convez.ai
MCP ServerMarketing & VendasIntermediário
AntonioBlago

Claude Code SEO Starter

AntonioBlago/claude-code-seo-starter

Automação completa de workflow SEO com dados reais para agências

Ver no GitHub
InicialPluginScore · de 0 a 100

Blueprint pronto para uso com Claude Code que automatiza o workflow completo de agências e freelancers SEO: análise de status quo, potencial, elaboração de propostas e geração de PDFs. Integra o MCP Visibly AI para capturar dados reais de GSC, keywords, backlinks e auditorias on-page, com modelo inteligente de CTR e hooks que mantêm Claude focado em dados concretos em vez de especulações.

Instalação

$npx convez-ai AntonioBlago/claude-code-seo-starter

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
3
Forks
1
Acompanhando
0
Saúde
57%
Último commit
há 6 dias
Versão
—
Issues abertas
0
Contribuidores
1

Casos de uso

  • Análise de visibilidade orgânica e oportunidades de ranking
  • Elaboração automatizada de propostas de consulting SEO com métricas
  • Geração de relatórios PDF brand-compliant para apresentação a clientes
  • Cálculo de ROI e projeções de tráfego em 12 meses baseadas em CTR empírico

Veredito

Solução sólida e battle-tested para agências SEO que querem eliminar tarefas repetitivas. O diferencial real é a integração Visibly AI MCP que puxa dados vivos em vez de deixar Claude adivinhar — essencial para consulting credível. Recomendado para freelancers e pequenas agências que já rodam processos SEO estruturados.

README

A tradução para o português deste README ainda está na fila.

Claude Code — SEO Agency & Freelancer Starter

A batteries-included Claude Code blueprint for SEO freelancers and agencies. Wire up the Visibly AI MCP, get ready-made slash commands for the full client workflow — Status-Quo → Potential Analysis → Offer → CI-compliant PDF — and a smart hook that nudges Claude toward real SEO data instead of guessing.

Built and battle-tested by Antonio Blago — SEO Freelancer & creator of the Neuro-SEO System®.


Why this exists

SEO consulting is the same five jobs over and over: pull the real ranking data, map it against the client's keyword set, quantify the opportunity, turn that into an offer, and ship a presentable PDF. Claude Code can do all of it — if you give it the data sources, the methodology, and the guardrails.

This repo packages exactly that. Install it, drop in a Visibly AI key — free tier available, 30 seconds to a key — and you have an SEO analyst on tap that knows your process. Visibly AI is the data engine behind the whole workflow: GSC, keywords, backlinks, competitors and on-page audits through one MCP.

✨ What's inside

PieceWhat it does
.mcp.jsonPre-wired Visibly AI MCP connection — GSC, keywords, backlinks, competitors, on-page audits, crawling.
/visibly-seo-status-quoMaps a client's live organic visibility: GSC × target keywords, classification, quick wins.
/visibly-seo-potentialPotential analysis: empirical CTR model → realistic 12-month targets → traffic, lead & ROI math.
/visibly-seo-offerDrafts a tailored, phased SEO consulting offer from your analysis + client context.
/visibly-seo-pdf-buildTurns any analysis script into a clean, brand-compliant PDF.
SEO hookA UserPromptSubmit hook that detects SEO intent and steers Claude to Visibly AI MCP tools instead of generic scraping.
CLAUDE.mdA project-instruction template encoding the whole workflow + folder conventions.
docs/The methodology written out: workflows, the CTR model, and best practices.

🚀 Quickstart

There are two ways to use this — pick one.

Option A — Install as a plugin (fastest)

/plugin marketplace add AntonioBlago/claude-code-seo-starter
/plugin install seo-starter@antonioblago

You get the /visibly-seo-status-quo, /visibly-seo-potential, /visibly-seo-offer, /visibly-seo-pdf-build commands, the auto-invoked SEO skills, the SEO-intent hook, and the Visibly AI MCP — wired in. Then just set your key (step 3 below). Restart with /reload-plugins if needed.

Option B — Clone the template

Use the full repo (docs, PDF template, setup script) as a project scaffold.

1. Prerequisites

  • Claude Code installed (npm install -g @anthropic-ai/claude-code)
  • A Visibly AI account — sign up free, the free tier is enough to run the full workflow
  • Python 3.11+ (only needed for the PDF / data-crunching helpers)

2. Get the blueprint

# Use it as a GitHub template, or just clone:
git clone https://github.com/AntonioBlago/claude-code-seo-starter.git
cd claude-code-seo-starter

3. Add your Visibly AI key

Don't have a key yet? Create a free account at visibly-ai.com and copy your API key from the dashboard — takes about 30 seconds, no card required.

cp .env.example .env
# then edit .env and paste your key:
# VISIBLYAI_API_KEY=lc_xxxxxxxxxxxxxxxx

The .mcp.json reads the key from the environment — no secret ever lands in git.

