Skill 详情
executive-dashboard
Direct design guidance but restricted to executive marketing dashboards.
使用前先检查
自动化审核只检查相关性,不代表安全审查或推荐。使用前请阅读来源中的说明。
SKILL.md
这段内容是审核时保存的快照。外部来源才是完整且最新的版本。
---
name: executive-dashboard
description: "Design executive marketing dashboards. Use when: building CMO reports, board metrics, or leadership views."
---
# /digital-marketing-pro:executive-dashboard
## Purpose
Design a C-suite marketing dashboard that translates marketing metrics into business outcomes for executive decision-making. Bridges the gap between marketing activity data and business impact, giving senior leaders the clarity to make faster, better-informed strategic decisions without drowning in operational detail.
## Input Required
The user must provide (or will be prompted for):
- **Executive role**: Primary audience — CEO, CMO, CFO, VP Marketing, or board — each requires different metric emphasis and abstraction level
- **Business model and revenue drivers**: How the company makes money — SaaS, e-commerce, lead gen, marketplace, subscription — and the key revenue levers marketing influences
- **Strategic priorities this quarter**: The 2-4 business priorities the executive team is focused on that marketing should ladder up to
- **Reporting frequency**: How often the dashboard will be reviewed — weekly executive standup, monthly leadership meeting, quarterly board review
- **Current data sources and tools**: Analytics platforms, CRM, ad platforms, attribution tools, and BI systems currently in use with data freshness and reliability notes
- **Existing reports being replaced**: Current reporting artifacts the dashboard will consolidate or replace — helps identify gaps and redundancies
- **Key decisions the dashboard should inform**: Specific decisions executives make that this dashboard should support — budget allocation, channel mix, hiring, campaign scaling, market expansion
- **Stakeholder data literacy level**: How comfortable the audience is with marketing metrics — determines labeling, context, and narrative density needed
## 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 custom templates at `~/.claude-marketing/brands/{slug}/templates/`. 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. **Identify north-star metrics**: Select 5-7 metrics that directly tie marketing activity to business outcomes — revenue influenced, pipeline generated, customer acquisition cost, lifetime value, market share, brand equity indicators
3. **Design metric hierarchy**: Organize metrics into three tiers — leading indicators (predict future performance), lagging indicators (confirm past results), and health metrics (signal system stability and sustainability)
4. **Select visualization type per metric**: Choose the optimal chart type for each metric based on data shape and decision context — trend lines for trajectory, gauges for targets, bar charts for comparisons, sparklines for density
5. **Define alert thresholds and anomaly triggers**: Set green/yellow/red thresholds for each metric with specific trigger values, and configure anomaly detection rules for unexpected spikes or drops
6. **Map data sources to each metric**: Document which system provides each metric, how it is calculated, data freshness (real-time, daily, weekly), and known limitations or lag
7. **Design layout for scanning speed**: Structure the dashboard for F-pattern or Z-pattern scanning — most critical metrics top-left, summary before detail, consistent visual hierarchy, minimal cognitive load
8. **Add narrative guidance**: Write "how to read this" instructions for each section — what good looks like, what bad looks like, and what a在 GitHub 阅读完整来源 (打开外部页面)