Initial commit

2025-11-29 17:55:04 +08:00
commit 51ebc9cf32
8 changed files with 605 additions and 0 deletions
--- a/.claude-plugin/plugin.json
+++ b/.claude-plugin/plugin.json
@@ -0,0 +1,16 @@
+{
+  "name": "content-library-auditor",
+  "description": "Analyze WordPress XML, CMS JSON, or CSV exports for content insights. Publishing trends, author breakdowns, topic analysis, and interactive HTML reports with charts.",
+  "version": "1.0.0",
+  "author": {
+    "name": "Tim Metz @ Animalz",
+    "email": "contact@animalz.co",
+    "url": "https://animalz.co"
+  },
+  "agents": [
+    "./agents"
+  ],
+  "commands": [
+    "./commands"
+  ]
+}
--- a/README.md
+++ b/README.md
@@ -0,0 +1,3 @@
+# content-library-auditor
+
+Analyze WordPress XML, CMS JSON, or CSV exports for content insights. Publishing trends, author breakdowns, topic analysis, and interactive HTML reports with charts.
--- a/agents/data-parser.md
+++ b/agents/data-parser.md
@@ -0,0 +1,47 @@
+---
+name: data-parser
+description: Parses WordPress XML, JSON, and CSV content exports into structured data
+model: sonnet
+---
+
+# Data Parser Agent
+
+Extract structured content data from CMS exports (WordPress XML, JSON, CSV).
+
+## Supported Formats
+
+### WordPress XML
+Extract from `<item>` elements:
+- title, pubDate, dc:creator, category, content:encoded
+- Parse dates to standard format
+- Calculate word counts from content
+
+### JSON
+Parse flexible schemas, looking for:
+- Common field names (title/name, date/published/created_at, author/creator)
+- Nested structures (data.posts, items, articles)
+- Array or object formats
+
+### CSV
+Parse with headers:
+- Required: title, date, author
+- Optional: category, tags, word_count, url, status
+
+## Output Format
+
+Return array of content objects:
+```json
+[
+  {
+    "title": "Post Title",
+    "date": "2024-01-15",
+    "author": "Author Name",
+    "categories": ["Category 1"],
+    "word_count": 1500,
+    "url": "/post-slug",
+    "status": "published"
+  }
+]
+```
+
+Sort by date (newest first). Report parsing stats to user.
--- a/agents/publishing-analyzer.md
+++ b/agents/publishing-analyzer.md
@@ -0,0 +1,40 @@
+---
+name: publishing-analyzer
+description: Analyzes publishing trends, cadence, and author contributions
+model: sonnet
+---
+
+# Publishing Analyzer Agent
+
+Analyze publishing patterns and author contributions from parsed content data.
+
+## Publishing Trends Analysis
+
+Calculate:
+- Posts per month (group by year-month)
+- Publishing frequency (posts/week, posts/month averages)
+- Trend direction (increasing/decreasing %)
+- Seasonal patterns
+- Peak and low periods
+
+Present as time series with month-by-month breakdown.
+
+## Author Contribution Analysis
+
+For each author calculate:
+- Total posts
+- Percentage of total content
+- Average post length
+- Publishing frequency (posts/month)
+- Active date range
+- Recent activity (last 3 months)
+
+Rank authors by post count. Identify top contributors vs long-tail.
+
+## Output Format
+
+Markdown report with:
+- Summary stats
+- Month-by-month publishing table
+- Author contribution rankings
+- Key insights and trends
--- a/agents/topic-classifier.md
+++ b/agents/topic-classifier.md
@@ -0,0 +1,41 @@
+---
+name: topic-classifier
+description: Analyzes content topics, categories, and identifies content gaps
+model: sonnet
+---
+
+# Topic Classifier Agent
+
+Analyze topic distribution and identify content opportunities.
+
+## Category Analysis
+
+From provided content data:
+- Count posts per category/tag
+- Calculate percentages
+- Identify most/least covered topics
+- Find orphaned content (no category)
+
+## Topic Patterns
+
+Look for:
+- Common category combinations
+- Topic evolution over time (early vs recent)
+- Emerging topics (growth in last 6 months)
+- Declining topics (decreased coverage)
+
+## Content Gap Identification
+
+Identify opportunities:
+- Underserved topics (<5 posts) that could be expanded
+- Related topics covered but specific angles missing
+- Competitor topics not covered (if competitive data provided)
+- Seasonal gaps (topics not covered in certain periods)
+
+## Output Format
+
+Markdown with:
+- Topic distribution table
+- Top 10 categories
+- Content gap analysis
+- Recommendations for content opportunities
--- a/agents/visualization-generator.md
+++ b/agents/visualization-generator.md
@@ -0,0 +1,48 @@
+---
+name: visualization-generator
+description: Creates interactive HTML reports with Chart.js visualizations
+model: sonnet
+---
+
+# Visualization Generator Agent
+
+Generate interactive HTML reports with charts for content audit data.
