Community연구 & 데이터 분석github.com

product-seo

Grows search traffic that turns into signups for a product website, working from real Search Console data instead of guesses. Use when the user asks about SEO, organic or search traffic, Google or Bing rankings, Search Console, keyword research, which pages to write, rewrite, merge or remove, titles and meta descriptions (CTR), use-case or landing pages for a specific query, free tools, comparison and alternatives pages, 301 redirects for thin or duplicate pages, backlinks and directory listings, llms.txt or showing up in ChatGPT and other AI search answers, or checking whether an SEO change worked and should be rolled back.

product-seo란 무엇인가요?

product-seo is a Claude Code agent skill that grows search traffic that turns into signups for a product website, working from real Search Console data instead of guesses. Use when the user asks about SEO, organic or search traffic, Google or Bing rankings, Search Console, keyword research, which pages to write, rewrite, merge or remove, titles and meta descriptions (CTR), use-case or landing pages for a specific query, free tools, comparison and alternatives pages, 301 redirects for thin or duplicate pages, backlinks and directory listings, llms.txt or showing up in ChatGPT and other AI search answers, or checking whether an SEO change worked and should be rolled back.

지원 대상✓Claude Code✓Codex CLI~Cursor
npx skills add https://github.com/tipsai/product-seo/tree/HEAD/skills/product-seo

Installed? Explore more 연구 & 데이터 분석 skills: affaan-m/uspto-database, affaan-m/scholar-evaluation, affaan-m/literature-review · View all 6 →

즐겨 사용하는 AI에게 물어보기

이 에이전트 스킬이 미리 로드된 새 채팅을 엽니다.

문서

Product SEO

SEO for a website that sells a product. The goal is signups from search. Impressions and clicks are only evidence on the way there.

The method: take the site's own search data, sort topics by whether the product is the answer, work on the ones where it is, across the whole site, then measure each change and undo the ones that hurt.

Rules that always apply

  1. Data before opinions. Start from Search Console. For a site with no impressions yet, use keyword data. Never guess what people search for.
  2. Judge by signups. Every topic goes into one of two piles: "the product is the answer" or "traffic only". Work the first pile. See references/triage.md.
  3. Look at what ranks before choosing what to build. If the first ten results for a query are tools, an article will not rank there.
  4. Fewer, better pages. One page that answers the query better than the current top ten beats ten pages that repeat them. Improve or merge an existing page before adding a new one. Never produce pages in volume.
  5. No invented facts. About the user's product: only what is in seo/product-facts.md. About other products: only from their official pages, with the exact quote, the URL and the date. No source, no claim. See references/facts.md.
  6. No statistics taken from the product's users in public text. A number from user data tells readers their data is being read.
  7. A human approves every change that goes live: publishing, redirects, removals, outgoing messages. Humans submit forms and send emails. You prepare everything up to that point.
  8. Save before changing. Back up the old version, change one thing per page, and log the change with the dates when it will be checked.
  9. Languages. Reply in the language the user writes in. Write site content in the site's language. Never mix two languages in one file or one message.
  10. Report plainly. Verdict first, then the evidence with its date range, then what to do next. When something could not be checked, say so instead of filling the gap.

First run

Look for seo/site-profile.md in the project.

If it is missing:

  1. Read references/setup.md.
  2. Ask the user, in a few short questions: what the product does in one line, who pays for it, what must never be claimed about it, which language the site is in, how pages get published.
  3. Create the seo/ workspace from the templates in assets/ and fill seo/site-profile.md and seo/product-facts.md with the user. Ask where product changes show up and which analytics exist, and record both in the profile.
  4. Add the short block from assets/agents-block.md to the project's CLAUDE.md or AGENTS.md, after showing it to the user. Every later session then knows where the SEO notes are, even when this skill is not loaded.
  5. Check what data is available. A CSV export from Search Console is enough to start. If the site is not in Search Console yet, or has almost no impressions, help connect it (references/setup.md) and follow the "New site" plan in references/triage.md.
  6. Run triage (references/triage.md) and show the two piles.

If it exists, at the start of every session:

  1. Read seo/site-profile.md, seo/change-log.md and seo/lessons.md.
  2. Tell the user which checks in the change log are due or overdue.
  3. Check what changed in the product since the date in the profile, update seo/product-facts.md, and list live pages that mention a changed fact. See references/facts.md, "Keeping up with the product".

Pick the play

SituationPlayRead
"Where do I start?", "audit my SEO", no plan yetTriage: two piles and an ordered listreferences/triage.md
"What should we write about?", the list of ideas has run outSources of ideas, page types, what to avoidreferences/content-ideas.md
"Check our existing pages", old pages nobody has re-read, a product fact changedAudit live pages: text, phone view, facts, links, calls to actionreferences/page-audit.md
Product queries stuck at positions 8–20Rewrite the pagereferences/page-workflow.md
Page is on page one but few people clickNew title and descriptionreferences/titles-and-snippets.md
Several pages compete for one query, or many thin pagesClean up, merge with 301references/cleanup-and-merge.md
The results for a query are tools or landing pagesA page where the visitor does the task, or a small free toolreferences/task-pages-and-tools.md
"X vs Y", "alternatives to X", "best X"Honest comparison pagereferences/comparison-pages.md
Few sites mention the productListings, mention exchange, getting into listsreferences/links-and-listings.md
"How do I show up in ChatGPT?", llms.txtAI search basicsreferences/ai-search.md
A change went live one or three weeks agoMeasure, keep or roll backreferences/measure-and-rollback.md
New site with no impressionsKeyword data, then the same two pilesreferences/triage.md, section "New site"

When the request does not say which play, run triage first and propose one.

The loop for one page

Every page, new or rewritten, goes through the same steps. Each step has its file.

  1. Queries. What this page is found for, and which words carry the impressions. references/page-workflow.md
  2. Facts. Product facts from the file, competitor facts collected by a separate agent. references/facts.md
  3. Draft. Form, length and text rules. references/page-workflow.md
  4. Images. references/images.md
  5. Review by a second model until the "sounds like AI" score is 3 or lower, then a reader pass on screenshots, then your own full read. references/review.md
  6. The owner sees the page as it will look and says "ok". Nothing goes live before that.
  7. It goes live. The owner pastes it in, or you publish that single item if they gave you access. references/publishing.md (optional)
  8. Log it with check dates at one and three weeks. references/measure-and-rollback.md
  9. Write down what you learned in seo/lessons.md. The next page starts by reading it.

Second model for review

A different model catches more than the one that wrote the text.

  • Running in Claude Code with the Codex CLI installed: send the review to Codex.
  • Running in Codex with Claude Code installed: send it to Claude.
  • Neither: use a fresh subagent that has not seen the drafting. Say in the report that the review was done by the same model.

Workspace

The skill keeps its state in a seo/ folder in the user's project, so nothing depends on one session's memory. Create it from assets/ on first run; assets/workspace-readme.md becomes seo/README.md.

seo/
  README.md          one line per file and folder
  site-profile.md    product, who pays, the two piles, standing decisions; read every session
  change-log.md      every change, its backup, check dates, results; read every session
  lessons.md         what to do differently; read before every new page
  product-facts.md   the only source for claims about the product; dated lines
  experiments.md     one hypothesis per page
  sources/           facts about other products: quote, URL, date
  backups/           old versions of changed pages
  audits/            page audit reports
  listings/          directory texts and the checklist of places
  data/  shots/      Search Console rows, screenshots; not in git

Scripts

Scripts live in scripts/ in this skill folder. Run them, do not read them into context; each prints its options with --help. They need Node.js 18 or newer and no packages, except shoot.mjs and brand.mjs, which need Playwright installed in the project. Run them with the user's project as the working directory so that seo/ and .env resolve, and call each one by its full path inside this skill folder: node <this skill's folder>/scripts/opportunities.mjs --help. In the reference files scripts/… means that path.

opportunities.mjs, coverage.mjs and measure.mjs also read the CSV tables of a Search Console export, so they work without API access.

ScriptUse it to
scripts/gsc-fetch.mjsDownload Search Console rows through the official API
scripts/opportunities.mjsList positions 8–20, weak CTR on page one, pages competing for one query, queries with no page
scripts/coverage.mjsCheck that the words people search with are in a page's title and headings
scripts/measure.mjsCompare a page before and after a change and apply the rollback rule
scripts/indexnow.mjsTell Bing and other IndexNow search engines about new or changed URLs
scripts/shoot.mjsScreenshot a page at three widths, or turn an HTML file into an image
scripts/brand.mjsRead the site's colours, fonts and logo into seo/brand.md, so images match the site

No Node, no credentials, or a sandbox without internet: work from the CSV files the user exports from Search Console and do the same analysis by hand. Say which numbers come from an export and what its limits are.

What this skill does not do

  • It does not produce an "SEO score". There is no honest way to compute one.
  • It does not generate pages in bulk.
  • It does not promise positions or traffic.
  • It does not publish, redirect, delete or send anything without the owner's "ok".

관련 스킬