Help us improve
Share bugs, ideas, or general feedback.
Scans connected marketing platforms for statistically significant anomalies in traffic, cost, conversions, and deliverability. Useful for early detection of issues or opportunities.
npx claudepluginhub indranilbanerjee/digital-marketing-proHow this skill is triggered — by the user, by Claude, or both
Slash command
/digital-marketing-pro:anomaly-scanThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Scan all connected marketing platforms for anomalies — statistically significant deviations from established baselines that could indicate problems (traffic drops, CPA spikes, deliverability collapse, budget overruns) or opportunities (viral content, conversion rate improvements, unexpected channel growth). Designed to catch issues early, before they compound into costly problems, and to surfac...
Pulls live marketing metrics from connected analytics platforms for a KPI health snapshot with target comparisons.
Analyzes marketing data (Meta Ads, TikTok Ads, GA4, Shopify) using a four-stage framework: Descriptive, Diagnostic, Predictive, Prescriptive. Outputs structured .md reports with actionable recommendations.
Detects acquisition divergence, attribution breakage, landing page failures, and page-performance regressions in PostHog web analytics data, comparing segments against their own history rather than aggregates.
Share bugs, ideas, or general feedback.
Scan all connected marketing platforms for anomalies — statistically significant deviations from established baselines that could indicate problems (traffic drops, CPA spikes, deliverability collapse, budget overruns) or opportunities (viral content, conversion rate improvements, unexpected channel growth). Designed to catch issues early, before they compound into costly problems, and to surface wins worth amplifying.
The user must provide (or will be prompted for):
~/.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.scripts/performance-monitor.py --brand {slug} --action get-baseline
to retrieve rolling averages, standard deviations, and expected ranges for each metric. If no baseline exists yet,
use the comparison period data to establish a temporary baseline and note this in the output.scripts/performance-monitor.py --brand {slug} --action detect-anomalies --sensitivity {level}
to flag metrics that fall outside expected ranges based on the chosen sensitivity threshold.
Apply day-of-week and seasonality adjustments where historical data supports it.scripts/execution-tracker.py --brand {slug} --action get-history --days 14
to correlate anomalies with recent changes — did a campaign launch, pause, budget shift, creative swap,
landing page change, or audience expansion precede the anomaly?skills/analytics-insights/anomaly-diagnosis.md. Categorize as data/tracking issue, external factor
(algorithm update, competitor action, seasonal shift), internal change (campaign modification, landing page
update), or platform change (policy update, feature deprecation, auction dynamics shift).scripts/campaign-tracker.py --brand {slug} --action add-insight
so they are tracked, surface in future reports, and can be referenced in post-mortems.A structured anomaly report containing: