google-ai-seo-fundamentals
Skill1 starsChanged 53 days agoMITView on GitHub
Google Search guidance for AI-assisted website content. Use when reviewing, writing, or governing generative AI content for SEO, including blog posts, marketplace listings, product descriptions, titles, meta descriptions, image alt text, structured data, and scaled content risks under Google's people-first content and spam policies.
In this repository21 other files it gives its agents.
- a11y-auditSkill
- agentic-peer-reviewSkill
- changelog-to-videoSkill
- cinematic-hyperframesSkill
- code-cleanupSkill
- endpoint-surface-mapSkill
- field-web-performanceSkill
- french-accountingSkill
- google-ai-seo-optimizationSkill
- ground-truthSkill
- harness-testingSkill
- impossible-by-designSkill
- legacy-code-reviewSkill
- merchant-feed-auditSkill
- merge-time-ci-economicsSkill
- postgres-privilege-auditSkill
- provider-canarySkill
- repo-wide-dead-code-sweepSkill
- security-hardeningSkill
- website-ai-agent-readinessSkill
- youtube-video-editingSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
16 rules. About 0 are common, 14 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈14
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
- Distinctive: line 12
Use this skill to keep AI-assisted content eligible for Google Search by making it helpful, reliable, accurate, and people-first.
- Distinctive: line 16
Read references/google-ai-content-guidance.md when the task needs Google-specific policy details, ecommerce AI-image/product-data notes, or …
- Distinctive: line 25
Keep the content useful to people before search systems.
- Distinctive: line 26
Verify factual claims, product details, brands, dates, prices, availability, event names, and visual descriptions.
- Distinctive: line 27
Remove generic filler, hallucinated specifics, keyword stuffing, and unsupported claims.
- Distinctive: line 28
Avoid scaled content patterns that create many low-value pages to manipulate rankings.
- Distinctive: line 32
Do not use AI to create misleading alt text, fake expertise, fake reviews, fake dates, or invented product attributes.
- Distinctive: line 33
If the site is an ecommerce merchant using Google Merchant Center, check AI-generated image and product-data labeling requirements before …
- Distinctive: line 37
Do not invent ratings, offers, availability, authors, organizations, or FAQ answers.
- Distinctive: line 38
Treat structured data as normal rich-result support, not an AI Overview shortcut.
- Distinctive: line 44
Keep optional agent-readable assets separate from Google Search content quality issues.
- Distinctive: line 48
Do not claim that Google penalizes AI content solely because it used AI.
- Distinctive: line 49
Do not claim AI output is acceptable without human review.
- Distinctive: line 50
Do not claim mass AI-generated pages are safe when they lack unique user value.
- Very specific: line 51
Do not claim special AI schema, llms.txt, or Markdown mirrors are required for Google Search.
- Very specific: line 52
Do not claim OKF/Open Knowledge Format bundles, knowledge bundles, pricing.md, or other agent-readable files are required for Google Search.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Google AI SEO Fundamentals
Use this skill to keep AI-assisted content eligible for Google Search by making it helpful, reliable, accurate, and people-first. Treat AI as a production assistant, not a shortcut around editorial quality.
Source First
Read references/google-ai-content-guidance.md when the task needs Google-specific policy details, ecommerce AI-image/product-data notes, or a source-backed audit.
Workflow
- Identify the content surface.
- Name the page type, content type, and publication goal.
- Distinguish AI-generated text, AI-assisted edits, AI-generated metadata, AI-generated images, and AI-generated structured data.
- Apply the Google quality gates.
- Keep the content useful to people before search systems.
- Verify factual claims, product details, brands, dates, prices, availability, event names, and visual descriptions.
- Remove generic filler, hallucinated specifics, keyword stuffing, and unsupported claims.
- Avoid scaled content patterns that create many low-value pages to manipulate rankings.
- Review metadata and media.
- Allow AI-assisted titles, descriptions, and alt text only when they are accurate, distinctive, concise, and relevant to the visible page.
- Do not use AI to create misleading alt text, fake expertise, fake reviews, fake dates, or invented product attributes.
- If the site is an ecommerce merchant using Google Merchant Center, check AI-generated image and product-data labeling requirements before shipping.
- Validate structured data.
- Make JSON-LD match the visible page content.
- Do not invent ratings, offers, availability, authors, organizations, or FAQ answers.
- Treat structured data as normal rich-result support, not an AI Overview shortcut.
- Produce an action-oriented result.
- State whether the content is safe to publish, needs edits, or should not ship.
- List the highest-risk issues first.
- Provide exact rewrites or review checklists when useful.
- Keep optional agent-readable assets separate from Google Search content quality issues.
Do Not Claim
- Do not claim that Google penalizes AI content solely because it used AI.
- Do not claim AI output is acceptable without human review.
- Do not claim mass AI-generated pages are safe when they lack unique user value.
- Do not claim special AI schema,
llms.txt, or Markdown mirrors are required for Google Search. - Do not claim OKF/Open Knowledge Format bundles, knowledge bundles,
pricing.md, or other agent-readable files are required for Google Search.
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.

