Skip to content
Back to search

seo

MarketplaceWorks with Claude CodeGitHub

Local-first SEO and AI-search diagnostics.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026. Its scripts were only partly scanned.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/iannuttall/seo with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/iannuttall/seo'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/iannuttall--seo/badge.svg)](/listings/iannuttall--seo)

HTML

<a href="/listings/iannuttall--seo"><img src="/api/listings/iannuttall--seo/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Requires Node 22 or newer.

npm i -g seo
seo start
seo report

The setup walks you through Google sign-in, your Search Console property, an optional traffic analytics connection, and a local project profile. Public releases can include the shared Google app. If it is unavailable in your build, setup guides you through adding your own desktop OAuth client.

DataForSEO, Semrush, and Ahrefs are optional research providers built into the main package. Connect one only when external result, keyword, domain, competitor, or link evidence would change the decision.

That is the normal path. The `seo` command is then available in every terminal, script, CI job, and local MCP client on the machine.

The main report uses the evidence you have, explains what it could not check, and recommends a short list of follow-up commands. You can start with a local technical report before connecting Google: `seo report --url` crawls the site and returns findings and an action list with no sign-in at all.

Running `seo help` shows the shape of the tool:

Run SEO audits, find what needs fixing, and ship the changes with your agent.

Start here
  seo start                                Connect first-party data and save a project profile
  seo report                               Run the main SEO report for the default project
  seo report --site sc-domain:example.com  Run without a profile
  seo report --url https://example.com     Start with a local technical report

Projects
  seo projects list  List saved project profiles
  seo projects add   Create or update a project profile
  seo sites          List Search Console properties
  seo doctor         Check local auth and config

Act on a report
  seo refresh-priorities  Rank the next best SEO actions
  seo quick-wins          Find ranking 4-10 low-CTR wins
  seo second-page         Investigate URLs averaging positions 10-20
  seo technical-watch     Crawl and index-monitor a site

Agent and power tools
  seo report --json    Run the main report as structured JSON
  seo export diagnose  Export report data to CSV
  seo mcp install      Install SEO tools into MCP clients
  seo skill list       Show the packaged SEO skill
  seo reports list     Discover every structured report

