/digital-marketing-pro:segment-audience

/digital-marketing-pro:segment-audience

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

Create or update audience segments in the brand's CRM or email platform based on behavioral, demographic, or engagement criteria. Segments can be used for ad targeting, email campaigns, retargeting, or personalization. Ensures segments are well-defined, properly sized, actionable across platforms, and documented with clear criteria for reproducibility — so the team can understand exactly who is in a segment and why. Supports RFM (recency, frequency, monetary) modeling, lifecycle-based segmentation, and predictive scoring criteria for advanced audience strategies.

Use this command to build targeting audiences before campaign launches. For importing new contacts into the CRM first, use /digital-marketing-pro:lead-import. For exporting segment member data to external tools, use /digital-marketing-pro:data-export after segment creation.

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 "${CLAUDE_PLUGIN_ROOT}/scripts/approval-manager.py" --brand {slug} --action create-approval --data '{"type":"segment-audience","platform":"<platform>","content_summary":"<one line from the Execution Summary>","risk_level":"<tier>"}', then python "${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):

• Segment criteria: The rules that define segment membership — demographics (age, location, job title, company size, industry), behaviors (pages visited, emails opened, links clicked, purchases made, events attended), engagement levels (active last 30/60/90 days, lapsed, at-risk, churned), purchase history (recency, frequency, monetary value, product category), lifecycle stage (subscriber, lead, MQL, customer), or custom field filters
• Target platform: Where the segment will be created — CRM (Salesforce, HubSpot, Zoho, Pipedrive), email platform (ActiveCampaign, Mailchimp), or ad platform (Meta Custom Audiences, Google Ads Customer Match, LinkedIn Matched Audiences, TikTok Custom Audiences)
• Segment name: A descriptive, standardized name following the brand's naming conventions — e.g., "High-Value-Customers-Last-90d" or "MQL-SaaS-Enterprise-US"
• Segment purpose: How this segment will be used — email campaign targeting, paid ad audience, retargeting pool, personalization cohort, suppression/exclusion list, lookalike seed audience, or cross-sell/upsell targeting
• Dynamic vs. static: Whether the segment should auto-update as contacts meet or leave criteria (dynamic/smart list) or remain fixed at time of creation (static/snapshot) — dynamic for ongoing campaigns, static for one-time sends or point-in-time analysis
• Refresh frequency (if dynamic): How often the segment membership should be recalculated — real-time (event-triggered), daily, weekly, or on-demand before each campaign send
• Exclusion criteria (optional): Contacts to explicitly exclude — unsubscribed, hard bounced, competitors, internal team members, existing customers (for acquisition campaigns), contacts in another active campaign (frequency capping), or suppression lists from partners
• Minimum segment size (optional): The smallest acceptable segment size for the intended use case — ad platforms typically require 1,000+ for effective delivery, lookalike seeds perform best at 1,000-10,000, and email segments should be large enough for statistical significance in A/B testing
• Cross-platform sync (optional): Whether this segment should be automatically synced to additional platforms — e.g., create in CRM and push to Meta Custom Audiences and Google Ads simultaneously
• Segment description: A human-readable explanation of the segment's purpose and criteria for team documentation — stored alongside the segment for future reference and knowledge transfer
• RFM parameters (optional): If using recency-frequency-monetary segmentation — define the scoring thresholds for each dimension, the lookback window for transaction history, and the number of segments to create (e.g., Champions, Loyal, At Risk, Lost)
• Lookalike expansion (optional): If this segment will seed a lookalike audience — specify the expansion percentage (1-10%) and target platform, so the segment can be optimized for seed quality rather than just size

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. Determine available data sources: Query connected platforms to identify what data is available for segmentation — CRM contact fields and custom properties, email engagement metrics (opens, clicks, bounces), ad platform audience data, website behavioral data (if analytics MCP connected), and purchase/transaction records. Map which criteria can be evaluated from which source and flag any criteria that cannot be supported by available data.