mirror of
https://github.com/alirezarezvani/claude-skills.git
synced 2026-10-11 03:37:58 +00:00
f61fc7b0ac
Phase 1 of the marketing skills improvement plan. Inspired by patterns from claude-seo (4.7k stars) and claude-ads (2.4k stars) — the highest- traction Claude Code plugins in the SEO/ads space. Adopts their best patterns without replacing our existing skills. seo-audit additions: - scripts/seo_health_scorer.py — weighted 0-100 health score across 7 categories (Technical 22%, Content 23%, On-Page 20%, Schema 10%, Performance 10%, AI Readiness 10%, Images 5%). Industry profiles (SaaS/ecommerce/local/publisher) adjust weights. Severity-weighted scoring with Critical/High/Medium/Low priority levels and Quick Wins extraction. Demo mode included. - references/cwv-thresholds.md — Core Web Vitals 2026 thresholds (LCP, CLS, INP) with good/needs-improvement/poor ranges and common fixes - references/eeat-framework.md — E-E-A-T audit checklist per Google's Sept 2025 Quality Rater Guidelines, YMYL topic handling - references/schema-types.md — active/deprecated JSON-LD types with validation checklist and common mistakes paid-ads additions: - scripts/ad_health_scorer.py — multi-platform ad account scoring with severity multipliers (Critical=5x, High=3x, Medium=1.5x, Low=0.5x). Platform-specific category weights for Google (6 categories, 74 checks), Meta (4 categories), LinkedIn (4), TikTok (4). Cross-platform aggregation weighted by budget share. Quick Wins prioritization. Demo mode with Google + Meta sample data. - references/scoring-system.md — full scoring algorithm, severity multipliers, platform weights, grade bands, quality gates (hard rules like "never Broad Match + Manual CPC") - references/copy-frameworks.md — 6 ad copy frameworks (PAS, BAB, AIDA, FAB, 4P, Star-Story-Solution) with selection matrix by product type, platform-specific character limits, and brand DNA extraction (7 voice axes as JSON schema) Key patterns adopted from claude-seo/ads: - Weighted numeric scores replace binary pass/fail - Severity multipliers make critical issues dominate the score - Industry/platform auto-detection adjusts weights - Quick Wins = high severity + partially working (warn not fail) - Reference files are lazy-loaded, not inline - Demo mode with realistic sample data All scripts stdlib-only, --json + --help verified. Also saved: documentation/implementation/marketing-skills-improvement-plan.md covering all 3 phases (Phase 2: content scoring, Phase 3: AI detection). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| craighewitt-mattpocock-reimplementation-plan.md | ||
| implementation-plan-november-2025.md | ||
| marketing-skills-improvement-plan.md | ||
| SKILLS_REFACTORING_PLAN.md | ||