competitor-seo-analysis
Skill0 starsChanged 33 days agoMITView on GitHub
Compare competitors' sampled Google rankings, estimated organic traffic, backlink samples and public page metadata. Use for competitor SEO research, search visibility comparisons and content gaps. Preserve provider, geography, language, device and query scope; label estimates and unavailable metrics explicitly.
In this repository6 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 0 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
Use scrape-google-serp for a bounded same-query search panel and discovery evidence.
- Very specific: line 12
Use keyword-rank-tracker only when its managed provider access is actually available.
- Very specific: line 13
Use website-backlink-checker for a bounded sample or labelled summary.
- Very specific: line 14
Use website-seo-spider for page-only or tightly bounded raw-HTML metadata.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Competitor SEO analysis
Turn search evidence into a prioritized set of hypotheses. Reuse supplied exports and accepted competitor identities. Follow execution.md for live runs and actors.json for the relevant contracts.
- Use
scrape-google-serpfor a bounded same-query search panel and discovery evidence. Count organic rankings consistently; paid placements are separate. An absent domain within collected depth is "not observed in this sample", not "unranked everywhere". - Use
similarweb-alternativefor up to three domains initially.organicEtvis estimated Google organic traffic from the provider's index, not measured website sessions or total visits.visitsis available only when the upstream Similarweb feed exists; do not fill it withorganicEtv.mode: free_tieris an Actor input label and does not make the run free. - Use
keyword-rank-trackeronly when its managed provider access is actually available. Set location, language, device, OS, keywords and depth explicitly. Never request or expose provider passwords in shared files; if managed access is unavailable, retain the sample SERP evidence and report the narrower coverage. - Use
website-backlink-checkerfor a bounded sample or labelled summary. A sample of five referring pages is not the site's total backlinks. Index scores are provider-specific and not interchangeable with another service's authority score. - Use
website-seo-spiderfor page-only or tightly bounded raw-HTML metadata. Its titles, H1s and issue flags support on-page observations; they do not measure conversion, browser-rendered behavior or revenue.
Save context fields with every observation: provider, country/location, language, device, OS, keywords, result depth, period basis and collection method where relevant. Compare history only within the same panel. Provider or scope changes need a new baseline, and sparse coverage cannot justify an overall winner.
Deliver the evidence table, a short content/keyword gap list, contrary evidence and three prioritized research or content actions with a rationale. Search performance estimates and suggested work do not promise future rankings or traffic gains. Save the panel for a later manual refresh using evidence-contract.md.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

