seo-news-discover
Skill6 starsChanged 3 months agoApache-2.0View on GitHub
Use when auditing or planning publisher visibility for Google News, Discover, news search, or comparable freshness-sensitive surfaces across editorial policy, article pages, dates/bylines, corrections, large images, NewsArticle markup, news sitemaps, feeds, paywalls, and first-party reports; require current policy evidence and never promise inclusion, Top stories, Discover traffic, subscriptions, or revenue.
In this repository27 other files it gives its agents.
- llms.txtllms.txt
- ai-search-researchSkill
- ai-visibility-monitorSkill
- optimise-seoSkill
- seo-action-planSkill
- seo-aeoSkill
- seo-agenticSkill
- seo-architectureSkill
- seo-auditSkill
- seo-authoritySkill
- seo-commerceSkill
- seo-competitor-pagesSkill
- seo-contentSkill
- seo-geoSkill
- seo-hreflangSkill
- seo-imagesSkill
- seo-localSkill
- seo-pageSkill
- seo-performanceSkill
- seo-planSkill
- seo-programmaticSkill
- seo-researchSkill
- seo-schemaSkill
- seo-sitemapSkill
- seoSkill
- seo-technicalSkill
- seo-videoSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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 10
Read markdown-delivery-contract.md for every task.
- Distinctive: line 17
Read news-discover-protocol.md before a formal audit.
- Very specific: line 26
Use first-party News/Discover/Search performance exports when supplied.
- Distinctive: line 32
Never fabricate authorship, publication dates, updates, corrections, sources, images, reports, or policy eligibility.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
News and Discover SEO
Markdown delivery contract
Read markdown-delivery-contract.md for every task. Write a substantive .md document for every material work step and register its direct destination in the work index.md. For public-site work, apply the owner-required Markdown discovery profile across the full eligible inventory; preserve native standards and immutable evidence formats.
Lane outputs: publisher-review.md; article-provenance.md (combine small related steps with stable section links). Keep article Markdown aligned with byline, publication/update dates, corrections, original reporting and rights. Preserve paywall/access policy and news feeds/sitemaps; never expose subscriber-only text through a public mirror.
Audit the publisher system behind freshness-sensitive discovery: editorial transparency, article pages, dates and corrections, media, structured data, sitemaps/feeds, access state, and reporting.
Read news-discover-protocol.md before a formal audit.
Procedure
- Define publications, editions/locales, article types, paywall/access model, newsroom owners, publishing cadence, and target surfaces.
- Capture representative article/listing pages, raw/rendered metadata, bylines, dates, corrections, publisher/contact/about evidence, images, structured data, sitemap/feed rows, canonicals, and access directives.
- Reconcile visible headline, author, publication/modification dates, section, image, publisher, paywall state, and NewsArticle/Article data. Preserve correction history rather than silently rewriting time-sensitive facts.
- Inspect news sitemap membership and freshness, article retirement/update rules, crawl/index state, large-image delivery, responsive page experience, internal discovery, and feed parity.
- Apply current platform content and spam policies to sensational, misleading, scraped, scaled, synthetic, or thin publication patterns. AI-assisted content still requires accuracy, quality, relevance, and accountable editorial review.
- Use first-party News/Discover/Search performance exports when supplied. Discover is not a stable keyword-ranking surface; keep its reporting separate from query-based search and AI visibility.
- Route schema to
seo-schema, images toseo-images, content toseo-content, technical access toseo-technical, video toseo-video, and measurement toseo-performance. - Package formal findings as SEO Findings
1.1.0withnews_property,web_page,sitemap, ormedia_settargets andnews-discover,policy,freshness,content,media, ortechnicalcategories.
Guardrails
Never fabricate authorship, publication dates, updates, corrections, sources, images, reports, or policy eligibility. Do not refresh dates without substantive updates or promise inclusion and traffic.
Formal evidence handoff
Package only supported observations as SEO Findings 1.1.0. Let <suite-root> mean ${CLAUDE_PLUGIN_ROOT} in Claude Code. In Codex, read .seo-suite-runtime.json beside this SKILL.md when present and use its suite_root value; otherwise use the absolute repository checkout, then run python "<suite-root>/scripts/validate_seo_findings.py" validate-findings <bundle>/seo-findings.json --bundle <bundle>. Keep the handoff provisional until this command passes.
Output
Return the publisher/article scope, transparency and policy evidence, article metadata parity, sitemap/feed freshness, media/access findings, reporting limits, owners, verification, and rollback.
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.

