GEO-First SEO Audit Tool
zubair-trabzada/geo-seo-claude
Audits a website for AI search visibility across ChatGPT, Claude, Perplexity and Google AI Overviews while checking traditional SEO, schema and E-E-A-T content quality.
Audit and fix a website's technical SEO and AI-search (GEO) readiness against Google's official guidance (plus Bing, Yandex, Apple and the AI crawlers), page by page, ending in a computed SEO/GEO…
Install SEO Audit
$ npx skills add umutxyp/Seo-Promt-Master --skill seo-audit -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install umutxyp/Seo-Promt-Master seo-audit --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/umutxyp/Seo-Promt-Master.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/seo-audit .claude/skills/seo-audit && 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 "seo-audit" agent skill from https://github.com/umutxyp/Seo-Promt-Master/tree/main/.claude/skills/seo-audit into .claude/skills/seo-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seo-audit", 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/umutxyp/Seo-Promt-Master/tree/main/.claude/skills/seo-auditType 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 umutxyp/Seo-Promt-Master --skill seo-audit -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install umutxyp/Seo-Promt-Master seo-audit --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/umutxyp/Seo-Promt-Master.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/seo-audit .agents/skills/seo-audit && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "seo-audit" agent skill from https://github.com/umutxyp/Seo-Promt-Master/tree/main/.claude/skills/seo-audit into .agents/skills/seo-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seo-audit", 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 umutxyp/Seo-Promt-Master --skill seo-audit -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install umutxyp/Seo-Promt-Master seo-audit --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/umutxyp/Seo-Promt-Master.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/seo-audit .cursor/skills/seo-audit && 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 "seo-audit" agent skill from https://github.com/umutxyp/Seo-Promt-Master/tree/main/.claude/skills/seo-audit into .cursor/skills/seo-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seo-audit", 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/umutxyp/Seo-Promt-Master.git --path .claude/skills/seo-audit--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 umutxyp/Seo-Promt-Master --skill seo-audit -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install umutxyp/Seo-Promt-Master seo-audit --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/umutxyp/Seo-Promt-Master.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/seo-audit .gemini/skills/seo-audit && 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 "seo-audit" agent skill from https://github.com/umutxyp/Seo-Promt-Master/tree/main/.claude/skills/seo-audit into .gemini/skills/seo-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seo-audit", 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 umutxyp/Seo-Promt-Master seo-auditInstalls 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 umutxyp/Seo-Promt-Master --skill seo-audit -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/umutxyp/Seo-Promt-Master.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/seo-audit .github/skills/seo-audit && 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 "seo-audit" agent skill from https://github.com/umutxyp/Seo-Promt-Master/tree/main/.claude/skills/seo-audit into .github/skills/seo-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seo-audit", 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 umutxyp/Seo-Promt-Master --skill seo-audit -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install umutxyp/Seo-Promt-Master seo-audit --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/umutxyp/Seo-Promt-Master.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/seo-audit .opencode/skills/seo-audit && 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 "seo-audit" agent skill from https://github.com/umutxyp/Seo-Promt-Master/tree/main/.claude/skills/seo-audit into .opencode/skills/seo-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seo-audit", 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.
Facts
- Skill name
seo-audit- GitHub stars
- 557
- Token cost
- ~1.4k tokens
- SKILL.md length
- 706 words
- Files
- 1
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
Audit and fix a website's technical SEO and AI-search (GEO) readiness against Google's official guidance (plus Bing, Yandex, Apple and the AI crawlers), page by page, ending in a computed SEO/GEO…
- Works in 5 steps: Fix shared infrastructure first. A… → Never break the build. Typecheck, lint… → Evidence, not assertion. A page is not… → …
- Asked to audit SEO
- SKILL.md covers Before anything else, Two ways to learn what is…, The workflow and Rules that are not negotiable, plus 1 more section
- Calls node
What it does
SEO Audit is an agent skill from umutxyp/Seo-Promt-Master. Audit and fix a website's technical SEO and AI-search (GEO) readiness against Google's official guidance (plus Bing, Yandex, Apple and the AI crawlers), page by page, ending in a computed SEO/GEO score. Use when asked to audit SEO, fix indexing or crawling problems, check canonicals/hreflang/sitemaps/structured data, diagnose why pages are not indexed or traffic dropped, prepare a site migration, or make a site visible to AI answer engines. Also use before shipping changes that touch routing, metadata, robots.txt…
Its SKILL.md is about 1.4k 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 Technical SEO and SEO audit. It works with Google Gemini and OpenAI. The repository describes itself as: 🔍 Google SEO's full docs as an AI prompt machine — drop it into your AI assistant to map every public route, audit each page against Google's rules, and fix the gaps step by step. The licence is MIT.
