/ Verzeichnis / Playground / Agentic-SEO-Skill
← Alle Server ↗ GitHub
● Community Bhanunamikaze ⚡ Sofort

Agentic-SEO-Skill

von Bhanunamikaze · Bhanunamikaze/Agentic-SEO-Skill

LLM-first SEO with 16 sub-skills, 10 specialist agents, 33 evidence-collector scripts — works in Antigravity, Codex, and Claude Code.

An evidence-first SEO skill: collect page data via utility scripts, analyze with an LLM that must cite proofs, apply confidence labels, prioritize by impact, and produce structured action plans. Enforces current Google standards (INP over FID, full E-E-A-T). Notable: a GitHub-analyst agent audits repo-hosted sites and writes GITHUB-SEO-REPORT.md.

▶ Demo ansehen 📦 Installieren 💡 Anwendungsfälle

Warum nutzen

Hauptfunktionen

Live-Demo

In der Praxis

agentic-seo-skill.replay ▶ bereit
0/0

Installation

Repository des Autors · Offizielle Dokumentation zu Claude Skills

Anwendungsfälle

Praxisnahe Nutzung: Agentic-SEO-Skill

Run an evidence-backed SEO audit with confidence labels

👤 SEO analysts tired of 'trust me' recommendations ⏱ ~60 min intermediate

Wann einsetzen: You want findings you can defend to a skeptical engineering lead.

Ablauf
  1. Trigger the full audit
    Use agentic-seo-skill on https://site.com — full evidence-backed audit.✓ Kopiert
    → Scripts collect raw data (meta tags, schema, link graph, CWV); agents analyze
  2. Review findings with proofs
    Show the top 10 issues with their supporting evidence and confidence labels.✓ Kopiert
    → Each finding has a literal quote/data point behind it
  3. Prioritized action plan
    Order by impact × effort.✓ Kopiert
    → Ranked plan with numeric rationale

Ergebnis: An audit where every finding is citable.

Fallstricke
  • Low-confidence findings treated as high priority — Use the confidence labels — skip 'low' until high/medium are done
Kombinieren mit: firecrawl

Audit a GitHub-hosted docs site with the GitHub-analyst agent

👤 Dev-tool teams with docs on GitHub Pages ⏱ ~40 min intermediate

Wann einsetzen: Your docs live in a repo and you want a SEO audit tied to the repo structure.

Ablauf
  1. Point the GitHub agent at the repo
    agentic-seo-skill — audit github.com/acme/docs site. Output GITHUB-SEO-REPORT.md.✓ Kopiert
    → Report in the repo format with per-file recommendations
  2. Open a PR with fixes
    Turn the high-confidence findings into a PR.✓ Kopiert
    → PR with concrete diffs

Ergebnis: A SEO-improved docs site with a trackable PR.

Fallstricke
  • PR touches too many files at once — Split by finding type (meta vs content vs schema)
Kombinieren mit: github

Optimize pages for Perplexity / ChatGPT / AI Overviews citations

👤 Content teams losing clicks to AI summaries ⏱ ~30 min intermediate

Wann einsetzen: You want to be the cited source, not just another organic result.

Ablauf
  1. Run the GEO/AEO sub-skill
    agentic-seo-skill — GEO audit on https://site.com/post.✓ Kopiert
    → Findings tied to snippet-friendliness, entity clarity, citation signals
  2. Apply and verify
    Apply recommendations and re-verify.✓ Kopiert
    → Score deltas with evidence

Ergebnis: Pages restructured for AI-citation pickup.

Fallstricke
  • Over-optimization hurts human readability — The content-quality agent catches robotic-sounding edits

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

agentic-seo-skill + firecrawl

Firecrawl does the JS-rendered crawl; agentic-seo interprets

Crawl with firecrawl, pipe rendered HTML into agentic-seo-skill for analysis.✓ Kopiert
agentic-seo-skill + github

Open PRs directly from audit findings

For the high-confidence findings, open a PR in the repo.✓ Kopiert
agentic-seo-skill + claude-seo-skill

Use the /seo slash commands for fast runs, agentic-seo for evidence-backed depth

First do /seo audit for the quick view, then agentic-seo-skill for the deep defensible audit.✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

WerkzeugEingabenWann aufrufenKosten
Technical SEO agent URL Baseline tech audit 0
Schema agent URL Structured data work 0
Performance agent URL CWV review 0
GitHub-analyst agent repo URL Audits on GitHub-hosted sites 0
Verification agent prior findings Before publishing audit 0

Kosten & Limits

Was der Betrieb kostet

API-Kontingent
None for the skill
Tokens pro Aufruf
10-30k for full audit — evidence collection uses scripts, not tokens, for the raw data
Kosten in €
Free — skill is local
Tipp
Utility scripts are Python — run them as preflight outside the LLM loop to save tokens.

Sicherheit

Rechte, Secrets, Reichweite

Credential-Speicherung: No credentials — scripts hit public URLs only
Datenabfluss: Only to the sites you audit

Fehlerbehebung

Häufige Fehler und Lösungen

Utility scripts fail to run

Check Python version and required packages; install dependencies from the skill's requirements file.

Prüfen: python --version
Confidence labels all 'low'

Scripts couldn't collect enough raw evidence — check network access and JS rendering.

GitHub-analyst can't access repo

Set a PAT for private repos; public repos should work unauthenticated.

Alternativen

Agentic-SEO-Skill vs. andere

AlternativeWann stattdessenKompromiss
claude-seo-skillYou want slash-command UX and enterprise reportingClaude-only; no multi-agent evidence framework
seo-geo-claude-skillYou want a phase-based lighter libraryLess evidence-first methodology

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen