/content-decay-scan

name: content-decay-scan
description: "Scan the content library for decay — declining traffic, falling keyword positions, stale content, broken links, lost AI citations — scoring each URL 0-100 via creative-fatigue-predictor.py and ranking refreshes by recoverable revenue, with actionable refresh briefs and traffic-recovery estimates for top-priority tiers. Triggers on \"/digital-marketing-pro:content-decay-scan\", \"which content is losing traffic\", \"find stale content to refresh\", \"our blog traffic keeps dropping\", \"prioritize content refreshes\". Pulls performance data from Google Analytics/Search Console MCPs or exported CSVs; cross-reference causes with /digital-marketing-pro:seo-drift. Reads the brand profile for content strategy context."
user-invocable: true
triggers:
  - scan for content decay
  - find declining content
  - content refresh audit
  - which content needs updating
  - content losing traffic
  - find stale content
  - content decay analysis
  - prioritize content refreshes

/digital-marketing-pro:content-decay-scan

Purpose

Scan the entire content library for decay signals and prioritize refreshes by business impact. Content decay is invisible revenue loss — pages that once ranked well and drove conversions silently lose traffic as competitors publish fresher content, search algorithms evolve, statistics become outdated, and AI systems stop citing stale sources. This command detects declining organic traffic, falling keyword positions, outdated content (stale dates, broken links, deprecated information), lost AI citations, and conversion rate drops. It then ranks every piece of content by business impact — traffic multiplied by conversion rate multiplied by revenue per conversion — so you refresh the content that recovers the most revenue first, not just the content that lost the most traffic.

Input Required

The user must provide (or will be prompted for):

• **Content library data**: URLs of the content to scan — can be a full sitemap, a specific content directory (e.g., /blog/*, /resources/*), or a curated list of high-value pages. For each URL, the system will pull or needs: current monthly traffic, traffic 3 and 6 months ago for trend analysis, primary keyword rankings (current and historical positions), publish date and last updated date, conversion rate if tracked (form fills, signups, purchases), and revenue attribution if available
• **Analytics source**: Where to pull performance data — Google Analytics and Google Search Console via connected MCPs, or exported CSV data. If MCPs are connected, data is pulled automatically. If not, the user provides exported analytics covering at least the past 6 months
• **Priority metrics**: Which decay signals matter most for this scan — traffic decline (default highest weight), ranking drops, content freshness (time since last update), AI citation loss, broken links, or conversion rate decline. The user can adjust weights or accept defaults. Revenue impact is always calculated regardless of signal weights
• **Decay thresholds (optional)**: Brand-specific thresholds for what constitutes "decay" — e.g., "flag anything with 20%+ traffic decline over 3 months" or "flag content not updated in 12+ months." If not provided, standard thresholds are applied: 15% traffic decline over 3 months, 10+ position drop on primary keyword, 18+ months since last update, or 20%+ conversion rate decline
• **Exclusions (optional)**: Content to exclude from the scan — seasonal pages, archived content, redirect targets, or pages scheduled for removal. Prevents false positives and focuses the scan on content the brand intends to maintain

Process

1. **Load brand context**: Read `~/.claude-marketing/brands/_active-brand.json` for the active slug, then load `~/.claude-marketing/brands/{slug}/profile.json`. Apply content strategy priorities, target keyword clusters, historical content performance baselines, and industry context for freshness expectations (fast-moving industries like tech need more frequent updates than evergreen niches). Also check for guidelines at `~/.claude-marketing/brands/{slug}/guidelines/_manifest.json`. Check for agency SOPs at `~/.claude-marketing/sops/`. If no brand exists, ask: "Set up a brand first (/digital-marketing-pro:brand-setup)?" — or proceed with industry defaults. 2. **Gather content performance data**: Connect to analytics MCPs (Google Analytics, Google Search Console) and pull performance data for the content library — monthly traffic for the past 6 months per URL, keyword position data for primary and secondary keywords, click-through rates from search results, and conversion data if available. For content not covered by MCPs, use any exported data the user provided. Build a performance timeline for each content piece showing the trajectory over the past 6 months. 3. **Score each content piece for decay**: Run the decay scorer with the performance data:

   python "${CLAUDE_PLUGIN_ROOT}/scripts/creative-fatigue-predictor.py" \
       --action decay-scan \
       --data '[{"content_id":"blog_01","url":"/blog/post-a","monthly_traffic_current":1200,"monthly_traffic_previous":1600,"monthly_traffic_6mo_ago":2100,"keyword_positions_current":{"seo tips":12},"keyword_positions_previous":{"seo tips":7},"last_updated":"2024-11-01"}, ...]'

(`creative-fatigue-predictor.py` actions: `score-health`, `predict-fatigue`, `generate-refresh-brief`, `decay-scan`, `priority-refresh`, `batch-health`. `--data` is a JSON object or array; there is no `--brand` flag on this script.) The decay scoring model evaluates multiple signals per content piece — traffic trend (3-month and 6-month decline rates, weighted by the user's priority metrics), keyword position changes (drops on primary keyword, movement direction and velocity), content freshness (months since last substantive update, presence of dated statistics or references), broken links (internal and external link health), and convers