$npx -y skills add AgriciDaniel/claude-blog --skill blog-rewriteRewrite and optimize existing blog posts for Google rankings (December 2025 Core Update, E-E-A-T) and AI citations (GEO/AEO). Full rewrite for both Google rankings AND AI citations. For AI-citation-only audit (no Google work), use blog-geo instead. Replaces fabricated statistics
| 1 | # Blog Rewriter: Optimize Existing Posts |
| 2 | |
| 3 | Rewrites and optimizes existing blog posts for dual ranking: Google search |
| 4 | and AI citation platforms. Preserves the author's voice while applying the |
| 5 | 6 pillars of optimization. |
| 6 | |
| 7 | **Key references:** |
| 8 | - `references/quality-scoring.md` - 5-category scoring (Content 30, SEO 25, E-E-A-T 15, Technical 15, AI Citation 15) |
| 9 | - `references/eeat-signals.md` - Experience, expertise, authority, trust markers |
| 10 | - `references/internal-linking.md` - Linking strategy and anchor text rules |
| 11 | - `references/visual-media.md` - Image sourcing and chart styling |
| 12 | - `skills/blog/references/synthesis-contract.md` - 6 LAWs for re-citation hygiene during rewrite (v1.8.0; cross-skill ref lives in the orchestrator's references dir) |
| 13 | - `skills/blog/references/research-quality.md` - cross-source clustering for replacement-statistic research (v1.8.0) |
| 14 | |
| 15 | ## Cross-reference |
| 16 | |
| 17 | For 21 evidence-led optimization prompts (AI-detector test, CTR audit, schema, PAA rewording, technical audit, ChatGPT visibility) directly applicable to rewrite work, see `/blog flow optimize`. |
| 18 | |
| 19 | ## Workflow |
| 20 | |
| 21 | ### Phase 1: Audit (Read-Only) |
| 22 | |
| 23 | 1. **Read the blog post** - Detect format (MDX, markdown, HTML) |
| 24 | 2. **Run the quality checklist** against `references/quality-scoring.md`: |
| 25 | - Count fabricated vs sourced statistics |
| 26 | - Check answer-first formatting (H2 -> stat in first sentence?) |
| 27 | - Count images and charts (type diversity?) |
| 28 | - Measure paragraph lengths (any > 150 words?) |
| 29 | - Check heading hierarchy (H1 -> H2 -> H3, no skips?) |
| 30 | - Look for FAQ schema |
| 31 | - Check freshness signals (lastUpdated, dateModified) |
| 32 | - Assess self-promotion level |
| 33 | - Evaluate citation tier quality |
| 34 | 3. **AI content detection scan**: |
| 35 | - **Burstiness score** - Measure sentence length variance across the post. Low |
| 36 | variance (most sentences within 3-5 words of each other) is a strong AI signal. |
| 37 | Calculate: standard deviation of sentence word counts. Target SD > 6. |
| 38 | - **Known AI phrase scan** - Check for these high-frequency AI phrases: |
| 39 | - "in today's digital landscape", "it's important to note", "dive into" |
| 40 | - "game-changer", "navigate the landscape", "revolutionize", "seamlessly" |
| 41 | - "cutting-edge", "harness the power of", "leverage" (as verb) |
| 42 | - "delve", "crucial", "elevate", "foster", "landscape" (overused) |
| 43 | - "multifaceted", "robust", "tapestry", "embark" |
| 44 | - Full list in `agents/blog-writer.md` |
| 45 | - **Vocabulary diversity** - Calculate Type-Token Ratio (TTR): unique words / |
| 46 | total words. Low TTR (< 0.40) suggests AI-generated repetitive phrasing. |
| 47 | Target TTR > 0.50 for natural prose. |
| 48 | - **AI content percentage estimate** - Based on burstiness, phrase density, and |
| 49 | TTR, estimate what percentage of the content reads as AI-generated (0-100%). |
| 50 | Report as: "AI content estimate: ~X%" |
| 51 | - **Second-order structural reflex scan** (v1.8.0) - The first-order checks above |
| 52 | are vocabulary-level. The second-order pass catches what survives them: structural |
| 53 | and rhythmic tics LLMs default to after the obvious words are replaced. Run against |
| 54 | `skills/blog/references/ai-slop-detection.md`. Flag at minimum: |
| 55 | - Question-cadence H2s above 70% of headings |
| 56 | - Three or more "Here..." paragraph openers |
| 57 | - Three-clause sentence rhythm above 50% in any 200-word window |
| 58 | - More than 2 hedge words ("may," "often," "typically," "generally") in any 20-word span |
| 59 | - Symmetric-list bloat (list-item word-count SD below 5) |
| 60 | - More than 2 wrap-up rhetorical questions ("What does this mean for...?") |
| 61 | - More than half of H2 openers starting with a transition word |
| 62 | - "The key insight is..." or "What's important here is..." as sentence openers |
| 63 | - Listicle pre-list intro above 250 words |
| 64 | - Opening-word repetition: top three first-words above 25% share |
| 65 | - Paragraph-shape SD below 25 (visual monotony) |
| 66 | A draft is only "AI-detection clean" when both passes are clean. The two-namespace |
| 67 | terminology (first-order/second-order for slop-detection vs Tier 1/2/3 for source |
| 68 | authority) is intentional: see `skills/blog/references/ai-slop-detection.md` for |
| 69 | why |