report-generator

name	report-generator
slug	aaron-report-generator
displayName	Report Generator · 报告生成
summary	面向干系人的营销活动报告:叙事结构、图表建议与洞察提炼
description	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
version	20.1.0
license	Apache-2.0
compatibility	Claude Code and compatible agent-skill hosts
homepage	https://github.com/aaron-he-zhu/aaron-marketing-skills
when_to_use	Activate after a campaign or reporting period ends and the user needs a written report for a specific stakeholder. Triggers include post-campaign wrap-ups, executive or board summaries, client-facing results decks, internal team retrospectives, and monthly or quarterly performance reports. Pick this when the inputs are already-computed metrics that need structure, narrative, and recommendations for a named audience.
argument-hint	<campaign name> [audience: executive|client|team|board]
metadata	{"author":"aaron-he-zhu","version":"20.1.0","discipline":"influencer","phase":"report","geo-relevance":"low","hermes":{"tags":["marketing","influencer","report"],"category":"influencer"},"openclaw":{"emoji":"📣","homepage":"https://github.com/aaron-he-zhu/aaron-marketing-skills"}}

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/.

Quick Start

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

Skill Contract

• Reads: campaign name, reporting period, target audience, opaque client_ref, preparer_ref, contact_ref, and owner_ref values when those roles appear, plus already-computed metrics with their provenance, window, target/comparator, and source artifact refs. ROI/ROAS/net-return values must come from roi-calculator, and performance deltas/rankings from performance-analyzer; raw spend plus revenue is not a computed ROI handoff. Reuse opaque creator_ref values from those artifacts, the optional tracker/stage, and an existing Campaign Retro Card. Raw client/staff/owner names, email addresses, and organization labels are transient resolver inputs only.
• Writes: return the finished audience-appropriate report inline by default. Preserve only a current scope-bound Campaign Retro Card from performance-analyzer; if it is absent or invalid, include an unknown placeholder rather than deriving a decision. Save the report/card together to memory/influencer/report-generator/YYYY-MM-DD-<topic>.md only with exact WARM-save authorization. Every saved report, template field, appendix, and handoff uses opaque client_ref, preparer_ref, contact_ref, owner_ref, creator_ref, and artifact/source refs—never resolved client/staff/owner/creator names, organization labels, contact emails, profile URLs, or provider IDs. Resolve those refs only in-memory for one explicitly named audience's transient render, discard the resolution afterward, and never save the mapping. Any external send/share/export requires a new exact authorization naming the report artifact/version, recipient audience, delivery channel, and identity/asset refs allowed for that audience; report creation or WARM save does not authorize distribution.