sxo
Skill0 starsChanged 2 days agoMITView on GitHub
Search experience optimisation: check whether a page is the kind of page searchers want for its query. From a results page the user pastes (titles, URLs, snippets, features), classify the dominant page type (guide, list, comparison, product or category page, tool, template, video, forum thread, local result), the format and angle, and what the searcher is about to do; compare with the user's page and say whether to adapt, create a different page or target another query. Use when the user asks 'why does my page not rank although it is better', 'search intent', 'SERP intent', 'wrong page type', 'what kind of content ranks for X', 'SXO', or 'should this be a landing page or a blog post'.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- nowork-studio/notfair-plugintheir own version, first seen Nov 11, 2026
- nowork-studio/topranktheir own version, first seen Oct 8, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- nowork-studio/notfair-plugin★ 4.2ksame name
- nowork-studio/toprank★ 4.1ksame name
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 repository44 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agent-readySkill
- ai-citationsSkill
- ai-crawlersSkill
- ai-logsSkill
- ai-trackerSkill
- backlinksSkill
- cannibalizationSkill
- canonicalsSkill
- citabilitySkill
- comparison-pagesSkill
- competitorsSkill
- content-briefSkill
- content-decaySkill
- content-qualitySkill
- core-web-vitalsSkill
- ecommerce-seoSkill
- ga4-aiSkill
- ghost-publishSkill
- gsc-bingSkill
- hreflangSkill
- imagesSkill
- indexingSkill
- internal-linksSkill
- llms-txtSkill
- local-seoSkill
- measure-rollbackSkill
- onpageSkill
- platformsSkill
- pseo-quality-gateSkill
- quick-winsSkill
- redirects-migrationSkill
- schemaSkill
- seo-planSkill
- seo-reportSkill
- setupSkill
- site-architectureSkill
- sitemapsSkill
- static-site-publishSkill
- tech-auditSkill
- titles-metaSkill
- topic-clustersSkill
- weekly-checkSkill
- wordpress-publishSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 24
Read the user's page (npx sitetiller page <url> --json for the facts.
- Very specific: line 34
Check the user's own data: npx sitetiller gsc example.com --start ...
- Distinctive: line 42
Do not run automated queries against Google or other search engines.
- Distinctive: line 44
Do not copy competitors' text or structure verbatim.
- Distinctive: line 45
Do not promise a ranking change from a page-type change.
≈ “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
SXO: match the page type to the search
Goal: stop optimising a page that is the wrong kind of page. If the top results for a query are free tools and the user's page is an essay, more words will not fix it.
Inputs
- The query and country.
- The results page, pasted by the user (top 10: title, URL, snippet, plus visible features such as AI Overview, videos, "Discussions and forums", shopping, map pack). This skill does not scrape search results; Google's terms do not allow automated queries.
- The user's page URL.
Steps
- Classify each result. Make a table: position, domain, page type, format, angle, freshness.
- Page types: guide/tutorial, listicle, comparison or "X vs Y", product page, category page, tool or calculator, template or example, video, forum or community thread, news, local result, official documentation.
- Format: long article, short answer, table, step list, interactive.
- Angle: beginner, expert, cheapest, fastest, year-specific, for a role or industry.
- Find the dominant pattern: the type and angle held by at least 6 of 10 results. If no type has 4 or more, intent is mixed; say so.
- Read the user's page (
npx sitetiller page <url> --jsonfor the facts; read the text yourself) and classify it the same way. - Name the job the searcher wants done next (learn, compare, pick, buy, calculate, fix, find a place). The page should let them do it without another search.
- Decide:
Situation Action Same type and angle, page still below Not an SXO problem: go to content-brief,content-quality,internal-links,backlinksDifferent type (essay vs tools ranking) Build the right type as a new page and link to it from the old one; keep the old page if it serves another query Same type, different angle Adapt the angle in title, intro and structure ( titles-meta), measure withmeasure-rollbackMixed intent Cover the dominant job first, with clear sections for the second Forums/videos dominate Firsthand experience wins: add real examples, screenshots, a video, or answer in those places honestly - Check the user's own data:
npx sitetiller gsc example.com --start ... --end ... --dims query,page --jsonshows which queries the page already gets impressions for. A page often ranks for a different intent than intended; follow the data.
Output to the user
- The results table and the dominant type, format and angle (or "mixed").
- The user's page classified the same way and the mismatch in one sentence.
- The decision from the table above and the first three concrete changes.
Guardrails
- Do not run automated queries against Google or other search engines; work from what the user pastes or exports.
- Results vary by location, device and person; note the country and date of the pasted results.
- Do not copy competitors' text or structure verbatim; match the job, not the wording.
- Do not promise a ranking change from a page-type change; measure it.
References
references/sources.md: Google guidance on helpful content, titles and search features, checked 2026-11-13.
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.