openseo-competitor-analysis
Deep-dive ONE competitor's organic footprint — exact ranking keywords and URLs, content themes, backlink profile, and exploitable gaps — with findings written into brand/competitors.md. Use this skill
SKILL.mdskills/openseo-competitor-analysis/SKILL.md
GitHubOpenSEO Competitor Analysis
Analyze one competitor deeply enough to decide what to learn from, avoid, counter-position against, or outrank. Findings merge into brand/competitors.md — mktg's competitor memory that competitive-intel maintains qualitatively and this skill now grounds in measured rows.
On Activation
- Readiness + binding:
mktg seo status --json --fields readiness,catalog.endpointError,project.not_configured→ hand off tocompetitive-intel(Exa qualitative), labeling metricsunknown. For a ready state, verify live access with the freewhoamiMCP tool before paid calls. - Brand grounding: read
brand/competitors.md+brand/positioning.md(tolerate templates). If the competitor isn't named, ask — never guess the domain.
OpenSEO MCP Tools
get_domain_overview: baseline organic traffic + keyword count (both domains when comparing).get_ranked_keywords: exact keyword/URL/rank/intent/traffic rows. UsemaxRank,minSearchVolume,excludeBrandTerms,resultTypesfilters to keep rows relevant.get_backlinks_overview: backlink/referring-domain profile (may be unavailable — continue without it).get_backlinks_profile: link-level sources, anchors, authority/spam signals, and lost/broken state when the decision needs more than a summary. Preserve target scope and pagination.find_serp_competitors: validate the named competitor actually overlaps in search.get_serp_results: head-to-head SERP checks for the important shared terms.get_search_console_performance: when comparing to the user's domain and GSC is connected, the USER's baseline is first-party — never estimate your own side from third-party data.research_keywords: expand gap terms.
Workflow
get_domain_overviewfor the competitor (and the user's domain when comparing).get_ranked_keywordsfor the competitor with sensible filters; same for the user, orget_serp_resultsfor shared terms when a lighter check suffices.find_serp_competitorswhen the supplied competitor's search overlap is unclear.- Group keywords into themes: product/category, alternatives/comparisons, templates/tools, educational guides, branded demand.
get_backlinks_overviewwhen authority appears to explain rankings.get_serp_resultsfor the important head-to-head terms.- Synthesize the plan: what they do well, where they're vulnerable, which pages/keywords to pursue, what NOT to copy.
- Merge into
brand/competitors.md(preserve existing sections; date the entry; confirm before overwriting populated competitor entries). - Hand off:
competitor-alternativesfor "X vs Y" pages,seo-contentfor gap-driven briefs,openseo-keyword-clusteringfor page mapping.
Output Format
Start with: snapshot, biggest lesson, best opportunity to beat them. Then:
| Area | Competitor pattern | Evidence | OpenSEO opportunity |
|---|
Anti-Patterns
- Treating every competitor keyword as desirable — because ranking for a term and PROFITING from a term are different things; filter through positioning before anything lands in a plan.
- Inferring page-level content strategy from keyword rows alone — because a keyword list can't tell you WHY a page works (structure, depth, format). Use SERP/web evidence for page-level claims.
- Estimating the user's own performance from third-party data when GSC exists — because first-party clicks/impressions/position are free and exact; third-party estimates of your own site are the worst data in the room.
- Recommending "copy what they do" — because imitation pages lose to the original on authority and freshness. Recommend a stronger angle on the same intent, never a replica.
- Separating evidence from inference nowhere — because "they rank for X" (evidence) and "their content strategy is Y" (inference) carry different confidence and must read differently in
brand/competitors.md.
Close the loop
After writing files, log completion so mktg plan / mktg status count the work (bare mktg run only logs loaded):
mktg run openseo-competitor-analysis --complete --writes <paths written> --result success --json
Adapted from every-app/open-seo .agents/skills/competitor-analysis (MIT). Workflow upstream; mktg brand-memory writes and handoff wiring added here.