Use `seo help <command>` or `seo <command> --help` for command help.
Use `seo help all` for the longer command list.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 14 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. {
  2. "name": "seo",
  3. "owner": {
  4. "name": "Ian Nuttall"
  5. },
  6. "description": "Local-first SEO and AI-search diagnostics.",
  7. "plugins": [
  8. {
  9. "name": "seo",
  10. "source": "./",
  11. "description": "The seo MCP server plus one SEO skill that gives an agent 50+ audit and report tools."
  12. }
  13. ]
  14. }
README.md · README · 180 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <p align="center">
  2. <picture>
  3. <source media="(prefers-color-scheme: dark)" srcset="assets/brand/s-dark.svg">
  4. <img src="assets/brand/s.svg" alt="SEO Skill" width="120">
  5. </picture>
  6. </p>
  7. # SEO For Agent-Native Teams
  8. [![npm](https://img.shields.io/npm/v/seo?style=flat-square)](https://www.npmjs.com/package/seo)
  9. The SEO data I give my agents every day, so they work from my real numbers
  10. instead of guessing.
  11. Most AI SEO tools do one of two things. They hand your agent a checklist of
  12. generic advice, or they feed it estimates from a keyword tool that has never
  13. seen your site. Either way you end up with the same pages everyone else is
  14. publishing. Pages written from a keyword list aren't SEO. They're slop.
  15. This works the other way round. It's a Google Search Console MCP server and
  16. CLI, and it doesn't tell your agent what to do. It gives it the facts: your
  17. clicks, impressions and positions from Search Console, your visits from
  18. Google Analytics, Clicky or Simple Analytics, your Bing data, the dates of Google updates, and
  19. a crawl of your site. Your agent works out what matters, and you decide what
  20. changes.
  21. It's free and open source. Hack around with it. Make it your own.
  22. ## Installation (30-second setup)
  23. ### 1. Connect it to your agent
  24. <details>
  25. <summary><strong>Claude Code</strong></summary>
  26. ```bash
  27. claude mcp add --transport http seoskill https://seoskill.dev/mcp
  28. ```
  29. </details>
  30. <details>
  31. <summary><strong>Codex</strong></summary>
  32. ```bash
  33. codex mcp add seoskill --url https://seoskill.dev/mcp
  34. ```
  35. </details>
  36. <details>
  37. <summary><strong>Any other agent</strong></summary>
  38. Add `https://seoskill.dev/mcp` as a remote MCP server. Cursor, Claude
  39. Desktop, VS Code and most other agents support it.
  40. </details>
  41. <details>
  42. <summary><strong>The CLI</strong> (for crawls and Bing, which run on your machine)</summary>
  43. ```bash
  44. npm i -g seo
  45. seo start
  46. ```
  47. `seo start` signs you in, connects your agents and installs the skill.
  48. </details>
  49. ### 2. Sign in with Google
  50. Your agent opens a Google sign-in. Pick the account that can see your Search
  51. Console. That's your account. There's no password and no signup form.
  52. ### 3. Ask it something real
  53. ```text
  54. Why did clicks drop on example.com last month?
  55. ```
  56. That's it. You're ready to go.
  57. ## What you can ask it
  58. - "Why did clicks drop last month? Was it the core update?"
  59. - "Which pages are close to page one, and what do they rank for?"
  60. - "Is this page indexed? If not, why not?"
  61. - "Which searches does this page show up for that it never mentions?"
  62. - "Can ChatGPT, Claude and Perplexity read my site?"
  63. - "Who am I up against in search, and is there demand for a 'vs' or alternatives page?"
  64. Your agent picks the commands, reads the results and shows you what it found.
  65. ## Why it exists
  66. I built this because agents kept failing at SEO in the same few ways.
  67. ### #1: The agent makes things up
  68. **The problem.** Ask an agent why your traffic dropped and you get a tidy
  69. list of possible causes. Algorithm update, technical issues, content
  70. quality. None of it comes from your site, so none of it helps.
  71. **The fix** is to give it your numbers:
  72. - [`seo report`](https://seoskill.dev/docs/report) shows your totals against the last period, the pages and queries that moved, and the places worth a look: quick wins, low click-through rates, pages stuck on page two, decay and cannibalization.
  73. - [`seo compare`](https://seoskill.dev/docs/compare) lines up the weeks before and after a date, with the Google updates in between.
  74. ### #2: Keyword tools are guessing too
  75. **The problem.** Ahrefs and Semrush estimate your traffic from a sample.
  76. They miss most of the long tail, and they rarely agree with each other.
  77. **The fix** is to start from your own data. Search Console is the source of
  78. truth for Google. When you do need keyword volumes or competitor data,
  79. [`seo research`](https://seoskill.dev/docs/research) uses your own
  80. DataForSEO or Ahrefs key, and it keeps those estimates apart from your real
  81. numbers.
  82. ### #3: The agent says it's fixed when it isn't
  83. **The problem.** Agents trust their own edits. Then you find the page is
  84. still noindexed, still redirecting, or still not in Google.
  85. **The fix** is to check the live site:
  86. - [`seo page`](https://seoskill.dev/docs/page) loads one URL and asks Google whether it's indexed.
  87. - [`seo index`](https://seoskill.dev/docs/indexing) checks every page that lost its clicks.
  88. - [`seo crawl`](https://seoskill.dev/docs/crawl) checks the whole site, including what AI agents can read.
  89. ### #4: Too many reports
  90. **The problem.** SEO tools love reports. The first version of this had about
  91. 70 of them, and almost nobody used most of them.
  92. **The fix** was to cut it down to a handful of commands. Each one takes a
  93. site or a URL, and dates if you want them. There are no settings to tune. Every result
  94. ends with the command to run next, so your agent always knows where to go.
  95. ## Reference
  96. | Command | What it returns |
  97. | --- | --- |
  98. | [`seo next`](https://seoskill.dev/docs/next) | Where a site is in the SEO loop and the one step to do now, with its first jobs |
  99. | [`seo report`](https://seoskill.dev/docs/report) | Your Search Console overview for `--site`, then the top rows of each section |
  100. | [`seo page`](https://seoskill.dev/docs/page) | One URL: the live page, its Google index status and its queries |
  101. | [`seo compare`](https://seoskill.dev/docs/compare) | Before and after a date, with Google updates |
  102. | [`seo index`](https://seoskill.dev/docs/indexing) | Google's indexing reasons for known URLs, labelled from live checks, and pages that lost their clicks |
  103. | [`seo submit`](https://seoskill.dev/docs/submit) | Ask Bing and others to crawl pages with IndexNow (free), or send them to Google with Index My Site (your own credits) |
  104. | [`seo research`](https://seoskill.dev/docs/research) | Keywords, search results, competitors, backlinks and AI answer citations from your own key |
  105. | [`seo data`](https://seoskill.dev/docs/data) | Raw Search Console or Bing rows, or Clicky and Simple Analytics landing pages |
  106. | [`seo analytics`](https://seoskill.dev/docs/analytics) | Landing pages from Google Analytics, Clicky or Simple Analytics |
  107. | [`seo crawl`](https://seoskill.dev/docs/crawl) | Technical issues and AI agent access across a site (CLI only) |
  108. | [`seo internal-links`](https://seoskill.dev/docs/internal-links) | Internal links to add across a site or to one page (CLI only) |
  109. | [`seo lint`](https://seoskill.dev/docs/lint) | Lines in a draft, title or description that read as AI-written, each with a fix |
  110. | `seo feedback` | Send a bug or idea about SEO Skill, with a proposed fix, to the maintainer |
  111. Every command is also an MCP tool, such as `seo_report`. Crawls and internal links are tools on the local MCP server only (`seo mcp serve`). Add `--json` to any
  112. command when you're scripting it.
  113. ## What it keeps
  114. As little as possible. The hosted server keeps your linked Google accounts
  115. and any keys you save, encrypted, plus the issues list and business context
  116. your agent saves for a site. It doesn't keep your reports, Search Console
  117. rows or request logs, except what the paid
  118. [weekly site audit](https://seoskill.dev/docs/weekly-site-audit) keeps. The CLI keeps your sign-in in your system
  119. keychain. The [privacy policy](https://seoskill.dev/privacy) has the details.
  120. ## Links
  121. - [Documentation](https://seoskill.dev/docs)
  122. - [Cloud agents and CI](https://seoskill.dev/docs/cloud-agents)
  123. - [Add your own analytics source](https://github.com/iannuttall/seo-provider-template)
  124. - [Changelog](CHANGELOG.md) and [contributing](CONTRIBUTING.md)
  125. - [Questions and bugs](https://github.com/iannuttall/seo/issues)
  126. Apache-2.0. The name and artwork are covered by the
  127. [brand policy](TRADEMARKS.md).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.