competitor-analysis
Skill2 starsChanged 52 days agoMITView on GitHub
Analyze one competitor's organic footprint, ranking keywords, content themes, backlinks and gaps, and decide what to learn from, counter or outrank. Use when the user names a competitor to study.
- Reads credentials
64 other projects use a version of this, 10 of them edited.
Adopted by
Most recently taken up by
- Kuan-AI-com/agent-skillstheir own version, first seen Nov 15, 2026
- asospy/asospy-agent-skillstheir own version, first seen Nov 15, 2026
- oivanfelipe/claude-skillstheir own version, first seen Nov 8, 2026
- alunadev/ald-skillstheir own version, first seen Nov 8, 2026
- foverse/seoverseedited, first seen Nov 8, 2026
- AppKittie/aso-mcp-skillstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use openseo-release-notes, openseo-review-web-content and 2 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
JwuthriSkillopenseo-release-notes
Cut an OpenSEO release — bump the version, draft user-facing release notes from commits since the last tag, run a review + subagent-verification pass, and open a "release: vX.X.X" PR. Use when the user asks to prepare a release, bump the version, or write release notes.
Also in 6 projects that use this
JwuthriSkillopenseo-review-web-content
Write and review content for the OpenSEO website (web/) — blog posts, guides, feature pages, FAQs. Distills the philosophy for on-brand, useful, accurate content. Use whenever adding or editing user-facing prose in web/content or web/src.
Also in 5 projects that use this
- +2 more from Jwuthri
Other versions64 projects use a version of this.
Word for word · 0
None found.
Edited · 10
- every-app/open-seo★ 27k56% same
- Jwuthri/Tracely-ai★ 1.3k48% same
- VladSez/easy-invoice-pdf★ 1.1k48% same
- jwuthri-cloud/Tracely-ai★ 97948% same
- petera2c/simple-table★ 23348% same
- foverse/seoverse★ 456% same
- ventra-rocket/EchoSEO★ 248% same
- winsley-jeune/harborrank-skills★ 215% same
- ictlondon/kraftskills★ 046% same
- IsaacBell/ai-marketing-toolkit★ 048% same
Wrote their own version · 54
- langchain-ai/deepagents★ 31ksame name
- browserbase/agent-browse★ 3.7ksame name
- indranilbanerjee/digital-marketing-pro★ 934same name
- OpenClaudia/openclaudia-skills★ 731same name
- vivy-yi/xiaohongshu-skills★ 455same name
- itseffi/agentic-os★ 114same name
- cognyai/claude-code-marketing-skills★ 106same name
- Infinite-Labs-AI/infinite-skills★ 43same name
- yuanhao667/Skills★ 10same name
- AppKittie/aso-mcp-skills★ 8same name
44 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- competitive-landscapeSkill
- keyword-clusteringSkill
- keyword-researchSkill
- link-prospectingSkill
- local-seoSkill
- seo-auditSkill
- seo-coachSkill
- seo-project-setupSkill
- seo-reportSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
16 rules. 0 are common, 4 are distinctive, and 12 are very specific to this project.
0
Common
Most of the 53 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
12
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Use this for a named competitor.
- Very specific: line 16
Use the installed agenticseo command.
- Very specific: line 26
Run agenticseo context first and ground the analysis in it: the saved competitors say whether this domain is already known and what was …
- Very specific: line 28
Before paying, check researchLog.
- Very specific: line 48
Run agenticseo domain for the competitor, passing --location/--language when the user gave a market.
- Very specific: line 49
If comparing to the user, run agenticseo domain for the user's domain too, and if Search Console is connected, agenticseo gsc report or …
- Very specific: line 50
Run agenticseo ranked for the competitor, filtered to relevant rows.
- Very specific: line 51
If comparing to the user, run agenticseo ranked for the user's domain or page too, or agenticseo serp for the shared terms when a lighter …
- Very specific: line 53
Run agenticseo competitors when the competitor was supplied by the user but its search overlap is unclear.
- Very specific: line 61
Run agenticseo backlinks overview for the competitor, especially if authority appears to explain rankings.
- Very specific: line 62
Use agenticseo serp for important shared or target keywords to compare positioning, with the market the user gave.
- Very specific: line 73
If a report template applies (see seo-report), its sections and tone replace this list.
- Distinctive: line 87
Do not treat all competitor keywords as desirable.
- Distinctive: line 89
Do not infer competitor page or content-type patterns from keyword rows alone.
- Distinctive: line 91
Do not recommend copying content.
- Distinctive: line 92
If the user's domain is unavailable, frame the analysis as competitor-only.
“Common” is measured: kept by at least 6 in 10 of the 53 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
<!-- Adapted from OpenSEO plugins/openseo/skills/competitor-analysis/SKILL.md (https://github.com/every-app/open-seo, MIT, Copyright (c) 2026 Ben Senescu) for the AgenticSEO CLI. -->Competitor analysis
Goal
Analyze one competitor deeply enough to decide what to learn from, avoid, counter-position against or outrank.
Use this for a named competitor. To identify the market leaders first, use competitive-landscape.
Use the installed agenticseo command. Research lookups are billed by DataForSEO and need DATAFORSEO_API_KEY; each result states its cost and points to an evidence file.
Required inputs
- The competitor domain
- The user's domain when a comparison is requested (the project domain by default)
- Optional topic, category, location or language
Project context
- Run
agenticseo contextfirst and ground the analysis in it: the saved competitors say whether this domain is already known and what was concluded about it before. If there is no project, set one up asseo-project-setupstep 1 describes. - This skill needs competitors. If none are saved, run a minimal inline setup: add the competitor being analyzed to
competitorsin.agenticseo/context.json, and ask the user (or infer fromagenticseo competitorsand confirm) whether there are others. Then continue. Never front-load the full interview; suggestseo-project-setupat the end for the rest. - Before paying, check
researchLog. If the same research ran within the last 30 days, reuse its evidence and say so instead of buying it again. - On finish, write back what is durable: upsert this domain in
competitorswith a shortnotesline on its strengths and where it is vulnerable, and append{ "entryDate": "<today from agenticseo context>", "summary": "Competitor analysis: <domain>. Verdict: <conclusion>. Evidence: <paths>" }toresearchLog. Runagenticseo contextto validate.
Deliver as a report
Deliver through the seo-report skill. If that skill is not available, say so and stop before writing the report.
Commands
agenticseo domain DOMAIN: baseline organic traffic and keyword count.agenticseo gsc performance: when comparing to the user's own domain and Search Console is connected, the first-party baseline (real clicks, impressions, CTR, position) instead of estimating the user's own performance from third-party data. It exits 2 when not connected.agenticseo ranked DOMAIN: exact keyword, URL, rank, intent, traffic, CPC and SERP-type rows for the competitor domain or page. Use--max-rank,--min-volume,--exclude BRAND,...and--types organicto keep rows relevant;--scope exact_urlwith an absolute URL for one page.agenticseo backlinks overview DOMAIN: backlink and referring-domain profile.agenticseo competitors KEYWORD...: validate whether the named competitor is a real search competitor across the target keyword set.agenticseo local businesses,agenticseo local serpandagenticseo local questions: for local SEO competitors, when Maps or local-pack visibility, nearby businesses, categories or Google Q&A matter.agenticseo serp "QUERY"...: validate head-to-head SERPs for important keywords, up to 10 queries per call.agenticseo research "SEED"...: expand gaps or category terms when needed.
Workflow
- Run
agenticseo domainfor the competitor, passing--location/--languagewhen the user gave a market. - If comparing to the user, run
agenticseo domainfor the user's domain too, and if Search Console is connected,agenticseo gsc reportoragenticseo gsc performancefor the user's real baseline. - Run
agenticseo rankedfor the competitor, filtered to relevant rows. - If comparing to the user, run
agenticseo rankedfor the user's domain or page too, oragenticseo serpfor the shared terms when a lighter check is enough. - For local SEO, run
agenticseo local businessesandagenticseo local serparound the relevant business location(s) before drawing local-pack conclusions. Addagenticseo local questionsonly when Q&A evidence matters. - Run
agenticseo competitorswhen the competitor was supplied by the user but its search overlap is unclear. - Group the competitor's keywords into themes:
- Product/category terms
- Alternatives/comparisons
- Templates/tools/calculators
- Educational guides
- Branded demand
- Local/neighborhood terms when relevant
- Run
agenticseo backlinks overviewfor the competitor, especially if authority appears to explain rankings. Continue without backlink evidence if it fails. - Use
agenticseo serpfor important shared or target keywords to compare positioning, with the market the user gave. - Produce an actionable plan:
- What they are doing well
- Where they are vulnerable
- Which pages and keywords to pursue
- What to avoid copying
Output format
Title: Competitor Analysis: <competitor domain> — <date> (see seo-report).
If a report template applies (see seo-report), its sections and tone replace this list.
Sections in this order:
- Snapshot: one or two opening sentences, then a table of the competitor's organic footprint (traffic estimate, keyword count, referring domains). Add the user's domain as a second row when comparing.
- The biggest lesson: one finding.
- Where they are vulnerable: one finding per opening, ordered by how winnable it is.
- Keyword themes: a table of theme, example keywords, volume and whether the user competes there. A bar chart when a few themes dominate the footprint.
- Content patterns and authority: prose, with a note for anything inferred from keyword rows rather than seen on a page.
- What to do next: an ordered list, shortest useful.
- How this report was made: opens with the skill link line from
seo-report, pointing athttps://github.com/kid7st/agenticseo/blob/main/.agents/skills/competitor-analysis/SKILL.md("AgenticSEO Competitor Analysis skill"), then which commands reported what (with costs and evidence paths), and what you checked yourself.
Guardrails
- Do not treat all competitor keywords as desirable. Filter for business fit.
- Separate evidence from inference.
- Do not infer competitor page or content-type patterns from keyword rows alone; use SERP or web evidence for page-level claims.
- For local SEO, do not infer Maps or local-pack strength from national organic domain metrics alone; use the local commands when the location is known or reasonably discoverable.
- Do not recommend copying content; recommend a stronger angle or a better answer to the same intent.
- If the user's domain is unavailable, frame the analysis as competitor-only.
- Missing metrics are
unknown, never 0. On exit code 3, ask the user to fix the key; on exit code 4, report the error and any charged cost, and do not retry in a loop.
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.

