/digital-marketing-pro:exec-summary

/digital-marketing-pro:exec-summary

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 concise, C-suite-ready executive summary of marketing performance. Focuses on business-level metrics — ROI, CAC, LTV, market share — rather than operational detail. Synthesizes strategic wins and risks, competitive positioning, and high-level recommendations into a format designed for executive decision-making. Supports single-brand summaries or portfolio-wide aggregation across all managed brands, and adapts depth and terminology to the target audience (CEO, CMO, board).

Designed to be the single artifact an executive needs to understand marketing's business impact, make resource allocation decisions, and assess strategic direction — without requiring follow-up questions or supplementary reports.

Input Required

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

• Scope: Whether to summarize a single brand (uses active brand) or the entire portfolio (aggregates across all brands in ~/.claude-marketing/brands/). Portfolio mode requires at least two configured brands
• Time period: The reporting window — this month, this quarter, this year, last 30 days, last 90 days, or a custom date range. Determines which data is pulled and which comparison baselines are used
• Focus areas (optional): Specific topics to emphasize — e.g., "paid media ROI", "customer acquisition", "content performance", "email revenue", "brand awareness". If omitted, the summary covers all active channels proportionally
• Audience: Who will read this — CEO (business outcomes, market position, growth trajectory), CMO (channel performance, team efficiency, strategic initiatives), CFO (ROI, CAC payback, budget utilization), VP Marketing (tactical wins, pipeline impact), or board (high-level portfolio health, competitive position, strategic direction)
• Delivery format (optional): How the summary should be delivered — markdown (default), Slack message, email draft, Google Sheets, or Google Slides. Multiple formats can be requested simultaneously
• Competitive context (optional): Whether to include competitive positioning analysis — requires prior competitor data from /digital-marketing-pro:competitor-analysis or connected competitive intelligence MCPs
• Comparison baseline (optional): What to compare against — prior period (MoM, QoQ), same period last year (YoY), plan/target, or industry benchmark. Defaults to prior period and YoY if data is available
• Prior executive summary (optional): Reference to a previous exec summary to enable period-over-period narrative continuity — tracks whether prior risks were mitigated, prior recommendations were acted on, and whether the trajectory improved

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. Gather performance data: For single brand — pull metrics from all connected MCPs (Google Analytics, Google Ads, Meta Ads, HubSpot, Salesforce, etc.), load campaign history from execution logs, load prior performance snapshots for trend comparison. For portfolio — iterate all brands in ~/.claude-marketing/brands/, aggregate metrics per brand, then roll up to portfolio totals with currency normalization if brands operate in different regions.
3. Calculate executive KPIs: Compute the five core executive metrics — Total Marketing ROI (revenue attributed to marketing / total marketing spend), Customer Acquisition Cost (total spend / new customers acquired), Customer Lifetime Value (average revenue per customer x average retention period), estimated market share trend (if competitive data available), and Brand Health Score (composite of awareness, sentiment, engagement, and loyalty indicators). Use the scripts for standardized computation (all have required args):

   python "${CLAUDE_PLUGIN_ROOT}/scripts/clv-calculator.py" --model simple --avg-purchase-value {value} --purchase-frequency {per-year} --customer-lifespan {years} --margin 30
   python "${CLAUDE_PLUGIN_ROOT}/scripts/roi-calculator.py" --channels '[{"name":"google_ads","spend":10000,"revenue":42000}]' --attribution last_touch --period "{YYYY-MM}"
   

4. Analyze trends and comparisons: Compare each KPI against the prior period (MoM or QoQ depending on time range), the same period last year (YoY), and targets or plan if set. Calculate percentage change and flag significant movements — improvement above 10% as a win, decline above 10% as a risk. Project end-of-period trajectory from the current run rate: python "${CLAUDE_PLUGIN_ROOT}/scripts/revenue-forecaster.py" --historical '[{"period":"2026-05","revenue":120000}]' --forecast-months 3 --growth-assumption 0.05 (SYNTHETIC EXAMPLE — fabricated for illustration; never reuse these numbers).
5. Review prior summary continuity: If a prior executive summary was referenced, compare current period against prior recommendations — which were acted on, which were deferred, and how the trajectory changed. Track whether previously flagged risks materialized or were mitigated, and whether prior wins were sustained or regressed.
6. Identify top 3 wins: Select the three most impactful positive outcomes in the period — largest ROI improvement, most efficient channel, best-performing campaign, fastest-growing segment, or strongest competitive gain. Each win must include specific data (numbers, percentages, dollar values), business impact framing, and a recommendation to scale or sustain the momentum.
7. Identify top 3 risks: Select the three most critical risk signals — declining channel performance, rising CAC, budget overrun, competitive threat, compliance exposure, or market shift. Each risk must include severity assessment (watch, concern, critical), supporting data, projected business impact if unaddressed, and a specific mitigation action with recommended owner and timeline.
8. Generate strategic recommendations: Based on wins, risks, and trend data, produce 3-5 prioritized strategic recommendations. Each recommendation includes the action, expected impact (quantified where possible), required investment or effort, timeline, and the data supporting the recommendation. Tailor language and framing to the target audience — financial language for CFO, growth language for CEO, operational language for CMO.
9. Assess competitive positioning: If competitive data is available, summarize relative market position — share of voice, share of search, ad impression share, content authority, and social engagement benchmarks versus key competitors. Identify competitive gaps and opportunities. If no competitive data exists, note this as a gap and recommend running /digital-marketing-pro:competitor-analysis.
10. Calculate budget utilization: Analyze total spend vs. plan, channel-level pacing (over/under), burn rate trajectory, and projected end-of-period spend. Flag channels pacing more than 15% above or below plan. Generate reallocation recommendations for underperforming or overspending channels: python "${CLAUDE_PLUGIN_ROOT}/scripts/budget-optimizer.py" --channels '[{"name":"google_ads","spend":10000,"roas":4.2}]' --total-budget {amount} (--total-budget is required).
11. Generate portfolio breakdown (portfolio mode): For multi-brand portfolios, create per-brand summary cards showing each brand's top KPIs, largest win, biggest risk, and relative contribution to portfolio totals. Rank brands by ROI and flag any brands significantly underperforming the portfolio average. Calculate portfolio-level diversification health — how dependent overall performance is on any single brand.