performance-check

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

/digital-marketing-pro:performance-check

Purpose

用途

Pull live metrics from all connected analytics MCPs and produce a comprehensive performance snapshot. Compares current performance to KPI targets defined in the brand profile, previous-period benchmarks, and industry averages. Designed for quick health checks — run it daily, weekly, or on-demand to stay on top of marketing performance without switching between platforms.

从所有已连接的分析MCP中提取实时指标，生成全面的绩效快照。将当前绩效与品牌档案中定义的KPI目标、往期基准数据以及行业平均值进行对比。本工具用于快速健康检查——可每日、每周按需运行，无需在各平台间切换即可掌握营销绩效状况。

Input Required

所需输入

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

Time period: Today, this week, this month, this quarter, or a custom date range (e.g., "last 14 days", "Jan 1 - Jan 31")
Channel focus (optional): Specific channels or platforms to prioritize (e.g., "paid search only", "email and social"). If omitted, all connected platforms are included
Comparison period (optional): Period to compare against — previous period, same period last year, or custom range. Defaults to the equivalent previous period
KPI targets (optional): Override targets for this check. If omitted, targets are pulled from profile.json goals and KPI settings
Granularity (optional): Daily, weekly, or aggregate view. Defaults to aggregate for the selected period

用户必须提供（或会被提示输入）：

时间周期：今日、本周、本月、本季度，或自定义日期范围（例如“过去14天”、“1月1日-1月31日”）
渠道重点（可选）：需优先关注的特定渠道或平台（例如“仅付费搜索”、“邮件与社交媒体”）。若未指定，则包含所有已连接平台
对比周期（可选）：用于对比的周期——往期、去年同期或自定义范围。默认使用对应往期周期
KPI目标（可选）：本次检查的自定义目标值。若未指定，则从profile.json的目标与KPI设置中提取
粒度（可选）：按日、按周或聚合视图。默认使用所选周期的聚合视图

Process

流程

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.
Detect connected analytics MCPs: Check
```
.mcp.json
```
and active MCP connections to identify which platforms are available (google-analytics, google-ads, meta-marketing, linkedin-marketing, tiktok-ads, mailchimp, stripe, mixpanel, amplitude, shopify, etc.). Log any expected platforms that are not connected so the user knows about gaps in coverage.
Pull metrics from each connected platform: Request key metrics for the specified time period:
- Traffic: sessions, users, pageviews, new vs returning
- Ads: impressions, clicks, spend, CPC, CPM
- Conversions: leads, purchases, sign-ups, goal completions
- Revenue: total revenue, average order value, transaction count
- Engagement: open rate, click rate, bounce rate, time on site
- Platform-specific: email deliverability, social reach, video views, app installs
Aggregate into unified dashboard: Normalize metrics across platforms into a single cross-channel view with consistent naming, currency conversion if multi-currency, and de-duplicated conversion counts where platforms overlap
Calculate KPIs vs targets: Compare actuals to targets from
```
profile.json
```
goals — flag green (on track or exceeding), yellow (within 10% of target), or red (missing by >10%). Include absolute and percentage variance for each KPI.
Compare to previous period: Calculate period-over-period change for every metric and attach trend direction (up/down/flat) with percentage change. If year-over-year data is available, include as a secondary reference point.
Benchmark against industry: Reference
```
skills/context-engine/industry-profiles.md
```
for the brand's industry to contextualize performance relative to category averages. Flag metrics significantly above or below industry norms.
Identify notable findings: Surface the top 3 wins (best-performing metrics or biggest improvements), top 3 concerns (underperforming or declining metrics), and any statistically significant changes that warrant deeper investigation.
Generate recommended actions: Based on the data, produce 3-5 specific, actionable next steps — e.g., "Pause underperforming ad set X", "Increase budget on high-ROAS channel Y", "Investigate traffic drop on Z", "Scale winning creative variant", "Run /digital-marketing-pro:anomaly-scan for deeper diagnosis".
Save performance snapshot: Execute
```
scripts/performance-monitor.py --brand {slug} --action save-snapshot
```
to persist the snapshot for historical comparison and trend tracking across future runs.
Log significant insights: For any metric with a notable deviation, save via
```
scripts/campaign-tracker.py --brand {slug} --action add-insight
```
so findings surface in future reports and campaign planning.