+
+## Charts to Generate
+
+### 1. Publishing Trends (Line Chart)
+- X-axis: Months
+- Y-axis: Post count
+- Show 12-24 month trend
+
+### 2. Author Contributions (Bar Chart)
+- X-axis: Author names (top 10)
+- Y-axis: Post count
+- Sorted by count descending
+
+### 3. Topic Distribution (Pie Chart)
+- Categories/topics
+- Show percentages
+- Top 8 categories + "Other"
+
+### 4. Content Length Distribution (Histogram)
+- Word count ranges (0-500, 500-1000, 1000-1500, etc.)
+- Post count per range
+
+## HTML Structure
+
+Create self-contained HTML file with:
+- Embedded CSS (clean, professional styling)
+- Chart.js from CDN
+- Navigation sections
+- Print-friendly styles
+- Responsive design
+
+## Data Tables
+
+Include interactive sortable tables for:
+- All posts (title, date, author, category, word count)
+- Author stats (name, posts, avg length, period)
+- Category stats (name, count, percentage)
+
+Save to `reports/[name]-audit.html`
--- a/commands/audit-content.md
+++ b/commands/audit-content.md
@@ -0,0 +1,349 @@
+---
+description: Comprehensive content library analysis from CMS export files
+argument-hint: [export-file] [--format] [--output-html]
+---
+
+# Audit Content Library
+
+Analyze WordPress XML, CMS JSON, or CSV exports to reveal publishing trends, author contributions, topic distribution, and content opportunities.
+
+## Step 1: Detect and Parse Export File
+
+**Read export file ($1):**
+- Auto-detect format (XML/JSON/CSV) unless --format specified
+- Validate file structure
+- Count total items (posts, pages, etc.)
+
+**Report to user:**
+```markdown
+## 📁 Content Export Detected
+
+**File:** $1
+**Format:** [WordPress XML / JSON / CSV]
+**Items found:** [number] posts/pages
+**Date range:** [earliest] to [latest]
+**File size:** [size]
+
+Would you like to proceed with analysis?
+```
+
+**Wait for user confirmation.**
+
+---
+
+## Step 2: Parse Content Data
+
+Use **data-parser** agent to extract:
+
+**For all formats:**
+- Post titles
+- Publication dates
+- Authors
+- Categories/tags
+- Post length (word count)
+- Status (published/draft)
+- URLs/slugs
+
+**Format-specific:**
+
+**WordPress XML:**
+```xml
+<item>
+    <title>Post Title</title>
+    <pubDate>Date</pubDate>
+    <dc:creator>Author</dc:creator>
+    <category>Category</category>
+    <content:encoded>Body content</content:encoded>
+</item>
+```
+
+**JSON:**
+```json
+{
+  "title": "Post Title",
+  "date": "2024-01-15",
+  "author": "Name",
+  "categories": ["cat1", "cat2"],
+  "content": "Body..."
+}
+```
+
+**CSV:**
+```csv
+title,date,author,category,word_count
+"Post Title","2024-01-15","Author","Category",1500
+```
+
+**Progress report:**
+```
+🔄 Parsing content...
+- ✅ Posts extracted: [number]
+- ✅ Authors identified: [number]
+- ✅ Date range: [range]
+- ✅ Categories: [number]
+```
+
+---
+
+## Step 3: Analyze Publishing Trends
+
+Use **publishing-analyzer** agent to calculate:
+
+**Publishing Cadence:**
+- Posts per month (last 6, 12, 24 months)
+- Publishing frequency trends (increasing/decreasing)
+- Seasonal patterns
+- Content velocity
+
+**Present to user:**
+```markdown
+## 📊 Publishing Trends
+
+### Overall Stats
+- Total posts: [number]
+- Active period: [months/years]
+- Average: [X] posts/month
+- Trend: [Increasing 15% / Stable / Decreasing 10%]
+
+### Recent Performance (Last 6 months)
+- [Month]: [count] posts
+- [Month]: [count] posts
+[etc...]
