# /Digital-marketing-pro:programmatic-SEO Human Guide

## What This Is For
Plan or audit SEO pages generated at scale from structured data — data-source quality, template uniqueness, URL patterns, internal linking, canonicals, sitemaps, and index-bloat prevention. It gives the agent a clearer input/output frame for search and SEO workflows: what context to ask for, what decisions to make, and what usable artifact to return.

Use this as a human-readable version of the /Digital-marketing-pro:programmatic-SEO agent skill. It is meant for marketers, operators, founders, and other non-coders who want the workflow without reading agent-specific implementation instructions.

## When To Use This
- Use this when you need a repeatable process for /digital-marketing-pro:programmatic-SEO.
- Use this when the task needs judgment, examples, constraints, or a clear output format rather than a one-off prompt.
- Use this when you want to hand an AI assistant enough context to produce a usable marketing artifact.

## When Not To Use This
- Do not use this when you only need a quick factual answer.
- Do not use this when the work depends on private data you cannot share with the assistant.
- Do not use this as a replacement for legal, compliance, financial, or medical review.

## What You Need Before Starting
- The goal or business outcome you want.
- The audience, customer segment, or market context.
- Any source material the assistant should respect, such as notes, briefs, examples, URLs, or brand guidance.
- Constraints such as tone, length, channel, deadline, region, or approval requirements.
- A clear definition of what a good final answer should look like.

## Step-By-Step Workflow
1. State the job clearly: "Use the /Digital-marketing-pro:programmatic-SEO guide to help me with..."
2. Add context: audience, goal, offer, channel, source material, and constraints.
3. Ask the assistant to identify missing inputs before producing the final output.
4. Have the assistant follow the skill-specific guidance below.
5. Review the result against the final checklist and ask for revisions where needed.

## Skill-Specific Guidance
- **URL or data source**: Existing programmatic pages to audit, or data source details for planning
- **Page type**: What kind of pages are being generated (location, product, integration, glossary, template, tool)
- **Data source**: CSV/JSON files, API endpoints, database queries — or existing pages to analyze
- **Target scale**: How many pages will be generated
- **Current status**: New build or auditing existing programmatic pages
- **Data source assessment**: Evaluate the data powering programmatic pages — row count, column uniqueness, missing values, duplicate detection (>80% field overlap), data freshness
- **URL pattern strategy**: Design URL hierarchy — lowercase hyphenated slugs, logical structure, uniqueness enforcement, under 100 characters, consistent trailing slash
- **Internal linking automation**: Hub/spoke model, related items (3-5 per page), breadcrumbs with BreadcrumbList schema, cross-linking by shared attributes, varied anchor text
- **Thin content safeguard check**: Apply quality gates (see below)
- **Canonical strategy**: Self-referencing canonicals, parameter handling, pagination strategy, manual page priority
- **Sitemap integration**: Auto-generate entries, split at 50K URLs, `<lastmod>` from actual data timestamps, exclude noindexed pages
- **Index bloat prevention**: Noindex low-value pages, pagination handling, faceted navigation canonicalization, crawl budget monitoring for 10K+ pages

## Decision Points And Nuance
The original skill emphasizes: Purpose, Input Required, Process, Quality Gates, Scale Thresholds, Scaled Content Abuse Context (2025-2026), Safe vs Risky Programmatic Pages, Uniqueness Calculation, URL Pattern Library, Common Patterns.

Use these questions to steer the work:
- What is the intended audience or buyer?
- What source material must be preserved?
- What should the assistant optimize for: clarity, persuasion, accuracy, speed, creativity, or conversion?
- What examples represent the desired quality bar?
- What should the assistant avoid?

## Common Mistakes
- The user must provide (or will be prompted for):
- | Pages without content review | 100+ | WARNING: require content audit before publishing |
- **Content differentiation**: 30-40%+ of content must be genuinely unique between any two programmatic pages (not just city/keyword string replacement)
- **Progressive rollout**: Publish in batches of 50-100 pages. Monitor indexing and rankings for 2-4 weeks before expanding. Never publish 500+ simultaneously without quality review.

## Copy-And-Paste Prompt
```text
Use the /Digital-marketing-pro:programmatic-SEO human guide.

My goal:
[Describe the business outcome]

Audience:
[Describe who this is for]

Context and source material:
[Paste notes, examples, links, or existing copy]

Constraints:
[Tone, length, channel, timeline, must-include items, must-avoid items]

Before producing the final output, ask me for any missing information that would materially improve the result.
```

## Final Checklist
- [ ] The output matches the original goal.
- [ ] The audience and context are reflected in the answer.
- [ ] Important constraints and source material were preserved.
- [ ] The assistant made the relevant decisions explicit.
- [ ] The final artifact is ready to use, review, or hand to the next person.

