share-of-voice

What this skill does

# /digital-marketing-pro:share-of-voice

## Purpose

Calculate and track share of voice across multiple competitive dimensions. Measure how visible the brand is relative to competitors across organic search (keyword rankings weighted by search volume), paid search (impression share and auction dynamics), social media (mention volume and sentiment-weighted presence), and AI engines (GEO visibility and citation rates). Share of voice is a leading indicator of market share — brands that consistently outperform competitors in visibility tend to gain market share over time, making SOV one of the most strategically important competitive metrics to track. This command provides a comprehensive competitive visibility picture by aggregating dimension-specific SOV scores into an overall competitive position assessment, with trend tracking to surface momentum shifts before they impact pipeline or revenue. Supports both point-in-time snapshots for current competitive standing and historical trend analysis when previous SOV measurements exist from prior runs.

## Input Required

The user must provide (or will be prompted for):

- **Competitors to compare**: A list of competitor names to include in the SOV calculation — e.g., "Acme Corp, Beta Inc, Gamma Labs". These should match competitors already tracked via competitor-monitor with saved baselines for the richest analysis, though new competitors can be added on the fly with reduced historical context and no trend data for the first measurement. Minimum two competitors recommended for meaningful competitive comparison, but single-competitor head-to-head analysis is supported for focused rivalry assessment
- **SOV dimensions to calculate**: Which visibility dimensions to include in the analysis — `organic` (keyword ranking visibility weighted by monthly search volume across the target keyword set), `paid` (Google Ads impression share, auction insights, and Meta ads impression data where available), `social` (mention volume and sentiment-weighted presence across social platforms over the specified time period), `ai` (AI engine citation rates and GEO visibility scores across ChatGPT, Gemini, Perplexity, and Copilot). Select all dimensions for a comprehensive competitive visibility picture or choose individual dimensions for focused analysis on a specific channel
- **Target keyword list**: The keyword set used for organic and paid SOV calculation — brand terms, category head terms, product-specific terms, and high-intent commercial queries where competitive visibility directly impacts pipeline. If not provided, defaults to keywords from brand context profile, any tracked keyword lists from previous keyword-research or seo-audit commands, and competitor overlap terms identified during baseline collection
- **Time period for social listening data**: The date range for social mention volume and sentiment analysis — e.g., "last 30 days", "Q4 2025", "January 2026", "trailing 90 days". Longer periods smooth out event-driven spikes and produce more reliable SOV percentages that reflect sustained presence rather than momentary virality. If not specified, defaults to the trailing 30 days
- **Comparison period (optional)**: A previous time period to compare against for trend analysis — e.g., "previous 30 days", "same period last year", "last quarter". Enables delta reporting showing SOV gains and losses per dimension per competitor, surfacing competitive momentum shifts and identifying which entities are gaining or losing ground

## Process

1. **Load brand context and load competitor baselines**: Read `~/.claude-marketing/brands/_active-brand.json` for the active slug, then load `~/.claude-marketing/brands/{slug}/profile.json`. Apply brand positioning, target market definitions, and competitive landscape context. Load existing competitor baselines and monitoring data from competitor-tracker.py to pull saved competitor profiles, tracked keyword lists, and any previous SOV measurements for trend comparison. If a comparison period was specified, retrieve the SOV snapshot from that period for delta calculation. Check for agency SOPs at `~/.claude-marketing/sops/`. If no brand exists, ask: "Set up a brand first (/digital-marketing-pro:brand-setup)?" — or proceed with defaults.
2. **Calculate organic keyword SOV**: For each target keyword in the keyword set, determine the brand's current ranking position and every competitor's ranking position using available search ranking data. Weight each keyword by its monthly search volume to reflect actual visibility impact — a position 3 ranking on a 50,000 volume keyword contributes more to SOV than a position 1 on a 500 volume keyword. Calculate a visibility score per position using a click-through-rate-based model — position 1 receives 100% visibility, position 2 approximately 65%, position 3 approximately 45%, position 4 approximately 30%, position 5 approximately 22%, scaling down through position 10 at approximately 10%, with page 2 and beyond receiving 0% visibility. For each entity (the brand and each competitor), sum the visibility-weighted scores across all keywords in the set and express as a percentage of the total available visibility pool. The result is organic SOV — the share of total organic search visibility each entity captures across the tracked keyword universe.
3. **Calculate paid SOV**: Pull auction insights data from Google Ads MCP for the target keyword set — impression share (percentage of eligible impressions actually won), overlap rate (how often each competitor's ads appeared alongside the brand's), outranking share (percentage of auctions where the brand's ad ranked above each competitor's), and top-of-page rate (percentage of impressions appearing above organic results). Aggregate these metrics into a paid search SOV score per entity that reflects both visibility volume and competitive positioning quality. If Meta Ads data is available via the Meta Ads MCP, incorporate impression share, estimated reach metrics, and audience overlap data for segments relevant to the brand's target market. Combine search and social ad metrics into a weighted paid SOV score reflecting total paid visibility across platforms.
4. **Calculate social SOV**: Pull mention volume and sentiment data from Brandwatch MCP for the brand and each competitor over the specified time period. Calculate raw volume share — each entity's total mention count as a percentage of the combined mention volume across all tracked entities, representing pure share of conversation. Then calculate sentiment-weighted share — multiply each entity's volume share by their average sentiment score on a normalized scale (positive mentions weighted at 1.5x, neutral at 1.0x, negative discounted to 0.5x) to produce a quality-adjusted social SOV that rewards brands generating positive conversation, not just high volume. Report both raw and sentiment-weighted social SOV to surface cases where a competitor has high volume but poor sentiment, indicating controversy rather than strength.
5. **Calculate AI visibility SOV**: Use GEO audit data from geo-tracker.py to compare brand versus competitor citation rates and recommendation frequency across AI engines — ChatGPT, Gemini, Perplexity, and Copilot. For each entity, calculate the percentage of AI-generated responses to category-relevant queries that cite, recommend, or reference them by name. Express as AI SOV — the share of AI engine visibility each entity captures in the category. Weight by AI engine market share where data is available (e.g., ChatGPT citations weighted higher than smaller engines). If GEO data is not available for all competitors, flag the data gap explicitly and provide SOV calculations based on available data with confidence level indicators noting which competitors have incomplete AI visibility profiles.
6. **Aggregate into unified SOV dashboard**: Combine all dimension-specific SOV scores into a unified competitive visibility assessment. Calculate per-