Category Dominance Matrix

What it does

Map and analyze brand dominance across different category clusters based on keyword and description signals, computing rank-weighted share per brand in each cluster, and classifying market concentration.

Execution Contract

Every execution of this skill must operate under the following contract:
- **ingestion_plan**: A documented plan for pulling data.
- **max_api_calls**: 3 (default, strictly enforced).
- **cache_key**: A unique key identifying the cached API dataset.
- **dataset_timestamp**: ISO timestamp of the ingested dataset.
- **analysis_mode**: `offline_only`

Data Access Policy

• API Target: Consume data from the FullMention API at GET /v2/runs/{runId}.
• Controlled Ingestion: Perform exactly one controlled ingestion pull from the FullMention API. Paginated batch fetching is preferred.
• API Decoupling: Do NOT treat the FullMention API as a persistent database or state-store; it is a read-only snapshot provider.
• 24-Hour TTL: FullMention v2 deletes run data after 24 hours, meaning offline persistence/database caching is a strict requirement for historical tracking.
• Local Persistence: Save all analytical outputs locally in the current workspace directory.
  • Raw structured JSON must be saved to [skill_name].json (e.g. category-dominance-matrix.json).
  • A premium, beautifully styled markdown report must be saved to [skill_name].md (e.g. category-dominance-matrix.md).
• Caching: Reuse the same stored dataset across iterative prompts. Do not repeat identical API calls.
• Refresh Window: Make additional API calls only if the user explicitly requests a refresh window or a missing page fetch.
• Rate Limits & Backoff: Respect API rate limits and backoff policies. Never run open-ended call loops.
• Allowed Sources:
  • Local working dataset produced from one ingestion pull of FullMention API data.
  • Optional user-provided local file/DB snapshot (read-only).
  • No repeated API fetching during analysis.

Required Input Fields & Parameters

The input dataset from the API/file must map to these fields:

• keyword (string, searched keyword)
• categorySuggestions[] (array of strings, suggested categories)
• brandRankings[].name (string, brand name)
• brandRankings[].position (integer, brand rank position)

Analytical Method

Follow these step-by-step logic rules during analysis:

1. Category Clustering: Group results directly using the categories listed in the root-level categorySuggestions[] array of strings (e.g. mapping keywords under suggested categories).
2. Rank-Weighted Share Computation: For each category cluster, calculate the rank-weighted Share of Voice (SOV) for each brand using the reciprocal position formula in brandRankings[]: $$\text{weightedScore} = \sum \frac{1}{\text{position}}$$ Convert each brand’s score to a percentage share of the total weighted score within that specific category cluster.
3. Dominance Classification: For each cluster, classify the overall dominance of the leading brands:
   • strong: A single leading brand holds a dominant share ($> 40%$ SOV) and a significant lead over the runner-up.
   • moderate: The top brands have closely competing, moderate shares (e.g., multiple brands with $20% - 30%$ SOV).
   • fragmented: No brand holds a meaningful share, with citations spread thinly across many brands.

Expected Output

The skill must generate two outputs in the local workspace:

1. category-dominance-matrix.json: Contains the raw structured analytical output, including the execution contract metadata, category matrix data with top brands and calculated shares, dominance classifications, confidence metrics, and the evidence map.

2. category-dominance-matrix.md: A premium, beautiful human-readable report. This report must contain:

   • Category Dominance Matrix: Formatted grid table displaying categories as rows, with columns for Top Brand, SOV Share %, Runner Up, Runner Up Share %, and Dominance Class (Strong | Moderate | Fragmented).
   • Key Strategic Opportunities: Analysis of fragmented or weakly defended clusters where the target brand can easily gain dominance.
   • Confidence & Limitations:
     • A confidence score from 0-100.
     • Confidence Rationale: Explanation of how the confidence score was derived.
     • Limitations: A list of data limitations or gaps.
   • Evidence Map: An array of objects evidence_map[] with:
     • finding_id
     • metric_name
     • source_field_paths[]
     • sample_result_ids[]

Guardrails & Constraints

• Low Confidence Fallback: If semantic clustering confidence is low or keywords are highly diverse, fallback to fewer, broader clusters to ensure statistical accuracy.
• No External Taxonomy Lookups: Do not use external taxonomy lookups or semantic categorization services unless explicitly supplied by the user as a local file or parameter.
• No Web Lookups: Do not perform external web lookups or enrichment of brand data.
• No Hallucination: Do not invent brands, rankings, keywords, or timestamps that are not present in the ingested dataset.