When your agent uses it
- Asked to audit SEO
- Crawling problems
- Check canonicals/hreflang/sitemaps/structured data
- Diagnose why pages are not indexed
Example prompts
- “s technical SEO and AI-search (GEO) readiness against Google”
- “/seo-audit”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Fix shared infrastructure first. A metadata helper, the sitemap builder,
- Never break the build. Typecheck, lint and build after every change. If it
- Evidence, not assertion. A page is not fixed until you have re-fetched it
- Persist progress to SEO-AUDIT-PROGRESS.md as you go. Long runs outlive
- Don't stop between phases to check in. A site with hundreds of routes is a
What it can do on your machine
Read from SKILL.md and the folder at commit 28e51d3. 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
Shell commands in SKILL.md call:
node
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
SEO Audit loads about 1.4k tokens when it runs. Until then it costs about 135 tokens; SKILL.md has 706 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.
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 umutxyp/Seo-Promt-Master at commit 28e51d3, republished under its MIT licence (© umutxyp). 706 words, ~1,356 tokens.
Download SKILL.mdSave it as
.claude/skills/seo-audit/SKILL.md (or your agent's skills folder).- name
- seo-audit
- description
- Audit and fix a website's technical SEO and AI-search (GEO) readiness against Google's official guidance (plus Bing, Yandex, Apple and the AI crawlers), page by page, ending in a computed SEO/GEO score. Use when asked to audit SEO, fix indexing or crawling problems, check canonicals/hreflang/sitemaps/structured data, diagnose why pages are not indexed or traffic dropped, prepare a site migration, or make a site visible to AI answer engines. Also use before shipping changes that touch routing, metadata, robots.txt or sitemaps.
SEO audit and repair
You are running SEO Prompt Master. Bring every public page of the project in the working directory into compliance with Google's documented guidance, and prove it rather than asserting it.
Before anything else
Read docs/README.md for the map, then keep docs/ open as you work. It is the
only source of truth in this skill. If a claim about how Google behaves is
not in docs/01–docs/18, say "not covered by the knowledge base" instead of
recalling it from memory — the SEO web is full of advice that was true in 2021.
Check verticals/README.md for an overlay matching the project's industry. It
adds emphasis; it never replaces the core audit.
Google is the reference engine, not the only one. docs/18 covers where Bing
(which also feeds DuckDuckGo, Yahoo and Copilot), Yandex, Apple/Safari, Brave
and the regional engines differ — never "fix" something for Google in a way that
blocks or throttles them.
For a single narrow task rather than the full workflow (rewrite robots.txt,
generate JSON-LD, diagnose a traffic drop), use the matching prompt in
prompt-library/README.md instead of running every phase.
Two ways to learn what is wrong, and you need both
Read the code to know what the project intends. Run the tool to know what the server actually does. They disagree more often than anyone expects, and the gap is where the bugs live.
node tools/seo-audit.mjs --url https://the-site.example --max 40 --md seo-report.mdZero dependencies, Node 18+. It samples across the sitemap rather than the head
of it, then checks robots.txt against RFC 9309, sitemap limits and lastmod
credibility, host consolidation, per-template soft 404s, canonical
self-reference and canonical targets, X-Robots-Tag headers, hreflang
reciprocity across pages (a one-way set is discarded in full), duplicate
titles, streamed-metadata visibility, raw-HTML content volume, structured-data
validity, and image dimensions. It prints a crawler access matrix (Google,
Bing, Apple, Yandex… and 16 AI crawlers), an SEO Score and a GEO Score, and
exits 1 if any P1 is open, so it can gate a deploy.
Point it at a local build (--url http://localhost:3000) when there is no live
site yet.
Three things it deliberately cannot see, which stay your job: whether the
content is any good (docs/14), off-page authority (docs/17), and real
field CWV data, which only CrUX has (docs/05).
The workflow
Follow START.md, which holds the full phase-by-phase instructions:
| Phase | File | Output |
|---|---|---|
| 0 — Bootstrap & detect | prompts/00-bootstrap.md | Stack report |
| 1 — Discover routes | prompts/01-discover-routes.md | ROUTES-INVENTORY.md |
| 2 — Audit each page | prompts/02-audit-page.md | SEO-AUDIT-PROGRESS.md |
| 3 — Prioritise | prompts/03-prioritize-fixes.md | P1/P2/P3 backlog + baseline score |
| 4 — Fix & verify | prompts/04-apply-and-verify.md | Fixes, each with evidence |
| 5 — Live signals (optional) | prompts/05-live-signals.md | Field data, if a live URL exists |
Classify every route as public-index, public-noindex (internal search, live
tools, auth screens) or private (dashboards, admin, API). Getting this wrong
in Phase 1 makes every later phase wrong: a page being reachable is not the
same as it deserving to be indexed.
Show full SKILL.md (238 more words)Show less
Rules that are not negotiable
- Fix shared infrastructure first. A metadata helper, the sitemap builder,
robots.txt, the i18n layer — one change there fixes hundreds of pages. Per-page work afterwards. - Never break the build. Typecheck, lint and build after every change. If it fails, fix it before moving on.
- Evidence, not assertion. A page is not fixed until you have re-fetched it
and seen the change —
curlthe route, grep the rendered output, or re-run the tool. "Should now be correct" is not a result. - Persist progress to
SEO-AUDIT-PROGRESS.mdas you go. Long runs outlive context windows; the file is what survives. - Don't stop between phases to check in. A site with hundreds of routes is a
reason to keep working, not a reason to summarise and wait. Stop only if you
cannot access the repo or run the build, or if a finding needs a genuine
product decision ("should
/internal-toolbe public at all") — ask that one question and keep going on everything else meanwhile.
