Cluster Command Build a complete topic cluster strategy with pillar page definition, 8-12 supporting articles, internal linking map, and creation sequence. ## Usage /cluster [topic] Examples: - /cluster "content marketing" - /cluster "podcast monetization" - /cluster "remote team management" ## Process ### Step 1: Gather Existing Data Check for existing research that informs this cluster: 1. Search research/ for any existing /research-topics output: `` Glob: research/topic-clusters-*.md ` 2. Search for any existing research on this topic: ` Glob: research/*[topic-slug]*.md ` 3. If found, extract: - Authority score for this topic area - Keywords already ranking - Coverage gaps identified - Any SERP analysis already done Document what exists vs. what needs fresh research. ### Step 2: Keyword Research Build the complete keyword landscape for this topic. 1. **DataForSEO Keyword Ideas** `bash python3 -c " import sys; sys.path.insert(0, 'data_sources/modules') from dataforseo import DataForSEOClient client = DataForSEOClient() results = client.get_keyword_ideas('$ARGUMENTS') for kw in sorted(results, key=lambda x: x.get('search_volume', 0), reverse=True)[:30]: print(f\"{kw.get('keyword', 'N/A')} | Vol: {kw.get('search_volume', 'N/A')} | Diff: {kw.get('keyword_difficulty', 'N/A')} | CPC: {kw.get('cpc', 'N/A')}\") " ` 2. **DataForSEO Questions** `bash python3 -c " import sys; sys.path.insert(0, 'data_sources/modules') from dataforseo import DataForSEOClient client = DataForSEOClient() results = client.get_questions('$ARGUMENTS') for q in results[:15]: print(f\"{q.get('keyword', 'N/A')} | Vol: {q.get('search_volume', 'N/A')}\") " ` 3. **WebSearch for Additional Keywords** ` WebSearch: "[topic] guide" site:ahrefs.com OR site:semrush.com OR site:moz.com WebSearch: "[topic] related keywords" OR "[topic] subtopics" ` 4. **Group Keywords into Tiers** - **Pillar-level**: Broad, high-volume (1000+ searches/mo), competitive - **Supporting-level**: Specific subtopics, medium volume (100-1000/mo) - **Long-tail**: Very specific queries, low volume (<100/mo), low competition ### Step 3: SERP Analysis Analyze what's winning for the pillar keyword. 1. **Get SERP Data** `bash python3 -c " import sys; sys.path.insert(0, 'data_sources/modules') from dataforseo import DataForSEOClient client = DataForSEOClient() results = client.get_serp_data('$ARGUMENTS') for r in results[:10]: print(f\"Position {r.get('position', 'N/A')}: {r.get('title', 'N/A')}\") print(f\" URL: {r.get('url', 'N/A')}\") print(f\" Description: {r.get('description', 'N/A')[:100]}\") print() " `` 2. Fetch Top 3 Pillar/Guide Pages Use WebFetch on the top 3 ranking comprehensive guides. For each, document: - H2/H3 structure - Word count estimate - Topics covered - Gaps and thin sections - Unique angles or data 3. Identify Differentiation Opportunities - What do all top results miss? - Where are they thin or generic? - What unique angle can we bring? - What data or examples are outdated? ### Step 4: Define Pillar Page Adopt the cluster-strategist agent role (@agents/cluster-strategist.md). Define the pillar page: | Element | Details | |---------|---------| | Title | [Compelling H1 targeting pillar keyword] | | Primary Keyword | [Highest-volume broad term] | | Secondary Keywords | [3-5 related terms] | | Search Intent | [Informational / Commercial Investigation] | | Target Word Count | 3,000-5,000 words | | Differentiation Angle | [What makes ours uniquely valuable] | Pillar Page Outline: - Create full H2/H3 outline - Each H2 should map to a supporting article topic - Include sections that competitors cover (Google-validated structure) - Add sections that fill identified gaps - Note where each supporting article will be linked from ### Step 5: Define Supporting Articles (8-12) For each supporting article, specify: | Field | Value | |-------|-------| | # | [Sequential number] | | Title | [Working title] | | Primary Keyword | [MUST be distinct from all other articles] | | Search Volume | [Monthly volume] | | Keyword Difficulty | [0-100 score] | | Search Intent | [Informational / How-to / Commercial / Comparison] | | Content Angle | [Specific perspective or approach] | | Pillar Relationship | [Which pillar H2 section this expands on] | | Word Count Target | [1,500-3,000] | | Priority Score | [0-100 using prioritization framework] | Prioritization Framework: - Volume (30%): Higher search volume = higher score - Difficulty Inverse (20%): Lower difficulty = higher score - Commercial Intent (20%): Closer to conversion = higher score - Pillar Dependency (15%): More essential to pillar completeness = higher score - Cross-link Va