content-quality
Skill0 starsChanged 2 days agoMITView on GitHub
Review a page against Google's helpful, reliable, people-first content guidance and E-E-A-T: who wrote it (byline, author page), how it was made (first-hand testing, data, AI disclosure), why it exists, sourcing, dates, readability (Flesch, sentence length), filler phrases that read as machine-written, and unsourced 'studies show' claims. Produces a 10-point checklist plus a rewrite plan. Use when the user asks 'E-E-A-T', 'is my content helpful', 'helpful content update', 'content quality audit', 'does this read like AI', 'why did my rankings drop after a core update', 'YMYL', or 'author bio'. Uses sitetiller quality.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- 6t9xstar/one-step-seotheir own version, first seen Nov 8, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- 6t9xstar/one-step-seo★ 5same 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
- 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
- sxoSkill
- tech-auditSkill
- titles-metaSkill
- topic-clustersSkill
- weekly-checkSkill
- wordpress-publishSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 19
Read the page yourself. The counts find candidates.
- Distinctive: line 45
Never fabricate authors, reviewers, credentials, quotes, reviews or "we tested" claims.
- Distinctive: line 46
Do not present the checklist result as a Google score or promise that fixing it restores rankings.
≈ “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
Content quality
Goal: show, with evidence from the page, where it falls short of Google's "Who, How and Why" questions, then rewrite the weakest sections. Google states E-E-A-T is not a specific ranking factor and that trust matters most; treat the checklist as a review aid, never as a score Google uses.
Steps
- Measure the page:
Output:npx sitetiller quality https://example.com/guide --jsonreadability(fleschReadingEase,avgSentenceWords,longSentenceShare,longParagraphs),signals(author,datePublished,dateModified,externalSources,firstHand,figures,aboutOrContact),filler[](phrase, count),vagueClaims[],checklist[](10 checks, pass/fail),passed,of. - Read the page yourself. The counts find candidates; only reading tells you whether the content is accurate, original and complete. Answer Google's questions in writing:
- Who: is the author obvious, with a byline that leads to their background? Is it someone who knows the topic?
- How: is it clear how the content was made: tested, measured, drawn from the site's own data? If automation or AI was used substantially, is that disclosed and is the reason explained?
- Why: was it made to help a reader, or mainly to attract search visits?
- Content: original information or analysis, beyond summarising other pages? Any easily verified factual errors? A clear, descriptive title?
- For YMYL topics (health, money, safety, legal), raise the bar: named expert author or reviewer, primary sources for every figure, an update date.
- Fix by checklist line:
| Failed check | Fix |
| Author is named | Real byline linked to an author page with relevant background. Never invent a person, headshot or credential |
| Publish / update date | Show dates on the page and in Article structured data (datePublished, dateModified); change dateModified only for real changes |
| At least 2 outside sources | Link primary sources (the vendor's documentation, the study, the dataset) next to the claim they support |
| First-hand work | Add what only you have: your test, screenshots, measurements, your customers' anonymised data, a worked example |
| Figures, tables, code or media | Turn comparisons into a table; add the screenshot or chart that proves the point |
| About or contact | Link an about page that says who runs the site and how to reach them |
| No filler phrases | Cut the phrase; say the specific thing instead ("delve into" -> the topic, "in today's fast-paced world" -> delete) |
| No unsourced "studies show" | Name and link the study, or remove the claim |
| Readable | Split sentences over 30 words; answer the question in the first sentence of each section (see citability) |
- Rewrite the two weakest sections first, keeping the facts and links. Snapshot the page before and after (
measure-rollback) if it is a page the user owns and wants measured.
Signals this tool cannot see
Reputation (what others say about the site or author), accuracy of facts, and whether the advice works. Say so in the report.
Guardrails
- Never fabricate authors, reviewers, credentials, quotes, reviews or "we tested" claims. Add only what the user can back up.
- Do not present the checklist result as a Google score or promise that fixing it restores rankings; core updates are not penalties with a fix list.
- The filler list flags phrases, it does not prove machine authorship; never accuse a writer on that basis.
- Flesch reading ease is calibrated for English; skip it for other languages.
References
examples/quality.json: real output of this skill's command on sitetiller.com (2026-11-13), seeexamples/README.md.references/sources.md: Google helpful content guidance and quality rater guidelines, 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.