+
+### Publishing Patterns
+- Peak month: [month] ([count] posts)
+- Lowest month: [month] ([count] posts)
+- Most active day: [day of week]
+
+Would you like to continue with author and topic analysis?
+```
+
+**Wait for user approval.**
+
+---
+
+## Step 4: Author Contribution Breakdown
+
+Use **publishing-analyzer** agent to:
+
+**Calculate per author:**
+- Total posts
+- Percentage of total content
+- Publishing frequency
+- Average post length
+- Active period (first to last post)
+
+**Present breakdown:**
+```markdown
+## ✍️ Author Contributions
+
+**Total authors:** [number]
+
+### Top Contributors
+
+#### 1. [Author Name]
+- **Posts:** [number] ([percentage]% of total)
+- **Avg length:** [words] words
+- **Active:** [date range]
+- **Cadence:** [X] posts/month
+
+#### 2. [Author Name]
+[Same format...]
+
+---
+
+### Long-tail Contributors
+- [number] authors with 1-5 posts ([percentage]% of total)
+
+Continue to topic analysis?
+```
+
+---
+
+## Step 5: Topic & Category Analysis
+
+Use **topic-classifier** agent to:
+
+**Analyze categories/tags:**
+- Distribution by category
+- Most/least covered topics
+- Topic combinations
+- Content gaps
+
+**Present analysis:**
+```markdown
+## 🏷️ Topic Distribution
+
+### By Category
+1. [Category 1]: [count] posts ([percentage]%)
+2. [Category 2]: [count] posts ([percentage]%)
+[etc...]
+
+### Topic Insights
+- **Most covered:** [topic] ([count] posts)
+- **Underserved:** [topics with <5 posts]
+- **Emerging:** [topics showing growth]
+
+### Content Opportunities
+- [Gap 1]: Only [X] posts, could expand
+- [Gap 2]: [Related topics] covered, but [specific angle] missing
+
+Proceed to generate report?
+```
+
+---
+
+## Step 6: Generate Reports
+
+**Ask user for output preference:**
+```
+📊 Report Format
+
+Choose output format:
+1. Terminal view (ASCII charts) - Quick review
+2. Markdown file - For documentation
+3. HTML report - Interactive charts (recommended)
+4. All formats
+
+Which would you like?
+```
+
+### Terminal View (ASCII Charts)
+
+```
+Publishing Trends (Last 12 Months)
+═══════════════════════════════════
+Jan 2024  ████████░░ 12 posts
+Feb 2024  ██████░░░░  9 posts
+Mar 2024  ███████████ 15 posts
+[etc...]
+
+Top Authors
+═══════════════════════════════════
+Alice Smith    ████████████████ 45 posts (35%)
+Bob Johnson    ██████████░░░░░░ 28 posts (22%)
+[etc...]
+```
+
+### Markdown Report
+
+Save to `reports/[filename]-audit.md`:
+```markdown
+# Content Audit Report
+
+**Analyzed:** [date]
+**Source:** [filename]
+**Period:** [date range]
+
+## Executive Summary
+[Key findings]
+
+## Metrics
+[Full breakdowns]
+```
+
+### HTML Report (with Charts)
+
+Use **visualization-generator** agent to create:
+- Line chart: Publishing trends
+- Bar chart: Author contributions
+- Pie chart: Topic distribution
+- Interactive data tables
+
+Save to `reports/[filename]-audit.html`
+
+---
+
+## Step 7: Deliver Results
+
+**Report completion:**
+```markdown
+## ✅ Content Audit Complete!
