Benchmark rivals and close the gaps in code, with your agent
Benchmarks your site against search and AI-citation rivals across clickd’s rulebook, topic gaps, backlinks and assistant citations, then closes the rule gaps or builds honest /vs/ comparison pages in code.
Add it, from the top of the site’s repositorynpx skills add subinternal/clickd --skill clickd-competitor-seo
Then ask your agentCompare example.com against our top three rivals with clickd, show every rule and topic they beat us on, and fix the top rule gaps in our repo.
For founders, marketers and developers competing in an established categoryCompare two sites
Four steps from rival benchmark to closed gaps
Your agent compares your site against rivals across rules, topics, backlinks and AI citations, then fixes template gaps or builds fair /vs/ pages.
1Benchmark the site against its real rivalsclickd_rivals
2Separate technical and structural gaps from content and authority gaps
3Build honest `/vs/` comparison pages or close the rule gaps in code
4Check live with clickdclickd_check
Side-by-side rival benchmark
Separating rulebook fixes you can ship in code today from topic and comparison pages.
example.com vs top 2 rivals
Rulebook, topic gap and AI citation comparison from clickd_rivals.
Sample
Rulebook gaps (view: "rules")Rivals pass Product/Software schema, entity sameAs and answer-first H2sClosed all 3 rule gaps in example.com shared templates
Topic gaps (clickd_gaps)Rivals cover SOC 2 automation and ERP migration checklistsQueued 2 fact-backed guides in clickd_content_brain
Comparison page (/vs/)No comparison page for “example vs rival” searchesBuilt /vs/rival with date-stamped facts and a clear “When to pick Rival” section
AI citations & backlinksRivals cited on 5 buyer questions via 3 industry directoriesListed exact referring domains and questions from clickd_backlinks & clickd_citations
How clickd compares rivals honestly
Every site is graded by the same public rulebook and real assistant questions.
clickd_rivals (views: rules, content, near, market)Compares your site and any rival rule by rule and topic by topic.
clickd_gaps & clickd_backlinksShows which buyer subjects and external referring domains rivals have that your site lacks.
clickd_citationsReveals which rivals AI assistants name for buyer questions in your market and why.
When to reach for it
Reach for it when
A competitor outranks you or gets cited by AI assistants when your site is left out.
You want to build /vs/<competitor> or <competitor> alternatives pages grounded in verifiable facts.2,1
You want to see which referring domains and topics your closest rivals have that you lack.
Leave it when
You want a comparison page that claims your product wins every single row and hides trade-offs.
You have not scanned your own site yet: start with the clickd skill first.
More things to ask your agent
Everyday prompts that load the Competitor SEO skill in Claude Code, Codex or Cursor.
Rule-by-rule rival diffCompare example.com against our top 3 rivals with clickd_rivals (view: "rules" and "content") and fix the rules they beat us on.
Build an honest /vs/ pageBuild a /vs/rival comparison page in our repo with date-stamped facts, a comparison table, and when each product is the better fit.
Backlink & citation gap listPull clickd_backlinks and clickd_citations for our rivals and list the directories and third-party pages citing them.
Competitor SEO skill vs the alternatives
Why pairing an open repository skill with a live crawler beats manual audits and prompt-only checklists.
How it reads your siteBy hand: Manual spot-checks in a browser · Prompt-only skill: Reads local source files only; misses live headers, redirects and JS shellsReads the live URL, HTTP headers, raw HTML and Search Console via clickd MCP
How changes are madeBy hand: Copy-pasting between docs, spreadsheets and editors · Prompt-only skill: Suggests generic copy in chat with no repo contextEdits your actual templates, routes and schema in the repository
How fixes are provedBy hand: Checking pages one by one after deploy · Prompt-only skill: Agent grades its own homework with no live checkRuns clickd_rescan and clickd_changes on the deployed site to prove rules passed
Skills to use alongside it
Included when you run npx skills add subinternal/clickd.
Keyword researchFinds striking-distance keywords (positions 4 to 20), CTR gaps, cannibalized queries and competitor topic gaps using Google Search Console data and clickd, then maps each query to one page and one action.See skill
Content briefTurns competitor topic gaps and customer questions from clickd’s content brain into fact-backed briefs and finished pages in your repo, complete with question headings, internal links and JSON-LD schema.See skill
AI visibilityAudits and fixes your site’s visibility in ChatGPT, Claude, Perplexity and Google AI Overviews: AI crawler access, non-JS HTML readability, answer-first passages, entity sameAs schema and live citation tracking.See skill
Questions about the Competitor SEO skill
Why does the skill insist on stating when a competitor is the better choice?
Buyers and AI assistants immediately discount one-sided comparison tables where the author’s product wins every row. Naming the specific use cases where a rival fits better makes the rest of your comparison credible and quotable.
Can it compare both SEO rules and AI assistant citations?
Yes. It combines clickd_rivals (rulebook and topic coverage), clickd_backlinks (referring domains) and clickd_citations (which rivals AI assistants recommend on buyer questions).
Install it by hand
The line at the top adds it for any agent. Or fetch its 1 files where your agent looks. Your agent also needs clickd connected over MCP: connecting an agent shows how.
Loads skills from .claude/skills/ in the repository, for everyone who works in it, or ~/.claude/skills/ for every project on your machine. Claude uses it when a request matches its description, or type /clickd-competitor-seo.
Puts the files in .claude/skills/clickd-competitor-seo/.
Loads skills from .agents/skills/ in the repository and its parent folders, or ~/.agents/skills/ for every project. Codex uses it when a task matches its description, or mention it as $clickd-competitor-seo; /skills lists them.
Puts the files in .agents/skills/clickd-competitor-seo/.
Loads skills from .cursor/skills/ or .agents/skills/ in the repository, or ~/.cursor/skills/ for every project. It also reads .claude/skills/, so one copy there serves both. The agent uses it when it is relevant, or type / in Agent chat and pick it.
Puts the files in .cursor/skills/clickd-competitor-seo/.
An agent that does not load skills can still follow the file. Save the folder in the repository and point its standing instructions at it, with a line in AGENTS.md, which many agents read. The agent reads AGENTS.md when it starts, and follows the file when the task matches.
SKILL.md stays short and sends your agent to a reference when a step needs it.
SKILL.mdThe four steps from benchmarking rivals across rules, topics, backlinks and citations to ranking the gaps, building honest /vs/ pages or fixing templates in code, and verifying live.85 lines