加载品牌上下文：读取
```
~/.claude-marketing/brands/_active-brand.json
```
获取活跃品牌标识（slug），然后加载
```
~/.claude-marketing/brands/{slug}/profile.json
```
。应用品牌话术、目标市场合规规则（
```
skills/context-engine/compliance-rules.md
```
）以及行业上下文。同时检查
```
~/.claude-marketing/brands/{slug}/guidelines/_manifest.json
```
中的指南——若存在则加载限制条件。检查
```
~/.claude-marketing/sops/
```
下的代理机构标准操作流程（SOPs）。若未设置品牌，则询问：“是否先设置品牌（/digital-marketing-pro:brand-setup）？”——或使用默认值继续。
检测已连接的分析MCP：检查
```
.mcp.json
```
和活跃MCP连接，识别可用平台（google-analytics、google-ads、meta-marketing、linkedin-marketing、tiktok-ads、mailchimp、stripe、mixpanel、amplitude、shopify等）。记录所有预期但未连接的平台，以便用户了解覆盖缺口。
从各已连接平台提取指标：请求指定时间周期的关键指标：
- 流量：会话数、用户数、页面浏览量、新用户vs回访用户
- 广告：展示量、点击量、花费、CPC、CPM
- 转化：潜在客户数、购买量、注册量、目标完成数
- 营收：总营收、平均订单价值、交易次数
- 互动：打开率、点击率、跳出率、网站停留时间
- 平台特定指标：邮件送达率、社交媒体触达量、视频播放量、应用安装量
聚合为统一仪表盘：将各平台指标标准化为单一跨渠道视图，统一命名规则，若涉及多币种则进行货币转换，并对平台重叠处的转化数据进行去重统计
计算KPI与目标对比：将实际值与profile.json目标中的设定值对比——标记为绿色（达标或超额）、黄色（与目标差距在10%以内）或红色（未达标幅度超过10%）。包含每个KPI的绝对差值和百分比差值。
与往期对比：计算每个指标的环比变化，并附上趋势方向（上升/下降/持平）及百分比变化。若有同比数据，将其作为次要参考点。
对标行业基准：参考
```
skills/context-engine/industry-profiles.md
```
中品牌所属行业的信息，将绩效置于行业平均水平的语境下分析。标记显著高于或低于行业标准的指标。
识别关键发现：突出显示Top 3亮点（表现最佳或提升最大的指标）、Top 3问题（表现不佳或下滑的指标），以及任何值得深入调查的统计显著变化。
生成建议行动：基于数据产出3-5项具体、可执行的下一步措施——例如“暂停表现不佳的广告组X”、“增加高ROAS渠道Y的预算”、“调查渠道Z的流量下降问题”、“扩大表现优异的创意变体规模”、“运行/digital-marketing-pro:anomaly-scan进行深度诊断”。
保存绩效快照：执行
```
scripts/performance-monitor.py --brand {slug} --action save-snapshot
```
以保存快照，用于历史对比及未来运行时的趋势跟踪。
记录重要洞察：对于任何出现显著偏差的指标，通过
```
scripts/campaign-tracker.py --brand {slug} --action add-insight
```
保存，以便在未来报告和活动规划中呈现这些发现。

Output

输出内容

A structured performance snapshot containing:

Executive summary: 2-3 sentence overview of overall marketing health with the single most important finding highlighted
Channel-by-channel metrics table: Traffic, impressions, clicks, conversions, revenue, spend, CPA, ROAS, and engagement rate per platform — sortable by any column
KPI scoreboard: Each tracked KPI with actual value, target value, percentage to target, variance (absolute and %), trend arrow (vs previous period), and RAG status (red/amber/green)
Cross-channel summary: Total spend, total conversions, blended CPA, blended ROAS, total revenue, marketing efficiency ratio, and overall health assessment
Period-over-period comparison: Percentage change for all key metrics vs the comparison period with directional indicators and sparkline-style trend data
Industry benchmark context: How key metrics compare to industry averages from industry-profiles.md, with percentile ranking where data is available
Notable findings: Top 3 wins, top 3 concerns, and any anomalies worth investigating further — each with supporting data points and severity indicator
Recommended actions: 3-5 specific next steps with priority ranking, expected impact, and the platform or campaign each action applies to
Data gaps: Any platforms that were expected but not connected, metrics that could not be retrieved, or time periods with incomplete data — so the user knows what is missing from the picture

结构化的绩效快照包含：

执行摘要：2-3句话概述整体营销健康状况，突出最重要的发现
分渠道指标表：各平台的流量、展示量、点击量、转化量、营收、花费、CPA、ROAS及互动率——可按任意列排序
KPI计分板：每个跟踪的KPI包含实际值、目标值、完成率、差值（绝对和百分比）、环比趋势箭头以及RAG状态（红/黄/绿）
跨渠道汇总：总花费、总转化量、混合CPA、混合ROAS、总营收、营销效率比及整体健康评估
环比对比：所有关键指标与对比周期的百分比变化，附带方向指示和迷你折线图式的趋势数据
行业基准语境：关键指标与industry-profiles.md中行业平均值的对比，若有数据则提供百分位排名
关键发现：Top 3亮点、Top 3问题以及任何值得进一步调查的异常——每项均附带支持数据点和严重程度指标
建议行动：3-5项具体下一步措施，包含优先级排序、预期影响及适用平台或活动
数据缺口：所有预期但未连接的平台、无法获取的指标或数据不完整的时间周期——让用户了解快照的信息缺失情况

Agents Used

使用的Agent

analytics-analyst — Metrics interpretation, KPI analysis, cross-channel normalization, trend identification, industry benchmarking, insight generation, and action recommendation
performance-monitor-agent — Data aggregation from connected MCPs, baseline comparison, snapshot persistence, historical trend analysis, and gap detection

analytics-analyst — 指标解读、KPI分析、跨渠道标准化、趋势识别、行业基准对标、洞察生成及行动建议
performance-monitor-agent — 从已连接MCP聚合数据、基线对比、快照持久化、历史趋势分析及缺口检测