4. Launch

claude

On first run, Claude Code will ask you to approve the Visibly AI MCP server. Approve it, then try:

/visibly-seo-status-quo example.com

That's it. You're running the full SEO workflow.

🔁 The workflows

Each slash command corresponds to one phase of a real client engagement. They chain:

/visibly-seo-status-quo <domain>   →   /visibly-seo-potential <domain>   →   /visibly-seo-offer <domain>   →   /visibly-seo-pdf-build <script.py>
   (where do we           (what's the upside,        (what should the          (hand the client a
    rank today?)           in clicks & €?)            client buy?)              polished PDF)

Full methodology is documented in docs/workflows.md.

📈 The CTR model

The potential analysis is only as good as its click-through-rate curve. This repo ships the Keyword Study 2026 — CTR by position from first-party Google Search Console data (1.3M keywords, 94 domains) — instead of the inflated textbook numbers most templates still use.

The differentiator: the curve is intent-aware. A navigational keyword at position 1 earns ~8.9% CTR; an informational one ~3.2%. Forecasting with one blended number quietly mis-states the upside. See docs/ctr-model.md for the full intent-by-position table and the Python to apply it. Honest inputs → defensible forecasts → offers that survive scrutiny.

🎨 Customise it

Everything is plain Markdown and shell — fork and adapt:

  • Branding — edit CLAUDE.md and templates/pdf_example.py with your colours, fonts, contact block.
  • Data source — swap or add MCP servers in .mcp.json (GA4, Ahrefs, etc.).
  • Workflows — the .claude/commands/*.md files are the workflows. Rewrite them in your own words.
  • Guardrails — extend .claude/hooks/seo-check.sh with your own keyword triggers.

See docs/setup.md for a deeper walkthrough and docs/best-practices.md for the hard-won lessons.

📂 Repo layout

claude-code-seo-starter/
├── .claude-plugin/           # makes this repo an installable plugin + marketplace
│   ├── plugin.json           # plugin manifest
│   └── marketplace.json      # marketplace catalog (one repo = both)
├── .mcp.json                 # Visibly AI MCP connection (key via env)
├── server.json               # MCP-registry manifest (publish via mcp-publisher)
├── .env.example              # copy → .env, add your key
├── CLAUDE.md                 # project instructions Claude reads on every run
├── .claude/
│   ├── commands/             # /visibly-seo-status-quo /visibly-seo-potential /visibly-seo-offer /visibly-seo-pdf-build
│   ├── skills/               # auto-invoked SEO skills (status-quo, potential, offer, pdf)
│   ├── hooks/                # seo-check.sh + hooks.json — SEO-intent nudge
│   └── settings.json         # hook registration + sane permissions (clone mode)
├── docs/
│   ├── setup.md              # detailed setup
│   ├── workflows.md          # the 4-phase methodology
│   ├── ctr-model.md          # empirical CTR curve
│   ├── folder-structure.md   # client knowledge base + CI base conventions
│   ├── best-practices.md     # lessons learned
│   └── promote.md            # discoverability checklist (registry, awesome lists)
├── templates/
│   ├── ci/                       # CI base — brand.py (constants) + CI.md (reference)
│   ├── client-template/          # copy → clients/<domain>/ (CLAUDE.md + _knowledge/)
│   ├── status-quo-template.md    # fill-in status-quo skeleton (classification, quick wins)
│   ├── potential-template.md     # fill-in potential skeleton (deltas, clusters, ROI scenarios)
│   ├── offer-template.md         # fill-in offer skeleton (phases, pricing, ROI, terms, CTA)
│   └── pdf_example.py            # minimal CI-PDF starter (fpdf2)
└── scripts/
    └── check-setup.sh        # verify your env is wired correctly

🤝 Contributing

PRs welcome — see CONTRIBUTING.md. Found this useful? A ⭐ helps others find it.

📜 License

MIT — see LICENSE. Use it commercially, fork it, ship it for your own clients.

💬 Want help setting it up?

If you'd rather have this dialled in to your agency's workflow — or want to talk SEO, Claude Code, or vibe coding — book a consultation.


Ver o original no GitHub

Bom para

Relacionados