Analyze competitor content coverage and uncover differentiated content opportunities using web search, page extraction, and DataForSEO content analysis. Use when asked for competitor content research, editorial gap analysis, content brief inputs, or topic whitespace.
npx skills add https://github.com/sandbaseai/sandbase-skills --skill competitor-content-intelligence
Compare public content evidence to identify differentiated editorial and landing-page opportunities. This Skill calls the named search, extraction, and analysis capabilities in the SandBase API map through the SandBase MCP gateway. In a SandBase Agent, run the capabilities directly. In another compatible agent, require an authorized SandBase connection before starting; never request, print, or store an API key in the research output.
Read example workflows when the user needs a starting prompt or wants to understand the output.
Collect or infer: the target audience and their problems, the topic or category, 2–5 competitor domains or brands, the target's positioning and differentiation, content types in scope (blog, landing page, documentation, comparison, tool), and the intended use of findings (content calendar, brief backlog, editorial strategy).
Classify the request as one or more of:
Read the SandBase API map before selecting tools. Use the listed tool_name through the SandBase gateway:
sandbase_describe_tool for the selected tool_name and read its current input schema.sandbase_call_tool with that exact tool_name and only schema-defined arguments.Use exa_search and cloudsway_search to map the competitor content landscape:
| Strategy | Approach |
|---|---|
| Topic coverage | Search for the category + each competitor's domain to find their published content |
| Question targeting | Search for buyer questions in the category and see which competitors answer them |
| Format variety | Search for comparisons, guides, tools, calculators, templates in the category |
| Freshness gaps | Search with date filters to find where competitor content is outdated |
Tips:
include_domains to search within a specific competitor's site.cloudsway_search for broader web coverage that may surface sources Exa doesn't index.Use context_dev_scrape_markdown and dataforseo_v3_on_page_content_parsing_live for deeper analysis:
When to extract full pages:
What to analyze in extracted content:
| Dimension | Questions to answer |
|---|---|
| Depth | How thorough is the coverage? What subtopics are included/excluded? |
| Freshness | When was it last updated? Are examples and data current? |
| Audience | Who is it written for? (beginner/advanced, role, industry) |
| Angle | What perspective or opinion does it take? |
| Format | How is information structured? (listicle, guide, comparison, tutorial) |
| Conversion | What CTA or next step does it offer? |
| Gaps | What questions does a reader still have after reading? |
Use dataforseo_v3_content_analysis_search_live to validate broader patterns:
For each identified opportunity, document:
Return a structured content intelligence brief:
| Topic / Question | Competitor 1 | Competitor 2 | Competitor 3 | Target | Gap type |
|---|---|---|---|---|---|
| ... | ✅ deep | ⚠️ shallow | ❌ absent | ❌ absent | Full gap |
| ... | ✅ deep | ✅ deep | ✅ deep | ⚠️ outdated | Freshness gap |
| ... | ❌ absent | ❌ absent | ❌ absent | ❌ absent | Market gap |
| # | Opportunity | Gap type | Evidence | Audience value | Differentiation angle | Recommended format | Priority |
|---|---|---|---|---|---|---|---|
| 1 | ... | ... | ... | ... | ... | ... | ... |
For the top 3–5 opportunities, provide actionable briefs:
Brief: [Topic]
Observations about competitor content strategy (publishing cadence, preferred formats, topic clusters, content quality trends).
What couldn't be verified, what additional research would help, and confidence levels.
Before delivering, verify that:
Take sandbaseai/competitor-content-intelligence from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.