seo-sxo

Trigger phrases

Phrases that activate this skill when typed to Claude Code:

• SXO
• page type mismatch
• SERP analysis
• why isn't my page ranking
• intent mismatch

What it does

seo-sxo is a Claude Code skill from AgriciDaniel’s claude-seo repo. It was contributed by Florian Schmitz (Pro Hub Challenge). SXO — Search Experience Optimization — bridges the gap between technical SEO compliance and actual ranking. The core insight: a page can score 95/100 on technical SEO and still fail to rank if it is the wrong page type for the keyword. If Google’s top 10 results for a query are 8 product pages and 2 comparison pages, a blog post targeting that keyword will never break through regardless of optimization.

The skill reads the SERP backwards to determine what Google is actually rewarding: it analyzes the top 10 organic results for page type (product, comparison, how-to, landing page, tool, etc.), content depth expectations, schema types present, and media requirements. It then compares the target page against this SERP consensus and scores alignment across 7 dimensions for an SXO Gap Score (0–100). It also derives 3–5 user stories from SERP signals (People Also Ask, ad copy themes, related searches) and scores the page from 4–7 persona perspectives on relevance, clarity, trust, and available next action.

When to use it

Reach for it when:

• A page is technically healthy (good technical SEO score) but ranking poorly for its target keyword
• You want to know whether you need a new page type rather than more optimization of the existing page
• You are planning a new page and want to validate the format decision before writing

When not to reach for it:

• The keyword has fewer than 5 organic results (limited SERP data to analyze)
• You need technical SEO data like CWV or indexation status — use seo-technical or seo-google for that; the SXO score is separate from the SEO Health Score

Install

Copy the seo-sxo SKILL.md into .claude/skills/seo-sxo/.

Trigger phrases: “SXO”, “search experience”, “page type mismatch”, “SERP analysis”, “user story”, “persona scoring”, “why isn’t my page ranking”, “intent mismatch”, “wireframe”.

Commands: /seo sxo <url> (full analysis, auto-detects keyword from title + H1), /seo sxo <url> <keyword> (for a specific keyword), /seo sxo wireframe <url> (generates IST/SOLL wireframe with concrete recommendations).

What a session looks like

A typical session has three phases:

1. SERP analysis and page-type classification. The target URL is fetched and parsed. The target keyword is identified (or provided). The skill searches Google for that keyword and classifies each of the top 10 results by page type using a taxonomy. It calculates SERP consensus: dominant page type (60%+ = strong consensus), content depth norms, schema expectations, and media requirements. Page-type mismatch is classified by severity: CRITICAL if a blog post is targeting a product-page keyword, HIGH if a product page is targeting an informational keyword.
2. User story derivation. SERP signals generate user stories in the “As a [persona], I want to [goal] because [driver], but I’m blocked by [barrier]” format. These come from PAA questions (knowledge gaps), ad copy themes (commercial triggers), related searches (search journey), and Featured Snippet format (expected answer structure).
3. Gap analysis and persona scoring. The 7-dimension SXO Gap Score is calculated. Then 4–7 personas are derived from SERP intent signals and each scores the target page on relevance, clarity, trust, and available next action. Recommendations are sorted by weakest persona first — these are the biggest opportunities.

Receipts

Works well: The page-type mismatch detection catches the single most common reason pages fail to rank despite technical health — the format is wrong for what Google rewards. This is something no standard technical SEO audit identifies, and it saves significant rework compared to discovering it after months of optimization.

Backfires: SERP classification relies on WebSearch calls for each result, which is slow. With DataForSEO, precision improves. The skill notes when SERP data is limited and is honest about reduced confidence.

Pattern that works: Run SXO analysis before any significant content rewrite. If the page type is wrong, rewriting the same format is wasted effort — you need to create a different kind of page. Knowing this before writing saves the most time.

Source and attribution

Originally written by AgriciDaniel, incorporating contribution from Florian Schmitz (Pro Hub Challenge). The canonical SKILL.md and supporting files live in the seo-sxo folder of the claude-seo repository.

License: MIT. Install, adapt, and redistribute with attribution preserved.

This page documents the skill from a practitioner’s perspective. For the formal spec and updates, defer to the source repo.