+
+**Analysis period:** [date range]
+**Total content:** [number] posts
+**Authors:** [number]
+**Categories:** [number]
+
+### Key Findings
+- [Finding 1]
+- [Finding 2]
+- [Finding 3]
+
+### Reports Generated
+- Terminal summary: [displayed above]
+- Markdown: reports/[name]-audit.md
+- HTML: reports/[name]-audit.html (open in browser)
+
+### Recommended Actions
+1. [Action based on findings]
+2. [Action based on findings]
+3. [Action based on findings]
+
+**Next steps:**
+- Use `/publishing-trends` for deeper time-series analysis
+- Use `/topic-analysis` to explore specific categories
+```
+
+---
+
+## Usage Examples
+
+```bash
+# WordPress export
+/audit-content wordpress-export.xml --output-html
+
+# JSON export from headless CMS
+/audit-content content-export.json
+
+# CSV from analytics
+/audit-content content-metrics.csv --format csv
+
+# With specific output format
+/audit-content export.xml --format wordpress --output markdown
+```
+
+---
+
+## Supported Formats
+
+| Format | Auto-detect | Notes |
+|--------|-------------|-------|
+| **WordPress XML** | ✅ | Standard WP export |
+| **JSON** | ✅ | Any CMS JSON with title/date/author fields |
+| **CSV** | ✅ | Must have title,date,author columns minimum |
+| **Custom** | Specify with --format | Provide field mapping |
+
+---
+
+## Tips for Best Results
+
+### Export Best Practices
+
+**WordPress:**
+1. Tools → Export → All content
+2. Download XML file
+3. Run audit
+
+**Headless CMS:**
+- Export with all metadata (author, dates, categories)
+- Include content body for word count analysis
+- JSON or CSV format preferred
+
+**Analytics Export:**
+- Include title, publish date, author, URL
+- CSV works well for this
+
+### Data Quality
+
+✅ **Ensure export includes:**
+- Publication dates (for trend analysis)
+- Author names (for contribution breakdown)
+- Categories/tags (for topic analysis)
+- Content/word count (for depth analysis)
+
+❌ **Watch out for:**
+- Drafts mixed with published (can filter)
+- Inconsistent date formats
+- Missing author attribution
+- Incomplete exports (verify date range)
--- a/plugin.lock.json
+++ b/plugin.lock.json
@@ -0,0 +1,61 @@
+{
+  "$schema": "internal://schemas/plugin.lock.v1.json",
+  "pluginId": "gh:animalzinc/claude-plugins:plugins/content-library-auditor",
+  "normalized": {
+    "repo": null,
+    "ref": "refs/tags/v20251128.0",
+    "commit": "1639f6ff1104f62ad5806e0b41e37389b9436bbc",
+    "treeHash": "a643e040db0ad7a59e0313da3833a23d2a0088bc293cc5411fcef7420c352e22",
+    "generatedAt": "2025-11-28T10:13:44.713884Z",
+    "toolVersion": "publish_plugins.py@0.2.0"
+  },
+  "origin": {
+    "remote": "git@github.com:zhongweili/42plugin-data.git",
+    "branch": "master",
+    "commit": "aa1497ed0949fd50e99e70d6324a29c5b34f9390",
+    "repoRoot": "/Users/zhongweili/projects/openmind/42plugin-data"
+  },
+  "manifest": {
+    "name": "content-library-auditor",
+    "description": "Analyze WordPress XML, CMS JSON, or CSV exports for content insights. Publishing trends, author breakdowns, topic analysis, and interactive HTML reports with charts.",
+    "version": "1.0.0"
+  },
+  "content": {
+    "files": [
+      {
+        "path": "README.md",
+        "sha256": "ab40de72915f51fb86c1abf8fab3edd5b7ffb8df4346e28ca5fcfecbada87293"
+      },
+      {
+        "path": "agents/topic-classifier.md",
+        "sha256": "e764a2981b138b75557bbcb05cee694da147a7c49c0fb285a55a572faa813e44"
+      },
+      {
+        "path": "agents/publishing-analyzer.md",
+        "sha256": "e91af534d5de343cfde4a51508d412e6e86fcfeecb4aee7daaf9eca65c60e0ff"
+      },
+      {
+        "path": "agents/visualization-generator.md",
+        "sha256": "b34165e2be69c9973dd3c55434b1810d90f868d0ef6ea397d66b2ab85cc8bc0c"
+      },
+      {
+        "path": "agents/data-parser.md",
+        "sha256": "30d2dc02e91159694c1793f9b2f8d96a9fb940f5a31661c5d0bb7c4c3fbb99f8"
+      },
+      {
+        "path": ".claude-plugin/plugin.json",
+        "sha256": "c08af0761f354fc45ff3829977b73381ab5bd1e400b75c3c1eded235a7bd4a66"
+      },
+      {
+        "path": "commands/audit-content.md",
+        "sha256": "b28a273a26dd62a6286df37356b00f97f450dee70bcff78b7b5512ed1f68cf9b"
+      }
+    ],
+    "dirSha256": "a643e040db0ad7a59e0313da3833a23d2a0088bc293cc5411fcef7420c352e22"
+  },
+  "security": {
+    "scannedAt": null,
+    "scannerVersion": null,
+    "flags": []
+  }
+}