Copy-ready Skill Prompt

Use this as a full copy/paste prompt in your AI tool:

Skill: Category Dominance Matrix
Goal: Map brand dominance by category clusters.

Data Access Policy:
- **API Target**: Consume data from the FullMention API at `GET /v2/runs/{runId}`.
- **Controlled Ingestion**: Perform exactly one controlled ingestion pull from the FullMention API. Paginated batch fetching is preferred.
- **API Decoupling**: Do NOT treat the FullMention API as a persistent database or state-store; it is a read-only snapshot provider.
- **24-Hour TTL**: FullMention v2 deletes run data after 24 hours, meaning offline persistence/database caching is a strict requirement for historical tracking.
- **Local Persistence**: Save all analytical outputs locally in the current workspace directory.
  - Raw structured JSON must be saved to `[skill_name].json` (e.g. `category-dominance-matrix.json`).
  - A premium, beautifully styled markdown report must be saved to `[skill_name].md` (e.g. `category-dominance-matrix.md`).
- **Caching**: Reuse the same stored dataset across iterative prompts. Do not repeat identical API calls.
- **Refresh Window**: Make additional API calls only if the user explicitly requests a refresh window or a missing page fetch.
- **Rate Limits & Backoff**: Respect API rate limits and backoff policies. Never run open-ended call loops.
- **Allowed Sources**:
  - Local working dataset produced from one ingestion pull of FullMention API data.
  - Optional user-provided local file/DB snapshot (read-only).
  - No repeated API fetching during analysis.

Input Fields & Params:
The input dataset from the API/file must map to these fields:
- `keyword` (string, searched keyword)
- `categorySuggestions[]` (array of strings, suggested categories)
- `brandRankings[].name` (string, brand name)
- `brandRankings[].position` (integer, brand rank position)

Method:
Follow these step-by-step logic rules during analysis:
1. **Category Clustering**: Group results directly using the categories listed in the root-level `categorySuggestions[]` array of strings (e.g. mapping keywords under suggested categories).
2. **Rank-Weighted Share Computation**: For each category cluster, calculate the rank-weighted Share of Voice (SOV) for each brand using the reciprocal position formula in `brandRankings[]`:
   $$\text{weightedScore} = \sum \frac{1}{\text{position}}$$
   Convert each brand's score to a percentage share of the total weighted score within that specific category cluster.
3. **Dominance Classification**: For each cluster, classify the overall dominance of the leading brands:
   - `strong`: A single leading brand holds a dominant share ($> 40\%$ SOV) and a significant lead over the runner-up.
   - `moderate`: The top brands have closely competing, moderate shares (e.g., multiple brands with $20\% - 30\%$ SOV).
   - `fragmented`: No brand holds a meaningful share, with citations spread thinly across many brands.

Expected Output:
The skill must generate two outputs in the local workspace:

1. **`category-dominance-matrix.json`**:
   Contains the raw structured analytical output, including the execution contract metadata, category matrix data with top brands and calculated shares, dominance classifications, confidence metrics, and the evidence map.

2. **`category-dominance-matrix.md`**:
   A premium, beautiful human-readable report. This report must contain:
   - **Category Dominance Matrix**: Formatted grid table displaying categories as rows, with columns for `Top Brand`, `SOV Share %`, `Runner Up`, `Runner Up Share %`, and `Dominance Class` (Strong | Moderate | Fragmented).
   - **Key Strategic Opportunities**: Analysis of fragmented or weakly defended clusters where the target brand can easily gain dominance.
   - **Confidence & Limitations**:
     - A confidence score from 0-100.
     - **Confidence Rationale**: Explanation of how the confidence score was derived.
     - **Limitations**: A list of data limitations or gaps.
   - **Evidence Map**: An array of objects `evidence_map[]` with:
     - `finding_id`
     - `metric_name`
     - `source_field_paths[]`
     - `sample_result_ids[]`

Guardrails:
- **Low Confidence Fallback**: If semantic clustering confidence is low or keywords are highly diverse, fallback to fewer, broader clusters to ensure statistical accuracy.
- **No External Taxonomy Lookups**: Do not use external taxonomy lookups or semantic categorization services unless explicitly supplied by the user as a local file or parameter.
- **No Web Lookups**: Do not perform external web lookups or enrichment of brand data.
- **No Hallucination**: Do not invent brands, rankings, keywords, or timestamps that are not present in the ingested dataset.