy@whitespark.ca.
Use it for: automating organic/Local Pack keyword-position and Visibility Score pulls into recurring reports alongside geogrid data. Don't reach for it when geographic coverage matters more than single-point positions — that's what the grids API and geogrid_scan are for.
| What You Found | Next Action | Skill |
|---|---|---|
| Citation gaps identified | Build missing citations, starting with Tier 1 | local-citations |
| Citations built, waiting for propagation | Work on other optimization while waiting (4-8 weeks) | gbp-optimization, review-management |
| Review generation campaign running | Monitor velocity and adjust messaging if response rate is low | review-management |
| Citation data needs to go in a report | Include in audit or monthly report | client-deliverables, local-reporting |
| Need MCP-accessible citation data | Use BrightLocal instead | brightlocal-tool |
| Need grid visuals or summary metrics in a report | Pull via the Local Ranking Grids API | local-reporting, client-deliverables |
| Need keyword positions or Visibility Score in a report | Pull via the Local Rank Tracker API | local-reporting |
Default next step: Whitespark's strength is managed citation services. If you need automated, agent-accessible citation data, use BrightLocal. If you need the highest-quality citation building, use Whitespark's managed service.
© garrettjsmith, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/whitespark-tool of garrettjsmith/localseoskills.
Open the folder on GitHubat commit 405ce20
Whitespark Tool 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Whitespark Tool this skillgarrettjsmith/localseoskills | 121 | — | ~2.6k | Automated safety check: Pass | MIT | |
| Citation Source Gap Finderirinabuht12-oss/marketing-skills | 4.1k | — | ~601 | Automated safety check: Pass | None | |
| Google Mapscablate/mcp-google-map | 469 | — | ~909 | Automated safety check: Pass | MIT | |
| Google Maps Local SEOcablate/mcp-google-map | 469 | — | ~633 | Automated safety check: Pass | MIT | |
| Google Maps Travel Planningcablate/mcp-google-map | 469 | — | ~710 | Automated safety check: Pass | MIT | |
| SEO Project Setuppetera2c/simple-table | 229 | 1 repos | ~1.5k | Automated safety check: Pass | MIT |
irinabuht12-oss/marketing-skills
Find the exact pages AI assistants cite when answering questions in your category, and identify which ones you can get into.
cablate/mcp-google-map
Search places, resolve addresses, compare routes, inspect neighborhoods, and retrieve geographic or environmental facts through the standalone @cablate/mcp-google-map CLI.
cablate/mcp-google-map
Analyze Google Business Profile visibility, geographic grid rankings, local search keywords, and nearby competitors through the standalone Google Maps CLI.
cablate/mcp-google-map
Build evidence-backed day trips, multi-day itineraries, and efficient stop sequences with Google Maps data through the standalone CLI.
petera2c/simple-table
Set up a durable local SEO workspace with project context, notes, goals, positioning, preferences, MCP checks, and Search Console data intake.
seranking/seo-skills
E-E-A-T + CITE quality audit for an EXISTING piece of content.
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.
garrettjsmith/localseoskills
When the user wants to create, schedule, or optimize Google Business Profile posts.
garrettjsmith/localseoskills
Generate complete semantic content briefs for local SEO content — location pages, service pages, blog posts, FAQ content, and pillar pages.
garrettjsmith/localseoskills
Manages persistent work state (briefs) for local SEO engagements.
garrettjsmith/localseoskills
Build a complete local content strategy from keyword research output.
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.
Works with
Categories
When the user wants citation gap analysis, managed citation building, review generation campaigns, or local rank tracking. Whitespark Tool is an agent skill from garrettjsmith/localseoskills. When the user wants citation gap analysis, managed citation building, review generation campaigns, or local rank tracking.
Whitespark Tool fits situations like: wants citation gap analysis; managed citation building; review generation campaigns; local rank tracking.
Run `npx skills add garrettjsmith/localseoskills --skill whitespark-tool -a claude-code`. Or copy the skill folder (skills/whitespark-tool in garrettjsmith/localseoskills) into .claude/skills/whitespark-tool in your project. Claude Code loads it when a task matches its description.
Run `npx skills add garrettjsmith/localseoskills --skill whitespark-tool -a codex`. Or copy the skill folder (skills/whitespark-tool in garrettjsmith/localseoskills) into .agents/skills/whitespark-tool in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add garrettjsmith/localseoskills --skill whitespark-tool -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/whitespark-tool, .gemini/skills/whitespark-tool, .github/skills/whitespark-tool and .opencode/skills/whitespark-tool in your project.
SKILL.md names no scripts, command-line tools or credentials: Whitespark Tool is instructions for the agent only.
SKILL.md names 2 domains. As links in the text: lrg.whitespark.ca and whitespark-api.apidocumentation.com. This is read from the text; nothing was executed.
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.
Whitespark Tool is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.6k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Whitespark Tool: Citation Source Gap Finder (irinabuht12-oss/marketing-skills, 4.1k stars), Google Maps (cablate/mcp-google-map, 469 stars), Google Maps Local SEO (cablate/mcp-google-map, 469 stars) and Google Maps Travel Planning (cablate/mcp-google-map, 469 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
garrettjsmith (a GitHub user) maintains it in garrettjsmith/localseoskills, which has 121 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.