$npx -y skills add indranilbanerjee/contentforge --skill content-refreshRefresh existing content with updated data, sources, and SEO while preserving rankings and brand compliance.
| 1 | # Content Refresh Workflow |
| 2 | |
| 3 | Re-optimize existing content with updated research, current statistics, new sources, refreshed SEO keywords, and Phase 6.5 humanization — while preserving what's working and maintaining search rankings. |
| 4 | |
| 5 | ## When to Use |
| 6 | |
| 7 | Use `/contentforge:content-refresh` when: |
| 8 | - Content is 6+ months old and needs updated stats/examples |
| 9 | - Search rankings are declining (lost top 10 position) |
| 10 | - Competitor content has surpassed yours |
| 11 | - Product/service features have changed |
| 12 | - Industry landscape has shifted |
| 13 | - Content scored well originally (≥7.0) but needs freshening |
| 14 | |
| 15 | ## What This Command Does |
| 16 | |
| 17 | 1. **Load Existing Content** — Read current .docx from Google Drive |
| 18 | 2. **Analyze What to Keep** — Identify evergreen sections, high-performing segments |
| 19 | 3. **Research Updates** — Find current statistics, new sources, recent examples |
| 20 | 4. **Selective Rewrite** — Update outdated sections, preserve working content |
| 21 | 5. **Re-run Quality Gates** — Fact-check new claims, re-humanize, re-score |
| 22 | 6. **SEO Preservation** — Maintain target keywords, internal links, meta structure |
| 23 | 7. **Version Control** — Save as v1.1, v1.2 (never overwrite v1.0) |
| 24 | |
| 25 | ## Required Inputs |
| 26 | |
| 27 | **Existing Content:** |
| 28 | - Google Drive URL or File ID |
| 29 | - OR: Local .docx file path |
| 30 | |
| 31 | **Refresh Scope (select one):** |
| 32 | - **Light Refresh** (20%): Update statistics, examples, citations only |
| 33 | - **Medium Refresh** (50%): Rewrite intro/conclusion, update 3-5 sections, add new research |
| 34 | - **Heavy Refresh** (80%): Complete rewrite using original as outline, keep only evergreen insights |
| 35 | |
| 36 | **Optional:** |
| 37 | - New target keywords (if pivoting focus) |
| 38 | - Sections to preserve (mark as "DO NOT EDIT") |
| 39 | - Deadline (for priority ranking in batch) |
| 40 | |
| 41 | ## How to Use |
| 42 | |
| 43 | ### Basic Usage |
| 44 | ``` |
| 45 | /contentforge:content-refresh https://docs.google.com/document/d/XYZ123 |
| 46 | ``` |
| 47 | **Prompt:** "What refresh scope? (light / medium / heavy)" |
| 48 | |
| 49 | ### With Scope Specified |
| 50 | ``` |
| 51 | /contentforge:content-refresh https://docs.google.com/document/d/XYZ123 --scope=medium |
| 52 | ``` |
| 53 | |
| 54 | ### Batch Refresh (multiple pieces) |
| 55 | Run the refresh sheet through `/contentforge:batch-process` — point it at a sheet whose rows reference existing documents: |
| 56 | ``` |
| 57 | /contentforge:batch-process https://docs.google.com/spreadsheets/d/ABC123 |
| 58 | ``` |
| 59 | Sheet columns: `doc_url`, `refresh_scope`, `priority` |
| 60 | |
| 61 | ## What Happens |
| 62 | |
| 63 | ### Step 1: Content Analysis (2-3 minutes) |
| 64 | - Load existing content from Google Drive |
| 65 | - Extract metadata (original publish date, current word count, quality score) |
| 66 | - Identify sections: intro, body paragraphs, conclusion, citations |
| 67 | - **Evergreen Detection**: Flag sections that are timeless (definitions, principles, frameworks) |
| 68 | - **Outdated Detection**: Flag statistics >12 months old, broken links, deprecated examples |
| 69 | - Calculate "freshness score" (0-100, based on %outdated) |
| 70 | |
| 71 | **Output:** |
| 72 | ``` |
| 73 | Content Analysis Report |
| 74 | ───────────────────────────────────────────────────── |
| 75 | Title: "AI in Healthcare: 2025 Trends and Predictions" |
| 76 | Original Publish: 2025-03-15 |
| 77 | Current Word Count: 2,340 words |
| 78 | Original Quality Score: 8.9/10 |
| 79 | |
| 80 | Freshness Score: 42/100 (Needs Refresh) |
| 81 | |
| 82 | Evergreen Sections (Keep): |
| 83 | ✓ Para 2: Definition of AI in healthcare |
| 84 | ✓ Para 5: Historical context (2010-2020) |
| 85 | ✓ Para 8: Ethical considerations framework |
| 86 | |
| 87 | Outdated Sections (Update): |
| 88 | ⚠ Para 1: Intro references "2025 predictions" (now outdated) |
| 89 | ⚠ Para 3: Statistics from 2024 market report |
| 90 | ⚠ Para 6: Example of startup acquired in 2025 |
| 91 | ⚠ Para 10: Conclusion mentions "upcoming 2025 regulations" |
| 92 | ⚠ Citations: 6/15 links are broken (404 errors) |
| 93 | |
| 94 | Recommendation: Medium Refresh (50% rewrite) |
| 95 | ───────────────────────────────────────────────────── |
| 96 | ``` |
| 97 | |
| 98 | ### Step 2: Research Phase (Targeted) |
| 99 | - Run Phase 1 (Research Agent) focused ONLY on outdated sections |
| 100 | - Search for: Current statistics (2026), new case studies, recent regulatory changes |
| 101 | - Find replacement sources for broken citations |
| 102 | - **Preserve existing sources** for evergreen content |
| 103 | |
| 104 | ### Step 3: Selective Rewrite |
| 105 | - **Keep evergreen sections unchanged** (no rewrite) |
| 106 | - **Update outdated sections** with new research |
| 107 | - **Rewrite intro/conclusion** to reflect current year, updated predictions |
| 108 | - **Maintain article structure** (same H2/H3 hierarchy) |
| 109 | - **Preserve internal links** and brand-specific terminology |
| 110 | |
| 111 | ### Step 4: Re-run Quality Pipelines |
| 112 | - **Phase 2 (Fact-Checker)**: Verify ONLY new claims and updated statistics |
| 113 | - **Phase 4 (Validator)**: Check for hallucinations in rewritten sections |
| 114 | - **Phase 5 (Structurer)**: Ensure refreshed content flows naturally with preserved sections |
| 115 | - **Phase 6 (SEO)**: Maintain keyword density ±0.3%, preserve meta structure |
| 116 | - **Phase 6.5 (Humanizer)**: Re-humanize rewritten sections |
| 117 | - **Phase 7 (Reviewer)**: Re-score (target: ±0.5 points from original score) |
| 118 | |
| 119 | ### Step 5: Version Control |
| 120 | - Original: `Article-AI-Healthcare_v1.0.docx` (never mod |