cyberneticlibrary

Produce multi-surface optimized articles

blog-writerskillsetup L10
prtikku-ships/claude-code-builds

Causal-lift measurements

seo-content-optimization+13pp vs no-skill baselinewith-skill 70% · baseline 57%

Measured by running the task with and without this artifact, K=5, graded by deterministic checks — no LLM judging.

What it does

Produce SEO-optimized articles optimized across discovery surfaces for lead generation

Best for

SaaS and service brands that need articles to generate signups/applications/consultations (not just traffic) and want to rank across Google, ChatGPT, Perplexity, and LinkedIn simultaneously.

Inputs
  • · Brand name and one-sentence description
  • · Primary landing pages (program, pricing, signup)
  • · 2-4 audience segments with pain points each
  • · Voice/tone descriptors and required vocabulary
  • · E-E-A-T signals (years in business, customer count, accreditations, named experts)
  • · Primary conversion event (signup, consultation, enrollment)
  • · Internal linking inventory (URLs, keywords, sessions, conversion rates)
  • · Query data (GSC export: keywords, impressions, CTR, position)
Outputs
  • · Brief with target keyword, search intent classification, why-now rationale
  • · 1,200-2,500 word article (optimized for search + AI answer engines + social)
  • · Internal link placement map
  • · CTA copy tied to conversion goal and funnel stage
  • · SEO metadata (title tag, meta description)
Preconditions
  • · Target keyword must be defined upfront
  • · Content-Market Fit Rule must be articulated (what brand is NOT)
  • · Editorial review chain documented
Failure modes
  • · Without BUSINESS_CONTEXT, pain points become generic
  • · Chasing high-volume keywords outside brand positioning requires disclaimers
  • · No internal link strategy → missed SEO equity and conversion funnel
  • · Article optimized only for Google rankings, not AI answer engines or social
Trust signals
  • · Explicit Content-Market Fit Rule test (no disclaimers needed = good fit)
  • · E-E-A-T signals required upfront (accreditations, named experts, customer count)
  • · Vertical-agnostic but context-aware (gathers intent data per brand first run)
  • · Conversion model explicitly tied to product SKUs and audience segments
  • · Conversion ladder framework (awareness → interest → decision)