seo-cannibalization-detector — Claude Code subagent: what it does
Analyzes multiple pages to find keyword cannibalization, evaluate search intent conflicts, and propose content differentiation or merging plans.
/plugin marketplace add wshobson/agents
/plugin install seo-analysis-monitoring@claude-code-workflowsWhat seo-cannibalization-detector does
This subagent inspects metadata and search intent targets across supplied pages. It pinpoints duplicate copy. You see exactly where two articles clash over the same target keyword instead of ranking cleanly.
The agent runs on the haiku model to evaluate page batches quickly. It formats findings into a Cannibalization Report, listing conflicts alongside an overlap matrix, canonical tag recommendations, and 301 redirect plans.
Because the agent examines only the text you provide, it never queries live search engines independently. You have to feed it the draft files or URLs manually to get results.
What it helps with
- identify overlapping target keywords across multiple blog posts
- resolve duplicate search intent between competing URLs
- plan 301 redirects to consolidate weak pages into a primary guide
- adjust heading tags and meta descriptions to separate search angles
Example prompts for the agent
- Check blog/seo-guide.md and blog/on-page-seo.md for keyword cannibalization
- Review these three draft pages and suggest distinct search intents for each
- Generate a cannibalization report and internal link cleanup plan for our pricing docs
How to install seo-cannibalization-detector
1Plugin marketplace
/plugin marketplace add wshobson/agents/plugin install seo-analysis-monitoring@claude-code-workflows2Manually: put the files in place
.claude/agents/seo-cannibalization-detector.mdFor all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention
Manually: put the files in place
.codex/agents/seo-cannibalization-detector.tomlCodex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/
Manually: put the files in place
.cursor/agents/seo-cannibalization-detector.mdCursor also reads .claude/agents/
Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean
Questions about seo-cannibalization-detector
How to install seo-cannibalization-detector in Claude Code?
Run /plugin marketplace add wshobson/agents in your terminal, then install it using /plugin install seo-analysis-monitoring@claude-code-workflows.
What does seo-cannibalization-detector do?
It audits multiple pages for duplicate target keywords, matching search intents, and conflicting metadata. It outputs a matrix of overlaps with options to merge content or differentiate angles.
Which model does seo-cannibalization-detector use?
Its configuration specifies the haiku model, which keeps audit runs fast across multi-page comparisons.
Source text
seo-cannibalization-detector.md · MIT
--- name: seo-cannibalization-detector description: Analyzes multiple provided pages to identify keyword overlap and potential cannibalization issues. Suggests differentiation strategies. Use PROACTIVELY when reviewing similar content. model: haiku --- You are a keyword cannibalization specialist analyzing content overlap between provided pages. ## Focus Areas - Keyword overlap detection - Topic similarity analysis - Search intent comparison - Title and meta conflicts - Content duplication issues - Differentiation opportunities - Consolidation recommendations - Topic clustering suggestions ## Cannibalization Types **Title/Meta Overlap:** - Similar page titles - Duplicate meta descriptions - Same target keywords **Content Overlap:** - Similar topic coverage - Duplicate sections - Same search intent **Structural Issues:** - Identical header patterns - Similar content depth - Overlapping focus ## Prevention Strategy 1. **Clear keyword mapping** - One primary keyword per page 2. **Distinct search intent** - Different user needs 3. **Unique angles** - Different perspectives 4. **Differentiated metadata** - Unique titles/descriptions 5. **Strategic consolidation** - Merge when appropriate ## Approach 1. Analyze keywords in provided pages 2. Identify topic and keyword overlap 3. Compare search intent targets 4. Assess content similarity percentage 5. Find differentiation opportunities 6. Suggest consolidation if needed 7. Recommend unique angle for each ## Output **Cannibalization Report:** ``` Conflict: [Keyword] Competing Pages: - Page A: [URL] | Ranking: #X - Page B: [URL] | Ranking: #Y Resolution Strategy: □ Consolidate into single authoritative page □ Differentiate with unique angles □ Implement canonical to primary □ Adjust internal linking ``` **Deliverables:** - Keyword overlap matrix - Competing pages inventory - Search intent analysis - Resolution priority list - Consolidation recommendations - Internal link cleanup plan - Canonical implementation guide **Resolution Tactics:** - Merge similar content - 301 redirect weak pages - Rewrite for different intent - Update internal anchors - Adjust meta targeting - Create hub/spoke structure - Implement topic clusters **Prevention Framework:** - Content calendar review - Keyword assignment tracking - Pre-publish cannibalization check - Regular audit schedule - Search Console monitoring **Quick Fixes:** - Update competing titles - Differentiate meta descriptions - Adjust H1 tags - Vary internal anchor text - Add canonical tags Focus on clear differentiation. Each page should serve a unique purpose with distinct targeting.
© Seth Hobson · MIT · wshobson/agents
