playbooks

SEO Content Engine

Build and run an SEO content engine: audit current state, identify gaps, build keyword architecture, generate content calendar, draft content.

Gooseby Athina AI
Install
Terminal
npx gooseworks install --all

# then, in Claude Code, Cursor, or Codex:
/gooseworks use the seo-content-engine skill
About This Skill

SEO Content Engine

Build a compounding SEO content engine for a client: audit → gap analysis → keyword architecture → content calendar → content drafting → publishing pipeline.

When to Use

  • "Build an SEO content strategy for [client]"
  • "Create a content engine for [company]"
  • "What content should [company] be publishing?"

Prerequisites

  • Client website URL
  • Client context.md with ICP, value props, positioning
  • Top competitors identified (from intelligence package or manually)

Steps

1. Audit Current State

Skill: seo-content-audit (orchestrates site-content-catalog + seo-domain-analyzer + brand-voice-extractor)

Run the full SEO audit to understand:

  • Current content inventory (what exists, by type and topic)
  • Domain authority, organic traffic, keyword rankings
  • Competitive gap matrix (what competitors rank for that the client doesn't)
  • Brand voice profile (writing style to match)

Skill: aeo-visibility

Test AI answer engine visibility for key queries.

Output: Complete picture of where the client stands in search.

2. Identify Content Gaps

From the audit, identify:

Competitive gaps: Keywords competitors rank for that the client doesn't Funnel gaps: Missing content at TOFU, MOFU, or BOFU stages Topic gaps: Industry/vertical content that doesn't exist Comparison gaps: Missing "vs" pages and "alternatives" pages

Prioritize by: search volume x commercial intent x competitive difficulty.

3. Build Keyword Architecture

Organize target keywords by funnel stage:

  • TOFU (awareness): "what is [category]", "[category] use cases", "how to [solve problem]"
  • MOFU (evaluation): "[category] comparison", "how to choose [solution]", "[compliance/technical] requirements"
  • BOFU (decision): "[Company] vs [Competitor]", "[Competitor] alternatives", pricing guides, migration guides

Map each keyword cluster to a content type (blog post, landing page, guide, comparison page).

4. Create Content Calendar

Build a prioritized content calendar:

  1. Week 1-2: Highest-urgency BOFU pages (comparison pages, especially if competitors are publishing attack content)
  2. Week 2-4: Core MOFU guides and evaluation content
  3. Week 4-8: TOFU awareness content and programmatic SEO templates
  4. Ongoing: 2-3 editorial pieces per week

5. Draft Content

Skill: content-asset-creator (for landing pages, reports, one-pagers) Method: AI-assisted drafting with brand voice matching (from brand-voice-extractor output)

For each content piece:

  • Match the client's brand voice and style
  • Include target keywords naturally
  • Build internal linking to related content
  • Include clear CTAs
  • Add structured data / schema markup recommendations

6. Build Internal Linking Architecture

Design the linking structure:

  • TOFU pages link to related MOFU pages
  • MOFU pages link to BOFU pages (comparison, pricing)
  • BOFU pages link to product/signup
  • All pages link to relevant pillar content

7. Publish & Monitor

  • Publish on client's blog/site (or provide drafts for client to publish)
  • Track: organic traffic by page/cluster, rankings by keyword, content-to-signup conversion
  • Monthly: Review which content is ranking, which needs updates

Ongoing Cadence

  • Weekly: Publish 2-3 pieces, monitor rankings
  • Monthly: Review content performance, update calendar, refresh underperforming pages
  • Quarterly: Re-run seo-content-audit to measure progress and identify new gaps

Human Checkpoints

  • After Step 2: Review gap analysis and priority recommendations
  • After Step 4: Review content calendar before drafting
  • After Step 5: Review content drafts before publishing

What's included

·
"Build an SEO content strategy for [client]"
·
"Create a content engine for [company]"
·
"What content should [company] be publishing?"
·
Client website URL
·
Client context.md with ICP, value props, positioning
You Might Also Like

Render Model Comparison Grid

Render a 'model comparison grid' video from a config — a fal-style "same prompt, N contenders" showcase — a dark real-DOM stage where per beat a monospace prompt fades in centered, docks to a small top strip, then a labeled 2-4 panel grid (static images OR muted video clips, mixable per cell) staggers in and holds for comparison, plus a minimal end card — frame-stepped via Playwright (video cells are frame-seeked deterministically) and encoded with FFmpeg. Deterministic assembly, FREE (cell media comes from create-image-fal / create-video-fal, music from create-music-elevenlabs), text stays pixel-crisp. Use for the model-comparison-grid format.

Render Offer Ad

Render a punchy ~12s vertical (9:16) music-only direct-response OFFER ad as a 4-beat kinetic-typography film — HEADLINE slam → real PRODUCT drop → CLAIM/proof → CTA pill — from one config of copy slots, a real product photo, a brand palette, fonts, bpm, and beat split. DETERMINISTIC + FREE (a bundled Remotion project; springs + interpolate, no AI-gen for visuals). Backgrounds are engine gradient divs off the palette, props are inline SVG, the ONLY composited bitmap is the REAL product photo (objectFit:contain, never stretched), and ALL headline/claim/CTA/URL/wordmark text is typeset in the engine — never AI-rendered (the format's credibility guard). A driver binds the config to Remotion input props, renders the 9:16 master, and derives a 1:1 center-crop with ffmpeg. Two gating checks run before render (claim verbs must match the product's physical format; the claim beat needs an edge-entry mechanism prop). Use for the motion-graphics-offer-ad format.

Render Myth Vs Fact

Assemble a myth-vs-fact kinetic-typography explainer video ad (≈29.5s, 9:16) from N myth/fact pairs + hook / turn / punch copy + palette + a brand end-card PNG + a VO track — a hook, 3 red-strike MYTH cards that flip to teal-check FACT cards (per-line strikethrough that crosses EVERY wrapped line), a "what actually works" turn, an optional proof reveal, a punch line, and a static end card. DETERMINISTIC assembly with ZERO AI-gen visuals — HTML hyperframes rendered frame-exact via Playwright (`window.renderAt(t)`, animation a pure function of beat-local time), Whisper beat-snap to VO word onsets, concat at a uniform fps, karaoke `.ass` captions burned last (suppressed on the proof + end-card beats), and a VO + optional music mix (music −20 dB, `amix normalize=0`, tail fade). FREE (Python + Playwright + ffmpeg); the recipe supplies the copy / palette / end-card / VO and gates the paid VO / music / Whisper calls to their own capabilities. Use for the myth-vs-fact format.

Newsletter

Learn to build Growth systems with AI

2-3 compounding systems per week using Claude Code, OpenClaw, and more.