## Source
This guide was generated from the indranilbanerjee/digital-marketing-pro skill entry for `programmatic-seo`.

## Source Skill Notes
These notes preserve the nuance from the original skill. Use them as supporting reference when the workflow above feels too generic.

# /digital-marketing-pro:programmatic-seo

## Purpose

Plan and audit SEO pages generated at scale from structured data sources (databases, APIs, CSV/JSON files). Enforces quality gates to prevent thin content penalties, index bloat, and Google's Scaled Content Abuse policy.

## Input Required

The user must provide (or will be prompted for):

- **URL or data source**: Existing programmatic pages to audit, or data source details for planning
- **Page type**: What kind of pages are being generated (location, product, integration, glossary, template, tool)
- **Data source**: CSV/JSON files, API endpoints, database queries — or existing pages to analyze
- **Target scale**: How many pages will be generated
- **Current status**: New build or auditing existing programmatic pages

## Process

1. **Load brand context**: Read `~/.claude-marketing/brands/_active-brand.json` for the active slug, then load `~/.claude-marketing/brands/{slug}/profile.json`. Apply industry context and compliance rules. Check for brand guidelines at `~/.claude-marketing/brands/{slug}/guidelines/_manifest.json`.
2. **Data source assessment**: Evaluate the data powering programmatic pages — row count, column uniqueness, missing values, duplicate detection (>80% field overlap), data freshness
3. **Template engine planning**: Design templates that produce genuinely unique pages — variable injection points, content blocks (static vs dynamic), conditional logic, supplementary content. Validate each page passes the "standalone value test"
4. **URL pattern strategy**: Design URL hierarchy — lowercase hyphenated slugs, logical structure, uniqueness enforcement, under 100 characters, consistent trailing slash
5. **Internal linking automation**: Hub/spoke model, related items (3-5 per page), breadcrumbs with BreadcrumbList schema, cross-linking by shared attributes, varied anchor text
6. **Thin content safeguard check**: Apply quality gates (see below)
7. **Canonical strategy**: Self-referencing canonicals, parameter handling, pagination strategy, manual page priority
8. **Sitemap integration**: Auto-generate entries, split at 50K URLs, `<lastmod>` from actual data timestamps, exclude noindexed pages
9. **Index bloat prevention**: Noindex low-value pages, pagination handling, faceted navigation canonicalization, crawl budget monitoring for 10K+ pages
10. **Score and report**: Score each dimension, produce prioritized action plan

## Quality Gates

### Scale Thresholds

| Metric | Threshold | Action |
|--------|-----------|--------|
| Pages without content review | 100+ | WARNING: require content audit before publishing |
| Pages without justification | 500+ | HARD STOP: require explicit user approval and thin content audit |
| Unique content per page | <40% | Flag as thin content (penalty risk) |
| Unique content per page | <30% | HARD STOP: scaled content abuse risk |
| Word count per page | <300 | Flag for review (may lack sufficient value) |

### Scaled Content Abuse Context (2025-2026)

Google's Scaled Content Abuse policy (introduced March 2024) saw major enforcement escalation:

- **June 2025**: Wave of manual actions targeting AI-generated content at scale
- **August 2025**: SpamBrain update enhanced pattern detection for AI-generated link schemes and content farms
- **Result**: 45% reduction in low-quality, unoriginal content in search results

**Enhanced quality gates for programmatic pages:**

- **Content differentiation**: 30-40%+ of content must be genuinely unique between any two programmatic pages (not just city/keyword string replacement)
- **Human review**: Minimum 5-10% sample review of generated pages before publishing
- **Progressive rollout**: Publish in batches of 50-100 pages. Monitor indexing and rankings for 2-4 weeks before expanding. Never publish 500+ simultaneously without quality review.
- **Standalone value test**: Each page should pass: "Would this page be worth publishing even if no other similar pages existed?"
- **Site reputation abuse**: Publishing programmatic content under a high-authority domain (not your own) may trigger site reputation abuse penalties (enforced aggressively since November 2024)

### Safe vs Risky Programmatic Pages

**Safe at scale:**
- Integration pages (with real setup docs, API details, screenshots)
- Template/tool pages (with downloadable content, usage instructions)
- Glossary pages (200+ word definitions with examples, related terms)
- Product pages (unique specs, reviews, comparison data)
- Data-driven pages (unique statistics, charts, analysis per record)

**Penalty risk at scale:**
- Location pages with only city name swapped in identical text
- "Best [tool] for [industry]" without industry-specific value
- "[Competitor] alternative" without real comparison data
- AI-generated pages without human review and unique value-add
- Pages where >60% of content is shared template boilerplate

### Uniqueness Calculation

Unique content % = (words unique to this page) / (total words on page) x 100

Measured against all other pages in the programmatic set. Shared headers, footers, and navigation excluded. Template boilerplate IS included.

## URL Pattern Library