/digital-marketing-pro:rank-monitor

/digital-marketing-pro:rank-monitor

Script location. If your host does not set ${CLAUDE_PLUGIN_ROOT}, the scripts are in this plugin's scripts/ folder, next to skills/. Run them with Python 3.10 or newer: python, or python3 where python is not found (macOS, many Linux systems).

Purpose

Set up and manage keyword ranking monitoring — and, with --features, SERP-feature tracking in the same run. Track target keyword positions across Google, establish baselines, detect drops greater than 5 positions, and generate alerts when rankings change significantly. In --features mode, also track which SERP features appear for each query (AI Overviews, Featured Snippets, People Also Ask, Knowledge Panels, Local Pack, Image Pack, Video Carousel, Shopping) and whether the brand owns them. This gives ongoing visibility into organic performance — catching ranking declines early, spotting upward trends, and tracking the increasingly feature-rich results page.

Merged skill (was rank-monitor + serp-tracker). SERP-feature tracking is now the --features mode of this one skill. The old /digital-marketing-pro:serp-tracker is a deprecation pointer to here.

Data sources (read this before configuring)

• Google Search Console MCP is the authoritative position + impressions source for verified properties. GSC returns per-query/per-page positions, impressions, clicks, and CTR — it does not return the full per-query SERP-feature layout or AI Overview citation lists. Do not claim otherwise.
• Rank-tracker MCPs (Ahrefs / Semrush / SE Ranking, if connected) fill in positions for keywords/competitors GSC can't see and provide their own SERP-feature flags.
• SERP snapshot file (optional, from any provider): if the brand already exports per-query SERP results from any SERP API or rank tracker, pass the export with --serp-snapshot <file> and validate it first:

  python "${CLAUDE_PLUGIN_ROOT}/scripts/serp-snapshot.py" --file <export.csv|export.json> --brand-domain <brand domain>
  

  Its rows supply position, AI Overview presence and citation, People Also Ask and featured-snippet ownership for those queries. The format is in serp-snapshot-format.md beside this file. The script reads only that file (no network, no API key, no provider code), exits 1 and lists every bad row if the export is malformed (show the errors and do not use the file), and nothing changes when no file is given.
• Moz MCP (mcp-moz) is optional — verify the package exists on npm before use (npm view mcp-moz); npx executes remote code, so don't wire an unverified package. If Moz isn't connected, use GSC + whichever rank-tracker MCP the brand already has.
• AI Overview presence in --features mode records only whether an AI Overview appeared and whether the brand was cited in it (a binary SERP-feature signal). For scored AI-visibility measurement across the 6 canonical AI surfaces, use /digital-marketing-pro:geo-monitor / /digital-marketing-pro:aeo-audit (the canonical AI-visibility scoring standard) and, for actual impressions, /digital-marketing-pro:gsc-ai-performance. Do not re-implement AI-visibility scoring here.

Input Required

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

• Target keywords: A list of keywords to monitor — provided directly, imported from a CSV or Google Sheet, or pulled from the brand's existing keyword tracking list at ${CLAUDE_PLUGIN_DATA}/{brand}/seo/keywords.json. Keywords should include search intent classification (informational, navigational, transactional, commercial) if available
• Mode: default is rankings-only. Pass --features to also build the SERP-feature presence matrix per query in the same run
• Monitoring frequency: daily or weekly — daily for high-priority head terms and active-campaign keywords (and volatile feature sets), weekly for long-tail and lower-priority terms
• Alert thresholds: Position change that triggers an alert — default is >5 position drop. Customizable per keyword group (e.g., >3 for brand terms, >5 for head terms, >10 for long-tail). Both drop and gain thresholds are supported
• Competitor domains (optional): Domains to track alongside the brand for the same keywords / features — up to 10
• Device type: mobile, desktop, or both
• Target country: The Google locale to check rankings in — e.g., US, UK, AU, CA, IN

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 brand voice, compliance rules for target markets (skills/context-engine/compliance-rules.md), and industry context. Also check for guidelines at ~/.claude-marketing/brands/{slug}/guidelines/_manifest.json — if present, load restrictions. 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 defaults.
2. Capture current rankings baseline: Query the connected rank sources (GSC MCP, plus any rank-tracker / Moz MCP available) for the current ranking position of each target keyword. Record position, ranking URL, click-through rate and impressions from GSC where available. In --features mode, also record which SERP features are present for the query (from the rank-tracker's feature flags, a validated SERP snapshot file, or manual observation) and the owning domain per feature, and say which source each query's flags came from. For competitor domains, capture their positions (and feature ownership) for the same keywords.
3. Configure monitoring schedule: Save the keyword list, mode (rankings or rankings+features), monitoring frequency, alert thresholds, competitor domains, device type, and target country to ${CLAUDE_PLUGIN_DATA}/{brand}/seo/rank-monitor/config.json. Create or update the baseline snapshot at ${CLAUDE_PLUGIN_DATA}/{brand}/seo/rank-monitor/baseline.json with the current positions (and, in --features mode, the feature matrix) as the reference point.
4. On each monitoring check: query and compare: Pull current positions for all tracked keywords. Compare each keyword's current position to both the baseline (original position when monitoring started) and the previous check (last recorded position). Calculate absolute change from baseline, change since last check, rolling 7-day and 30-day trend direction, and average position across all tracked keywords. In --features mode, diff the feature matrix against the previous snapshot (features gained/lost, ownership changes, AI Overview appearance/citation changes).