agentsclimarketplace

Seo website builder skill

Skill ongkipro/seo-website-builder-skill

End-to-end SEO operating system for building, auditing, and improving websites. Use for technical SEO, information architecture, metadata, schema/JSON-LD, sitemap, robots.txt, canonical/noindex decisions, internal linking, Shopify SEO, Astro/static SEO, local business SEO, ecommerce SEO, programmatic SEO, Search Console diagnosis, SEO QA, multi-engine algorithm updates, and AI-search readiness.From its SKILL.md

Install
npx -y skills add ongkipro/seo-website-builder-skill

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

5.1 KB, ~1.1k tokens by cl100k_base, as published. Nobody here has run it

SEO Website Builder

End-to-end SEO operating system for building, auditing, improving, and maintaining websites across Google, Bing, Yandex, Pinterest, and AI-search surfaces.

First Rule

Do not guess. Extract available facts from the project/site first. Ask for missing business-critical inputs when needed.

Evidence Rule

Prefer official search engine/platform documentation and existing project data. Industry sources may guide tactics, but do not claim secret algorithm knowledge.

Always Read First

  1. Compact Skill References
  2. SEO OS Playbook

Then Load by Task

TaskRead
Astro/static/Cloudflare siteAstro SEO Playbook
Next.js frontend/App Router/Pages Router siteNext.js SEO Playbook
Shopify product/collection/listing/feedShopify SEO Playbook
Local/service businessLocal Business SEO Playbook
Algorithm/update reviewSearch Engine Algorithm Brief, Source Index, Algorithm Update Log
Complete page audit / title-description-schema checklistPage Completeness Formula
Audit/build/schema templatesOutput Templates
Deep routing/reference mapReference Manifest

Workflow

  1. Classify the task: new build, audit, Astro/static, Shopify, local business, ecommerce, programmatic, schema, algorithm update, or launch QA.
  2. Gather inputs: website URL/project path, business model, audience, market/location, conversion goal, stack/CMS, main pages/products, current pain.
  3. Inspect before advising:
    • local codebase: routes/pages, metadata/layout, sitemap/robots, schema, build scripts, rendering strategy
    • live site: source HTML, robots/sitemap, canonical, schema, mobile CTA, page experience
  4. For important indexable pages, apply the Page Completeness Formula: purpose, metadata, canonical/robots, social metadata, headings, images, links, schema, sitemap, and measurement.
  5. Produce the output contract.
  6. Validate using QA checklist.

Output Contract

For substantial SEO work, return:

Critical Assessment
Evidence / Source Confidence
Missing Inputs / Assumptions
Search Intent Map
Page Type Map
URL Structure
Index + Canonical Rules
Metadata Pattern
Schema Plan
Internal Linking Plan
Content Requirements
Multi-Engine Notes (Google/Bing/Yandex/Pinterest where relevant)
Technical Implementation
Complete Page Formula Checks
QA / Validation Checklist
Measurement Plan
Risk Notes

Hard Stops

Stop and ask/flag if:

  • business goal unclear
  • page map unclear
  • index/canonical decision unclear
  • requested content would be fake/misleading
  • schema would mark invisible content
  • location pages would be copy-paste doorway pages
  • bulk Shopify changes requested without pilot approval
  • project lacks any measurement plan

Mode Rules

Local Business

Use references/LOCAL_BUSINESS_SEO_PLAYBOOK.md.

Must produce NAP consistency, Google Business/Profile alignment notes, LocalBusiness/Service/FAQ schema if eligible, service/location page rules, and phone/WhatsApp/contact QA.

Shopify

Use references/SHOPIFY_SEO_PLAYBOOK.md.

Must respect pilot-first workflow, no invented product facts, no fake reviews, kept SKUs unchanged, no supplier/origin junk, image ALT limits, title/meta/handle limits.

Astro / Static

Use references/ASTRO_SEO_PLAYBOOK.md.

Must enforce static-first public pages, content in initial HTML, smallest client islands, per-route metadata/canonical, valid sitemap/robots, and non-lazy LCP image.

Next.js

Use references/NEXTJS_SEO_PLAYBOOK.md.

Must check App Router/Pages Router metadata, generateMetadata(), app/sitemap.ts, app/robots.ts, SSR/SSG/ISR strategy, client component boundaries, JSON-LD availability in rendered HTML, next/image ALT/LCP handling, and crawlable next/link navigation.

Algorithm Intelligence

Use references/SEARCH_ENGINE_ALGORITHM_BRIEF.md, references/SEARCH_ENGINE_SOURCE_INDEX.md, and references/ALGORITHM_UPDATE_LOG.md.

Must label evidence confidence, prefer official sources, avoid secret-algorithm claims, and update recommendations only when action is justified.

Promotion / Tests

For validating this skill, see Test Cases. Keep large original SEO OS exports in /home/fantastico/Documents/SEO; load them only when deep research is needed via the manifest.

What ships with it: 18 files

110.5 KB alongside SKILL.md

Gives 0 of the 12 instructions most marketing audience skills give in ~1.1k tokens

Counted across 690 of the 894 authors here whose files we hold, read 2026-08-07

  • Apply Poppins font to headingsin 41 of 690, across 6 files
  • Apply Lora font to body textin 41 of 690, across 6 files
  • Use Arial fallback for headingsin 39 of 690, across 4 files
  • Use Georgia fallback for body textin 39 of 690, across 4 files
  • Maintain text hierarchy and formattingin 39 of 690, across 4 files
  • Use accent colors for non-text shapesin 38 of 690, across 3 files
  • Use RGB values for precise color matchingin 38 of 690, across 3 files
  • Use brand colors for primary text and backgroundsin 36 of 690, across 1 file
  • Read product marketing context file before asking questions, starting, or auditingin 35 of 690, across 23 files
  • Use active voice instead of passive voicein 26 of 690, across 10 files
  • Implement or generate appropriate JSON-LD structured datain 24 of 690, across 17 files
  • Prioritize clarity over clevernessin 22 of 690, across 8 files

Said here and by no other author read

  • extract available facts before advising
  • prefer official documentation over industry sources
  • read compact skill references and playbook first
  • load task-specific playbooks as needed
  • classify the task type
  • gather website business and stack inputs

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,149. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.