agentleFS
Sign inStart free
davepartnerdavepartner/seo-ai-optimizer/SKILL.md

seo-ai-optimizer

Skill0 starsChanged 6 days agoMITView on GitHub

Optimize a website or platform for search engines (SEO) AND for AI answer engines and app directories (AEO/GEO) — Google, Bing, ChatGPT Apps, Perplexity, Gemini, Claude/MCP. Audits the whole codebase, produces a prioritized improvement list, builds an admin checklist page with submission instructions and check-off progress, and tracks Google ranking before/after. Use when asked to improve SEO, rank on Google, get cited by AI, submit to the ChatGPT app store, or build an SEO admin dashboard. Triggers: "improve SEO", "rank on Google", "SEO audit", "AI SEO", "AEO", "GEO", "llms.txt", "ChatGPT app store", "submit to ChatGPT", "structured data", "sitemap", "robots.txt", "get cited by AI".

  • Installs packages

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. luongnv89/skills★ 145same name
    2. hongphuc5497/skills★ 2same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repositoryOne other file it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No cloaking, no sneaky redirects, no hidden text, no doorway pages — they cause penalties.

    line 94
  2. Distinctive:

    Don't touch the UI unless asked.

    line 96
  3. Very specific:

    Run npm install && npm test (checklist + ranking tests).

    line 114

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

SEO & AI Discovery Optimizer

Make a website or platform rank on search engines and get found/cited by AI — then give the admin a clean page to work through and watch the numbers move.

It is framework- and language-agnostic: it audits whatever the app is built with, then builds the admin page and the fixes in that stack. It optimizes for two audiences at once:

  1. Search engines — Google, Bing (classic SEO: crawl, index, rank).
  2. AI answer engines & app directories — ChatGPT Apps, Perplexity, Gemini, Claude/MCP (AEO/GEO: be crawlable, machine-readable, and quotable).

Honesty rule: not every "AI SEO trick" works. llms.txt is cheap to add but many AI crawlers ignore it; the reliable levers are crawlability, structured data, clear content, entity clarity, and real citations. This skill says what actually helps.

The pipeline

Scan ─▶ Audit ─▶ Build admin page ─▶ Submit ─▶ Implement ─▶ Measure (before/after)
  1. Scan the platform + source code — routes, templates, metadata, rendering, sitemaps, robots, structured data, and existing SEO artifacts (references/discovery.md).
  2. Audit against the checklist, split into code-level findings and content/AI findings (references/source-audit.md, references/technical-seo.md, content-seo.md, ai-discovery.md).
  3. Build the admin page — sections of checkable items, progress, "how to submit" details, the source-audit list, and the ranking chart (references/admin-ui.md).
  4. Submit where required — Google Search Console, Bing/IndexNow, ChatGPT Apps, MCP directory, etc. (references/submissions.md).
  5. Implement the safe wins — without breaking URLs, canonicals, redirects, or the UI.
  6. Measure — capture the Google baseline (impressions, clicks, CTR, average position) and compare before/after (references/ranking-tracking.md, examples/ranking.mjs).

The admin page (the deliverable)

A page in the admin (e.g. "SEO & AI") with:

  • Sections — Technical · Content & E-E-A-T · AI Discovery · Submissions · Measurement.
  • Checkable items — each shows what to do, why it matters, and how (with a link). The admin ticks them off; progress bars per section + overall.
  • Submission guide — step-by-step where to submit (GSC, Bing, IndexNow, ChatGPT Apps, MCP) with links.
  • Source-audit results — the code-level findings from scanning the repo, each with the fix and file.
  • Ranking before/after — a chart of Google impressions/clicks/CTR/position from the baseline to now.
  • Priority — remaining items sorted by impact × effort, so the admin knows what to do next.

Full spec: references/admin-ui.md. The checklist data lives in examples/seo-checklist.json.

AI discovery (AEO / GEO) — what actually helps

  • Be crawlable by AI. In robots.txt, allow the search/retrieval crawlers that produce citations — OAI-SearchBot, Claude-SearchBot, PerplexityBot — and decide your policy on training crawlers (GPTBot, ClaudeBot, Google-Extended, CCBot). See references/ai-discovery.md.
  • Be machine-readable. JSON-LD Organization, WebSite, BreadcrumbList, Article, Product, FAQPage, HowTo, LocalBusiness. Clear entity/brand info.
  • Be quotable. Concise answers, definitions, FAQs, dates, and sources. AI cites content that is explicit and verifiable.
  • llms.txt — add it (cheap), but don't rely on it; most AI crawlers still read HTML directly.
  • ChatGPT Apps / app store — build an MCP server via the Apps SDK, then submit through the plugin/app submission portal (OAuth + domain verification + app guidelines). See references/submissions.md.

Google ranking before/after

  • Capture a baseline from Google Search Console (Performance → impressions, clicks, CTR, average position) before changes; store it.
  • Re-measure after; compare with examples/ranking.mjs (compareSnapshots) and show the deltas on the admin page. Note: GSC "average position" is an average, not your literal rank per query — treat it as directional.

Safety (don't wreck the SEO you have)

  • Never change or remove existing URLs without a 301; preserve canonicals and redirects.
  • No cloaking, no sneaky redirects, no hidden text, no doorway pages — they cause penalties.
  • Additive robots.txt/sitemap changes only; test that key pages still return 200 and are indexable.
  • Don't touch the UI unless asked; keep Core Web Vitals in the good range.
  • Snapshot the baseline before editing, so the before/after is real.

References

  • references/discovery.md — scan the platform + source code.
  • references/technical-seo.md — crawl, index, canonicals, sitemaps, robots, rendering, CWV, structured data.
  • references/content-seo.md — titles, headings, E-E-A-T, internal links, FAQ.
  • references/ai-discovery.md — AI crawlers, robots policy, llms.txt, machine-readable content, citations.
  • references/submissions.md — exact submission steps: GSC, Bing/IndexNow, ChatGPT Apps, MCP, others.
  • references/admin-ui.md — the "SEO & AI" admin page (sections, checkboxes, submissions, chart).
  • references/source-audit.md — how to audit the codebase and produce the improvement list.
  • references/ranking-tracking.md — Google Search Console baseline + before/after.
  • references/report-template.md — the audit report format.
  • examples/seo-checklist.json — the structured checklist data (sections + items).
  • examples/checklist.mjs / ranking.mjs — tested progress + before/after helpers.
  • Run npm install && npm test (checklist + ranking tests).

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.

Check your setup, free