Reporting
End with the SEO Score and GEO Score from docs/11: the per-category
breakdown, the coverage status (final vs provisional), and the caveat that
off-page factors are out of scope. A bare number is not a report.
Before calling a score final, re-verify a random ~15% of everything already marked done by re-reading the actual output, not your notes. Optimistic copy-paste ticks are the failure mode this catches.
© umutxyp, 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 .claude/skills/seo-audit of umutxyp/Seo-Promt-Master.
Open the folder on GitHubat commit 28e51d3
Compare with similar skills
SEO Audit 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 |
|---|---|---|---|---|---|---|
| SEO Audit this skillumutxyp/Seo-Promt-Master | 557 | — | ~1.4k | Automated safety check: Pass | MIT | |
| GEO-First SEO Audit Toolzubair-trabzada/geo-seo-claude | 11k | — | ~2.8k | Automated safety check: Notes | MIT | |
| SEOAgriciDaniel/seo-os | 137 | 2 repos | ~3.5k | Automated safety check: Pass | MIT | |
| GEO Platform Optimizerzubair-trabzada/geo-seo-claude | 11k | 2 repos | ~4.7k | Automated safety check: Notes | MIT | |
| AI Discoverability AuditBrianRWagner/ai-marketing-claude-code-skills | 441 | — | ~2.3k | Automated safety check: Pass | None | |
| SEOAgriciDaniel/codex-seo | 799 | — | ~3.7k | Automated safety check: Pass | MIT |
Similar skills
SEO
AgriciDaniel/seo-os
Comprehensive SEO analysis for any website or business type.
GEO Platform Optimizer
zubair-trabzada/geo-seo-claude
Audits a site for AI search visibility one platform at a time, scoring Google AI Overviews, ChatGPT, Perplexity, Gemini and Bing Copilot and listing gaps to fix.
AI Discoverability Audit
BrianRWagner/ai-marketing-claude-code-skills
Audits how a brand is described by AI search tools such as ChatGPT, Perplexity and Gemini, then produces a scored report, action plan and re-audit schedule.
SEO
AgriciDaniel/codex-seo
Comprehensive SEO analysis for any website, page, business, or topic.
Money SEO
iamzifei/show-me-the-money
SEO and GEO (Generative Engine Optimization) for organic traffic and AI search visibility.
Related
Works with
Categories
Questions about SEO Audit
What does SEO Audit do?
Audit and fix a website's technical SEO and AI-search (GEO) readiness against Google's official guidance (plus Bing, Yandex, Apple and the AI crawlers), page by page, ending in a computed SEO/GEO…. SEO Audit is an agent skill from umutxyp/Seo-Promt-Master. Audit and fix a website's technical SEO and AI-search (GEO) readiness against Google's official guidance (plus Bing, Yandex, Apple and the AI crawlers), page by page, ending in a computed SEO/GEO score.
When should I use SEO Audit?
SEO Audit fits situations like: asked to audit SEO; crawling problems; check canonicals/hreflang/sitemaps/structured data; diagnose why pages are not indexed.
How do I install SEO Audit in Claude Code?
Run `npx skills add umutxyp/Seo-Promt-Master --skill seo-audit -a claude-code`. Or copy the skill folder (.claude/skills/seo-audit in umutxyp/Seo-Promt-Master) into .claude/skills/seo-audit in your project. Claude Code loads it when a task matches its description.
How do I install SEO Audit in Codex?
Run `npx skills add umutxyp/Seo-Promt-Master --skill seo-audit -a codex`. Or copy the skill folder (.claude/skills/seo-audit in umutxyp/Seo-Promt-Master) into .agents/skills/seo-audit in your project. Codex loads it when a task matches its description.
Can I use SEO Audit 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 umutxyp/Seo-Promt-Master --skill seo-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/seo-audit, .gemini/skills/seo-audit, .github/skills/seo-audit and .opencode/skills/seo-audit in your project.
What does SEO Audit need to run?
Going by SKILL.md and its folder, SEO Audit needs the command-line tools its instructions call (node).
Does SEO Audit 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 SEO Audit 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 SEO Audit use?
SEO Audit 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 SEO Audit use?
About 1.4k tokens (SKILL.md is roughly 5.4k 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 SEO Audit?
Skills that share tags, products or a category with SEO Audit: GEO-First SEO Audit Tool (zubair-trabzada/geo-seo-claude, 11k stars), SEO (AgriciDaniel/seo-os, 137 stars), GEO Platform Optimizer (zubair-trabzada/geo-seo-claude, 11k stars) and AI Discoverability Audit (BrianRWagner/ai-marketing-claude-code-skills, 441 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains SEO Audit?
umutxyp (a GitHub user) maintains it in umutxyp/Seo-Promt-Master, which has 557 GitHub stars. The repository was last updated on October 3, 2026.
Source: umutxyp/Seo-Promt-Master on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.