SEO Content Toolkit v1.2

SEO content planning that prioritizes readable writing over keyword stuffing — with deep domain knowledge from Google's published guidelines, W3C standards, and schema.org specifications. Now includes keyword discovery for short-tail and long-tail opportunities from seed keywords or URLs.

Installation

1. Download the pf-seo-content.plugin file
2. Open Claude Desktop and navigate to Settings > Plugins
3. Click Install Plugin and select the downloaded .plugin file
4. The plugin will be installed and available immediately

Note: All data stays local on your machine. No external API calls or cloud storage required.

Why This Exists

SEO content tools like Surfer SEO ($948–2,628/yr), Clearscope ($1,548–2,040/yr), and Frase ($180–540/yr) charge premium prices for content optimization. Many users report that these tools encourage keyword stuffing and over-optimization at the expense of natural writing. This plugin brings the most useful SEO workflows — content briefs, meta descriptions, content audits, and internal linking — into a free, local, privacy-first tool that focuses on actionable recommendations.

Quick Start

1. Install the plugin in Claude Desktop / Cowork
2. Run /pf-seo-content:seo-content-setup to initialize your workspace
3. Place your input files in inbound/ (keyword list, page CSV, article text, or sitemap)
4. Run any skill individually or use /pf-seo-content:seo-content-full [keyword] for the full pipeline

Commands

Command	Description
/pf-seo-content:seo-content-setup	Initialize workspace — folders, config, dependency check
/pf-seo-content:seo-content-brief [keyword]	Generate an SEO content brief for a target keyword
/pf-seo-content:seo-content-meta [csv-path]	Batch-generate meta descriptions from a page list
/pf-seo-content:seo-content-audit [file-path]	Audit content against SEO best practices with scoring
/pf-seo-content:seo-content-links [sitemap-path]	Generate internal linking recommendations from your sitemap
/pf-seo-content:seo-content-keyword-discovery [seed or URL]	Discover keyword opportunities from a seed keyword or URL
/pf-seo-content:seo-content-full [keyword]	Run the full pipeline (brief + meta + audit + links)
/pf-seo-content:seo-content-kb	Display SEO domain knowledge base (E-E-A-T, CWV, schema.org)
/pf-seo-content:seo-content-status	Show pipeline progress and output status

How It Works

Each skill operates independently (hub-and-spoke topology) — run any skill in any order based on what you need today. The full pipeline command runs all four skills sequentially, skipping any that lack required inputs. All outputs flow through lifecycle folders: inbound/ (your data) → processing/ (structured JSON intermediates) → outbound/ (final deliverables).

What It's an Alternative To

SaaS Tool	Annual Cost	Key Overlap
Surfer SEO	$948–2,628/yr	Content briefs, content scoring/auditing
Clearscope	$1,548–2,040/yr	Content auditing, keyword optimization scoring
Frase	$180–540/yr	Content briefs, meta descriptions, basic auditing
MarketMuse	$3,600+/yr	Content briefs, topic modeling, internal linking

Key Differentiators

Beyond being free, the SEO Content Toolkit offers: complete data privacy (all processing is local — data is processed within the Cowork environment), fully customizable workflows (edit any skill's config to match your content strategy), no vendor lock-in (all outputs are standard CSV, JSON, and markdown), and batch processing with checkpoint/resume for large-scale operations.

