Seo Ai Search Share Of Voice

> Example output: [examples/seo-ai-search-share-of-voice-wix-com-20260427/REPORT.md](../../examples/seo-ai-search-share-of-voice-wix-com-20260427/REPORT.md)

AI Search Share of Voice

Compare AI-search visibility for a target brand against competitors across every major LLM engine, then analyse the topic clusters each brand owns and where gaps exist.

Prerequisites

• DataForSEO MCP server connected.
• User provides: (a) target domain and its brand name, (b) list of competitor domains and brand names, (c) country (default: us), and (d) optionally, which engines to analyse (default: all supported: ai-overview, chatgpt, perplexity, gemini, ai-mode).

Process

1. Leaderboard snapshot mcp__dataforseo__ai_opt_llm_ment_top_domains + mcp__dataforseo__ai_opt_llm_ment_agg_metrics; Google AI Overview presence from mcp__dataforseo__serp_organic_live_advanced (AIO block)

• Pull the LLM-mention leaderboard (top cited/mentioned domains) for the target domain's category in the target country; for the AI Overview engine, read the AIO citation block from serp_organic_live_advanced on the category's seed keywords.
• Capture mention counts and share percentages per engine, per domain.

1. Heatmap table

• Build a table: rows = domains (target + competitors), columns = engines, cells = % share of voice.
• Highlight the leader per engine and the worst performer.

1. Prompt sampling per domain mcp__dataforseo__ai_opt_llm_ment_search, mcp__dataforseo__ai_opt_llm_ment_top_pages; for actual answers mcp__dataforseo__ai_optimization_chat_gpt_scraper / mcp__dataforseo__ai_optimization_llm_response

• For each domain (target and each competitor):
• Use ai_opt_llm_ment_search to pull prompts/queries where the domain appears as a cited source (link mention) and where the brand is mentioned by name; ai_opt_llm_ment_top_pages surfaces the specific pages cited.
• Where a live answer is needed to confirm a mention, scrape it with ai_optimization_chat_gpt_scraper (ChatGPT) or ai_optimization_llm_response (other models).
• Save query text and the exact sources cited so the user can validate.

1. Topic clustering

• Group prompts by theme (e.g., pricing, feature comparison, tutorials, alternatives, reviews).
• For each brand, note which clusters it dominates and which it is absent from.

1. Gap and recommendation synthesis

• Identify 3 to 5 topic clusters where the target underperforms competitors despite having relevant content.
• Recommend specific actions: new content angles, structured data additions, partnerships with frequently-cited sources, comparison pages, FAQ/How-To schema.

Output format

Create a folder seo-ai-search-share-of-voice-{target-slug}-{YYYYMMDD}/ with:

seo-ai-search-share-of-voice-{target-slug}-{YYYYMMDD}/
├── 01-leaderboard.md         # raw leaderboard per engine
├── 02-heatmap.md             # visual heatmap table
├── 03-prompts-{domain}.md    # one file per domain with 20 sampled prompts
├── 04-topic-clusters.md      # cluster membership per brand
└── REPORT.md                 # executive summary

REPORT.md follows this shape:

# AI Search Share of Voice: {target brand} vs competitors

## Summary
- Target: {target} ({share}% across all engines)
- Leader: {leader brand} ({share}%)
- Target rank: {n} of {total}

## Heatmap

| Domain | AI Overview | ChatGPT | Perplexity | Gemini | AI Mode |
|---|---|---|---|---|---|
| {target} | {%} | {%} | {%} | {%} | {%} |
| {comp1} | ... | ... | ... | ... | ... |

## Who owns what

### {target brand}
Strong in: {cluster 1}, {cluster 2}
Absent from: {cluster 3}, {cluster 4}

### {competitor 1 brand}
...

## Topic cluster ownership

| Cluster | Leader | Share | Target position | Gap |
|---|---|---|---|---|
| Pricing | {brand} | {%} | {n} | {% behind} |
| Alternatives | {brand} | {%} | {n} | {% behind} |
| Tutorials | {brand} | {%} | {n} | {% behind} |

## Top 5 actions to close gaps
1. {action with target cluster}
2. ...

Tips

• Do not hallucinate citation counts. If the API returns zero prompts for a given domain/engine, report zero, do not estimate.
• For each competitor, validate the brand-name match in the prompt text. Sometimes "Wix" appears in a sentence about "wiktionary" or a person's name. Flag ambiguous matches in the raw-prompt file.
• base_domain scope is the default; do not narrow to subdomain unless the user asks.
• DataForSEO allows up to 2,000 calls/min, 30 concurrent; pace sequentially. With 5 domains and 2 mention queries per engine per domain, pace the loop. DataForSEO bills per call — cap large mention lists with limit and ai_optimization_llm_mentions_filters.
• The report is not a one-time artefact. Recommend the user re-run monthly and diff results to see ranking momentum.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: amirjahfar1
• Source: amirjahfar1/automate-seo-with-claude
• License: MIT
• Homepage: https://nextbrainsolutions.com/

Install and usage instructions live in the source repository linked above.