client-report

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: client-report
description: "Generate client-facing reports. Use when: white-labeled performance report with KPIs, trends, strategic recommendations."
---

# /digital-marketing-pro:client-report

## Purpose

Generate a professional, white-labeled client report for a specific brand. Uses agency voice (not brand voice), includes KPI performance, channel breakdowns, strategic recommendations, and next steps. Designed for external client delivery via Slack, email, Google Sheets, or markdown — with approval gating before any external send to prevent accidental disclosure or premature delivery of draft findings.

## Input Required

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

- **Brand slug**: The brand this report covers — must match a configured brand in `~/.claude-marketing/brands/`
- **Report type**: One of:
  - Weekly pulse: Quick KPI snapshot with 3-5 key metrics and brief commentary
  - Monthly review: Full performance analysis with channel breakdowns and recommendations
  - QBR: Quarterly deep-dive with strategic roadmap and forward plan
- **Date range**: Specific start and end dates for the reporting period — defines what data is pulled and analyzed
- **Delivery channel**: Where the report should be sent — slack, email, google-sheets, or markdown-only (no external delivery, just generate the artifact)
- **Custom sections (optional)**: Any additional sections the client has requested — competitive update, creative performance breakdown, audience insights, attribution deep-dive, or ad-hoc investigation topic
- **Comparison period**: What to compare against — prior period, same period last year, plan/target, or all three simultaneously
- **Recipient list (optional)**: Specific client contacts who should receive the report if delivering via email or Slack — names and handles/addresses
- **Narrative emphasis (optional)**: What the client cares most about this period — growth, efficiency, brand awareness, pipeline generation, or revenue — influences which metrics are highlighted first and how insights are framed
- **Include appendix**: Whether to attach raw data tables and campaign-level detail as an appendix — defaults to yes for monthly and QBR, no for weekly pulse
- **White-label settings (optional)**: Agency logo placement, color scheme, and disclaimer text — pulled from agency profile if configured, otherwise uses clean defaults

## 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 all metrics for the brand**: Query connected MCP servers and run `python "${CLAUDE_PLUGIN_ROOT}/scripts/campaign-tracker.py" --brand {slug} --action list-campaigns` (then `--action get-campaign --id {id}` per campaign) to gather performance data across all active channels; filter to the specified date range during analysis
3. **Gather campaign history and execution log**: Run `python "${CLAUDE_PLUGIN_ROOT}/scripts/execution-tracker.py" --brand {slug} --action get-history` to compile all deliverables completed, campaigns launched, optimizations made, and tests concluded, then filter to the reporting period during analysis
4. **Calculate KPIs vs targets and vs comparison period**: Compute actuals against the brand's stated KPI targets from `profile.json` and against the selected comparison period — calculate deltas, percentage changes, trend direction, and statistical significance where sample sizes allow
5. **Break down performance by channel**: Segment metrics by channel (paid search, paid social,