/digital-marketing-pro:data-export

/digital-marketing-pro:data-export

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

Export marketing data — metrics, contacts, campaign results, and performance snapshots — to an external data store for analysis, reporting, or integration with other tools. Supports BigQuery for data warehousing and advanced analytics, Google Sheets for sharing and collaboration with stakeholders, and Supabase for custom database use and application integration. Transforms raw marketing data into clean, structured, tabular formats ready for downstream consumption with full schema documentation. Handles PII redaction when exporting contact data to shared destinations, ensuring compliance with privacy regulations.

Use this command to move data out of the marketing system for external analysis, client reporting, or data warehouse integration. For exporting audience segments specifically, use /digital-marketing-pro:segment-audience to create the segment first, then this command to export the member data.

Execution gate (MANDATORY — cannot be skipped)

1. Present the full preview — recipients / spend / changes / compliance — as an Execution Summary before touching any live system.
2. The user must type yes (or an equivalent explicit approval). ANY other input — ambiguous, implied, partial, or absent approval — cancels the run.
3. Never proceed on ambiguous input. Never auto-retry a failed execution; a failure needs human review before any re-run.
4. Only after the user types yes, record it: python "${CLAUDE_PLUGIN_ROOT}/scripts/approval-manager.py" --brand {slug} --action create-approval --data '{"type":"data-export","platform":"<platform>","content_summary":"<one line from the Execution Summary>","risk_level":"<tier>"}', then python "${CLAUDE_PLUGIN_ROOT}/scripts/approval-manager.py" --brand {slug} --action approve --id {approval_id}. If either command errors, stop and report the error; never work around it with another tool. The record proves the approval step ran for this action; it cannot prove who typed yes.
5. Execute. A write sent through connector_executor.py needs --approval-id and fires only against a matching, unused, unexpired record (see /digital-marketing-pro:execute-action). A write through a connected MCP server tool is outside that code check: it relies on this typed yes and on your host's permission prompt. Afterwards run python "${CLAUDE_PLUGIN_ROOT}/scripts/approval-manager.py" --brand {slug} --action mark-executed --id {approval_id} --data '{"execution_result":"success"}' (or failure).

Input Required

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

• Data type: What to export — metrics (KPIs, channel performance, funnel metrics), contacts (CRM records, segments, lead lists), campaigns (structure, settings, targeting, creative), performance (daily/weekly snapshots, trend data, year-over-year comparisons), or custom query (specific fields and filters defined by the user)
• Destination: Where to export — BigQuery (project, dataset, and table name), Google Sheets (existing spreadsheet ID or create new with specified name), or Supabase (project reference, schema, and table name)
• Date range: Time period for the export — specific start and end dates, relative window (last 7/30/90/365 days), quarter-to-date, year-to-date, or all available historical data
• Filters (optional): Criteria to narrow the export — specific channels, campaigns, audience segments, geographic markets, device types, performance thresholds (e.g., only campaigns with ROAS above 2.0), or custom field values
• Format preferences: Column ordering priority (dimensions first or metrics first), naming conventions (snake_case, camelCase, Title Case), date format (ISO 8601, MM/DD/YYYY, YYYY-MM-DD), currency formatting (symbol, code, decimal places), timezone for timestamps, and whether to include calculated fields (percentages, ratios, period-over-period deltas)
• Append or replace: Whether to append new data to existing destination table/sheet or replace the entire contents — critical for recurring exports where append prevents data duplication while replace ensures a clean snapshot
• Schema preferences (optional): Custom column definitions, data types, or transformations — e.g., "split full name into first_name and last_name", "convert all currencies to USD", "aggregate daily data to weekly", or "pivot channels into columns"
• Scheduling (optional): Whether this is a one-time export or should be saved as a recurring export template — if recurring, specify frequency (daily, weekly, monthly) and any conditional triggers (e.g., only export when new data is available)
• Access permissions (optional): For Google Sheets, who should have access (specific emails, domain-wide, or public link). For BigQuery, which service accounts or users need query access. For Supabase, which API keys or roles need read access.
• PII handling (optional): Whether to redact, hash, or anonymize personally identifiable information — relevant when exporting contact data to shared destinations or less-secured environments
• Comparison baseline (optional): Whether to include prior period data alongside the current export for trend analysis — e.g., include both current month and previous month side-by-side, or add period-over-period change columns
• Summary row preferences (optional): Whether to include aggregation rows — totals, averages, or weighted averages at the bottom of the export for quick reference without additional calculation
• Notification on completion (optional): Whether to send a notification when the export finishes — email with download link, Slack message with summary stats, or CRM activity log entry referencing the exported data

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 and relevant category files. 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. Gather data from available sources: Collect data from local storage — ~/.claude-marketing/brands/{slug}/campaigns/ (via campaign-tracker.py --action list-campaigns), ~/.claude-marketing/brands/{slug}/executions/ (via execution-tracker.py --action get-history), ~/.claude-marketing/brands/{slug}/performance/ snapshots, insights files, and segment exports — and from connected MCPs (Google Analytics, ad platforms, CRM, email platform) based on the requested data type and date range. Merge data from multiple sources where needed, resolving conflicts by source priority.