Feature Comparison

Feature	This Plugin	Surfer SEO	Clearscope	Frase
SEO content briefs	✅	✅	⚠️	✅
Meta description generation	✅	❌	❌	⚠️
Content audit/scoring	✅	✅	✅	⚠️
Internal linking analysis	✅	❌	❌	❌
Real-time SERP data	❌	✅	✅	✅
Keyword discovery (seed + URL)	✅	⚠️	❌	⚠️
Search intent classification (Google §12.7)	✅	❌	❌	❌
SERP feature opportunity mapping	✅	⚠️	❌	❌
Keyword clustering for content planning	✅	⚠️	❌	⚠️
Keyword difficulty scores	❌	✅	⚠️	✅
NLP-based term suggestions	⚠️	✅	✅	✅
AI writing assistant	⚠️	✅	❌	✅
Data privacy (local only)	✅	❌	❌	❌
Customizable workflows	✅	❌	❌	❌
Batch processing with resume	✅	⚠️	⚠️	⚠️
E-E-A-T evaluation framework	✅	❌	❌	❌
YMYL topic detection	✅	❌	❌	❌
Schema.org markup guidance	✅	⚠️	❌	❌
Google rewrite trigger avoidance	✅	❌	❌	❌
Keyword cannibalization detection	✅	⚠️	❌	❌
Core Web Vitals awareness	✅	✅	❌	❌
Cost	included with your subscription	$948–2,628/yr	$1,548–2,040/yr	$180–540/yr

Estimated Cost per Use

Disclaimer: Token estimates are approximate and based on typical usage patterns measured from skill prompt sizes. Actual costs vary with input data size, conversation length, and complexity. Estimates use Claude Sonnet 4.6 pricing ($3/1M input, $15/1M output). Cowork and Claude Desktop subscription users (Pro/Max/Team) are not charged per-token — these estimates apply only to direct Anthropic API usage. Running stages individually in fresh sessions uses fewer input tokens than running the full pipeline sequentially, because pipeline mode accumulates conversation history across stages.

Per skill (run individually in a fresh session):

Stage	Skill Prompt	User Input	Total Input	Output	Est. Cost
seo-brief	~3.5K	~800	~7.1K	~3.5K	~$0.07
seo-content-audit	~4.0K	~800	~7.8K	~4.0K	~$0.08
seo-internal-links	~2.8K	~800	~6.4K	~3.0K	~$0.06
seo-kb	~4.6K	~800	~8.2K	~4.6K	~$0.09
seo-meta-descriptions	~2.5K	~800	~6.1K	~3.0K	~$0.06
Standalone total			~35.5K	~18.1K	~$0.38

Full pipeline (all stages in one session — context accumulates):

Stage	Base Input	+ History	Total Input	Output	Est. Cost
seo-brief	~7.8K	0	~7.8K	~3.5K	~$0.08
seo-content-audit	~8.3K	~4.3K	~12.6K	~4.0K	~$0.10
seo-internal-links	~7.1K	~9.1K	~16.2K	~3.0K	~$0.09
seo-kb	~8.9K	~12.9K	~21.8K	~4.6K	~$0.13
seo-meta-descriptions	~6.9K	~18.3K	~25.1K	~3.0K	~$0.12
Pipeline total			~83.6K	~18.1K	~$0.52

Running the full pipeline once typically costs $0.37–$0.68 in API tokens (Claude Sonnet 4.6).

AI-Powered Features

• Centralized SEO Knowledge Base: 9 authoritative knowledge domains — Google E-E-A-T framework, Search Essentials, Core Web Vitals (LCP/INP/CLS), schema.org structured data, W3C WCAG 2.1 heading hierarchy, meta description display rules, Hub & Spoke linking model, content freshness signals, keyword cannibalization detection
• YMYL Detection & Elevated E-E-A-T: Automatically detects Your Money or Your Life topics per Google Search Quality Evaluator Guidelines §2.3 and flags elevated expertise requirements
• Schema.org Markup Recommendations: Recommends Article, FAQPage, HowTo, or BreadcrumbList structured data per content type with required vs. recommended properties
• Google Rewrite Trigger Avoidance: Meta descriptions validated against 5 documented conditions that cause Google to auto-generate snippets instead of using yours
• Per-Category Audit Checklists: Content audit scoring tied to specific pass/fail criteria from W3C WCAG 2.1, Google spam policies, and Core Web Vitals thresholds
• Hub & Spoke Linking with PageRank Awareness: Internal linking follows established topical authority model with link direction guidance based on PageRank distribution principles
• Keyword Cannibalization Detection: Flags pages competing for the same keyword with resolution recommendations (consolidate, differentiate, canonicalize)
• Content Freshness Assessment: Identifies freshness-sensitive topics per Google's QDF algorithm factor and recommends update cadence with datePublished/dateModified schema markup
• Keyword Discovery from Seeds or URLs: Discovers short-tail and long-tail keyword opportunities using systematic expansion (modifier, semantic, question-based, long-tail generation) or by extracting keywords from an existing URL's content (title, headings, body text, URL slug)
• Search Intent Classification: Every discovered keyword is classified per Google Search Quality Evaluator Guidelines §12.7 — informational, commercial investigation, transactional, or navigational — so you know what content type to create
• Keyword Clustering for Content Planning: Groups discovered keywords into pillar + supporting clusters with content recommendations per cluster, directly feeding into the brief generator
• SERP Feature Opportunity Mapping: Identifies which keywords can target Featured Snippets, People Also Ask, FAQ/HowTo rich results, Local Pack, Video Carousel, or Image Pack — with specific content requirements for each
• Keyword Analysis & Briefs: Generates comprehensive SEO briefs with recommended article structure, H2 headings per W3C WCAG 2.1 §1.3.1, word count targets, and competitive angle analysis
• Content Audit Scoring: Evaluates existing content across heading structure, depth with E-E-A-T signals, keyword usage, readability, and technical SEO with per-category checklists
• Internal Linking Strategy: Identifies content clusters and recommends specific link paths using Hub & Spoke model to maximize topical relevance and link equity distribution
• Meta Description Optimization: Batch-generates platform-optimized meta descriptions with Google rewrite trigger avoidance checklist and keyword integration guidance

Known Limitations & Workarounds

This is a Claude Cowork plugin, not a traditional SaaS application. It has architectural constraints you should know about before adopting it.

Limitation	Impact	Workaround
No real-time SERP data	Briefs and audits rely on Claude's training knowledge, not live search results	Paste competitor content into inbound/ for analysis; use free Google Search Console for ranking data
No persistent tracking database	Cannot track keyword rankings or content performance changes over time	Export CSV/JSON outputs to your own tracking tools or spreadsheets
Session-based operation	Cannot schedule recurring audits or alert on performance changes	Pair with Cowork scheduled tasks for periodic runs
Context window limit	Very large articles or 500+ page sitemaps need batching	Checkpoint/resume handles interruptions automatically for batch skills
Heuristic-based scoring	Won't match NLP-powered scores from Surfer/Clearscope	Focuses on actionable, transparent recommendations over opaque scores

Context & Performance Guide

Session management

Claude's context window (200K tokens) is shared across the entire session. For best results running the full pipeline, start a fresh session before running /pf-seo-content:seo-content-full.

Data volume guidance

Tested with up to 200 pages for meta descriptions and sitemaps. For larger datasets, the plugin automatically batches (50 pages for meta descriptions, 100 for internal links) with checkpoint/resume.

Tips for best results

• Provide input data as files in inbound/ rather than pasting into chat — file reading is more context-efficient
• Keep your messages concise during pipeline runs — every message stays in the context window
• For the highest quality output, run each stage in a separate session. The plugin saves state between stages via project.json
• Provide rich input data — CSV pages with categories and tags produce much better clustering than bare titles

Degradation signals

If responses become shorter, less detailed, or skip sections that previously worked well, start a new session and re-run the current stage.

Requirements

• Claude Desktop or Cowork mode
• Python 3 (pre-installed in Cowork VM)

Important Disclaimers

• AI-Generated Content: This plugin uses AI (LLM) technology which can produce inaccurate or incomplete outputs. All content should be treated as a starting point and reviewed for accuracy before use.
• Not Professional Advice: Outputs do not constitute legal, financial, tax, medical, or other professional advice. Consult qualified professionals before making decisions based on generated content.
• No Compliance Guarantee: References to industry standards, regulations, or guidelines are for informational purposes only. This plugin does not guarantee compliance with any law or regulation. Users are responsible for verifying all outputs meet their specific regulatory requirements.
• No Endorsement or Affiliation: Mention of third-party products, standards, or organizations does not imply endorsement, partnership, or certification by those entities.