/digital-marketing-pro:send-report

/digital-marketing-pro:send-report

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

Generate a formatted performance report from connected analytics sources and deliver it via Slack, email, or Google Sheets. Supports weekly pulse, monthly review, QBR, and custom report types. Pulls live metrics from connected platforms, calculates KPIs against targets and previous periods, adds trend analysis with anomaly detection, generates actionable recommendations, then formats and delivers through the user's preferred channel with appropriate approval gates.

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

• Report type: The report format — weekly-pulse (top-line metrics and highlights, 1 page), monthly-review (full channel breakdown with trends, 3-5 pages), qbr (quarterly business review with strategic analysis and recommendations, 8-12 pages), or custom (user-defined metric selection and structure)
• Delivery channel: Where to send the report — Slack (channel post or DM with formatted blocks), email (HTML report via SendGrid or connected email MCP), or Google Sheets (new spreadsheet or append to existing tracking sheet)
• Date range: Reporting period — last 7 days, last 30 days, last quarter, custom start and end dates, or "since last report" to auto-detect the last delivery timestamp from execution logs
• Recipients: Optional — Slack channel name or user handles, email addresses for distribution list, or Google Sheets sharing permissions and notification settings for the target audience
• Custom metrics: Optional — specific metrics to include or exclude beyond the report type defaults, custom KPI definitions, calculated fields (e.g., blended CAC, marketing-influenced pipeline), or specific campaign IDs to isolate
• Comparison period: Optional — compare against previous period (WoW, MoM, QoQ, YoY), a specific custom date range, or targets and forecasts defined in brand profile
• Report branding: Optional — include brand logo, custom color scheme, header and footer text, or white-label formatting for client-facing or agency delivery
• Narrative depth: Optional — executive summary only (3-5 sentences), standard (summary plus channel commentary), or deep dive (full analysis with hypotheses and test recommendations)
• Campaign filter: Optional — isolate performance data for specific campaigns, channels, or audience segments rather than reporting on all activity
• Benchmarks: Optional — include industry benchmarks for context, competitive intelligence from previous analyses, or custom benchmarks defined by the brand
• Annotations: Optional — key events to overlay on the report (campaign launches, promotions, seasonal events, budget changes) that provide context for metric movements
• Distribution schedule: Optional — set this report to recur automatically at the specified cadence (weekly, monthly, quarterly) with the same configuration
• Executive audience: Optional — name the specific stakeholders who will read the report, so narrative tone and metric abstraction level can be adjusted accordingly

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. Pull metrics from connected analytics: Run performance-monitor.py to gather data from connected analytics MCP servers — Google Analytics (traffic, conversions), Google Ads (spend, CPC, ROAS), Meta Ads (spend, reach, frequency), LinkedIn Ads (spend, leads), email platforms (opens, clicks, deliverability), and any other configured sources. Aggregate metrics for the specified date range and comparison period.
3. Calculate KPIs against targets: Compare actual performance against targets defined in profile.json and against the comparison period. Calculate period-over-period deltas, percentage changes, trend direction, and statistical significance for key movements. Flag metrics that are more than 10% above or below target with severity indicators (warning, critical).
4. Identify trends and anomalies: Analyze metric trajectories across the reporting window — identify sustained upward or downward trends (3+ consecutive periods), sudden spikes or drops (single-period movements exceeding 2 standard deviations), seasonal patterns, and correlations between channels that suggest attribution shifts or budget reallocation opportunities.