pSEO + SEO Skills for AI Coding Assistants

A complete set of skills for implementing programmatic SEO (pSEO) at scale, plus general SEO skills for multilingual sites, migrations, log analysis, regression checks and content pruning. Works with Claude Code, Cursor, GitHub Copilot, Windsurf, Cline, OpenAI Codex CLI, Aider, Continue, Amazon Q, Zed AI, Cody, Junie, Devin, and any LLM-powered coding assistant. Designed for 1000+ page sites with built-in quality safeguards, memory management, and alignment with Google’s current spam policies (scaled content abuse, doorway abuse, site reputation) and optional visibility for non-Google AI agents.

Skills

General SEO skills

Usable on any site, pSEO or not. Most also slot into the pipeline below.

Where they fit:

• seo-i18n: run alongside pseo-metadata and pseo-linking when the site is multilingual.
• seo-regression-guard: run before and after each deploy.
• seo-log-analysis and seo-content-refresh: run after launch, together with gsc (monthly or quarterly).
• seo-migration: standalone, whenever URLs, domains or the stack change.

Pipeline

pseo-discovery (0)
    |
    v
pseo-audit (1)
    |
    v
pseo-scale (1.5)       <-- conditional: only if 10K+ pages
    |
    v
pseo-data (2)
    |
    +---------------+
    v               v
pseo-templates (3)  pseo-linking (4)
    |               |
    +-------+-------+
            |
    +-------+-------+
    v               v
pseo-metadata (5)   pseo-schema (6)
    |               |
    +-------+-------+
            |
    +-------+-------+
    v               v
pseo-performance    pseo-llm-visibility
    (7)             (8)
    |               |
    +-------+-------+
            v
pseo-quality-guard (9)
    |
    v
seo-regression-guard   <-- before deploy (baseline + check)
    |
    v
(deploy, submit sitemap)
    |
    v
seo-regression-guard   <-- after deploy (live check)
    |
    v
gsc (10)               <-- post-launch monitoring, recurring
    |
    v
seo-log-analysis, seo-content-refresh   <-- recurring, after launch

seo-i18n: alongside pseo-metadata / pseo-linking (multilingual sites)
seo-migration: standalone

Installation

Each skill lives in its own folder in skills/ (a SKILL.md, plus references/ or scripts/ where present). Copy to your AI assistant’s custom instructions location:

The skills are plain markdown and work with any assistant that accepts custom instructions. The gsc skill also ships TypeScript scripts: run npm install once in skills/gsc/scripts/ (copy that folder too if your assistant needs a flat file). seo-regression-guard ships a scripts/ folder as well; copy it with the skill.

Usage

Ask your AI assistant to run individual skills or the full pipeline:

• Full pipeline: “Run the pseo-orchestrate skill with full pipeline”
• Discovery only: “Run pseo-discovery to find pSEO opportunities”
• Single skill: “Run pseo-data to design the data architecture” or “Run pseo-quality-guard to check for abuse patterns”

The orchestrate skill handles dependency ordering automatically. For manual execution, follow the pipeline order shown above.

Key Features

• Scales to 100K+ pages: Database-backed data layer, data sufficiency gating, incremental validation, CDN/edge delivery, crawl budget management
• Two-tier data architecture for memory safety (PageIndex vs BaseSEOContent), cursor-based iteration at scale
• Data sufficiency gating: Prevents thin page generation before build time - only pages with enough data get created
• Google policy alignment: scaled content abuse and doorway abuse checks, E-E-A-T and Needs Met signals, YMYL risk assessment, no reliance on retired rich results (FAQ, HowTo)
• LLM visibility: llms.txt and AI crawler configuration for non-Google agents (Google Search ignores llms.txt and gives no special treatment to chunked or rewritten content), entity clarity
• Scalable similarity detection: MinHash/LSH and SimHash instead of O(n^2) pairwise comparison
• Incremental validation: Delta-only quality checks for fast iteration at scale, with periodic full scans
• Gradual rollout: Rollout strategies from 100 to 100K pages
• Content enrichment pipeline: Structured data enrichment with optional LLM-assisted generation and human review sampling
• Post-launch monitoring: self-contained Search Console scripts (OAuth, search analytics, URL inspection, sitemaps), read-only scope by default
• Framework-agnostic: Next.js App Router by default, adaptable to Astro, Nuxt, Remix, SvelteKit

Sources

Current facts (Google policies, ranking updates, crawler limits, Next.js 16.4, AI crawlers) are documented with links in docs/research-2026-10.md. Items marked UNVERIFIED there rest on secondary sources.

Last updated: 2026-10-12

Author

Created by mariluukkainen