aaron-he-zhu/report-generator
Use when the user asks to "create a campaign report", "build an executive summary", or "deliver client results"; produces audience-tailored influencer marketing reports (executive, client, internal team) with data tables, narrative, key learnings, and recommendations. Not for raw metric computation — use performance-analyzer. 达人营销报告/结案汇报
npx skills add https://github.com/aaron-he-zhu/aaron-marketing-skills --skill report-generator
This skill helps you create professional influencer marketing reports that tell the story of your campaign performance. It adapts content and depth based on the audience.
> Cross-discipline (paid ads): this is also the paid-ads reporting surface — build exec/client/channel reports from RQS history (memory/audits/ad/) and measurement-loop readback verdicts. It presents metrics; it does not compute them (return math stays in roi-calculator). Save paid runs under memory/ad/report-generator/.
Shortest invocation:
Create a campaign report for [campaign name] for [audience: executive/client/team]
Common scenario:
Generate an executive summary for our Q3 influencer campaigns
performance-analyzer and roi-calculator if available.memory/influencer/report-generator/YYYY-MM-DD-<topic>.md.memory/hot-cache.md.> Emit the standard shape from skill-contract.md §Handoff Summary Format.
This family ships Tier 1: every step works with no live integration. Give the skill the campaign metrics directly and it builds the report from your inputs.
Optional connectors that can pre-fill data where available:
~~social platform analytics — reach, impressions, engagement, video views per post~~influencer database — creator handles, tiers, fees, audience demographics~~analytics — link clicks, conversions, attributed revenue~~CRM — new-customer counts and downstream revenueWithout any of these, the skill asks you for the numbers and proceeds. See CONNECTORS.md for the free/keyless data recipe per category.
When a user requests a report:
performance-analyzer and roi-calculator outputs when present; otherwise ask the user for the numbers. Pair every metric with context (target, benchmark, or prior period).memory/influencer/report-generator/YYYY-MM-DD-<topic>.md (paid runs to memory/ad/report-generator/). Promote durable verdicts (final ROI/ROAS, top performers, renew/drop calls, headline learnings) to memory/hot-cache.md.User: "Create an executive report for our holiday campaign: $50K spend, $165K revenue, 3.5M reach across 15 influencers"
Output (excerpt — full template in report-templates.md):
# Holiday Campaign 2024: Executive Summary
## Bottom Line: Campaign Exceeded All Targets ✅
**ROI: 230%** | **ROAS: 3.3:1** | **Revenue: $165,000**
| Metric | Target | Actual | Status |
|--------|--------|--------|--------|
| Revenue | $100K | $165K | ✅ +65% |
| ROAS | 2:1 | 3.3:1 | ✅ +65% |
| Reach | 2M | 3.5M | ✅ +75% |
### Recommendation
Increase Q1 influencer budget by 25%, focused on TikTok micro-influencers and product-demo content.
Primary: content-quality-auditor — run the finished report through the publish-readiness gate before it goes to a stakeholder.
Alternates (same report phase / influencer family):
Termination note (visited-set): if a recommended skill has already been invoked this session, stop and report the chain as complete instead of re-running it. Honor a max chain depth of 3 hops to avoid loops.
Take aaron-he-zhu/report-generator from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.