agentleFS
serankingseranking/seo-skills/skills/seo-ai-search-share-of-voice/SKILL.md

seo-ai-search-share-of-voice

Skill201 starsChanged 5 months agoMITView on GitHub

Measure AI Search share of voice for a target domain versus competitors across ChatGPT, Perplexity, Gemini, Google AI Overview, and AI Mode. Pulls the AIO leaderboard, then samples prompts where each domain appears as a source or brand mention, and analyses topic clusters each brand owns. Use when the user asks for AI Search share of voice, LLM visibility tracking, AEO/GEO analysis, AI Overview competitive analysis, or wants to know which brands LLMs cite in their category.

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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. Very specific:

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

    line 43
  2. Distinctive:

    Do not hallucinate citation counts.

    line 95

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Example output: 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

  • SE Ranking 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 DATA_getAiOverviewLeaderboard
    • Pull the AIO leaderboard for the target domain's category in the target country.
    • Capture mention counts and share percentages per engine, per domain.
  2. Heatmap table
    • Build a table: rows = domains (target + competitors), columns = engines, cells = % share of voice.
    • Highlight the leader per engine and the worst performer.
  3. Prompt sampling per domain DATA_getAiPromptsByBrand, DATA_getAiPromptsByTarget
    • For each domain (target and each competitor):
      • Pull 10 ChatGPT prompts where the domain appears as a source (link mention).
      • Pull 10 ChatGPT prompts where the brand is mentioned by name.
    • Save query text and the exact sources cited so the user can validate.
  4. 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.
  5. 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.
  • Respect Data API rate limit: 10 requests per second. With 5 domains and 2 prompt queries per engine per domain, pace the loop.
  • The report is not a one-time artefact. Recommend the user re-run monthly and diff results to see ranking momentum.

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.