aaron-marketing-skills is a collection of 120 AI-agent skills covering marketing work such as brand narrative, search optimization, social media, email, advertising, influencer campaigns, and launches. Marketers and agent users can install it as a plugin, use its portable skills, or run its described bot team. The catalogue entries are components of this marketing workflow.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/aaron-he-zhu/aaron-marketing-skillsnpx agentmods add skills/aaron-he-zhu/aaron-marketing-skills/report-generatorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/aaron-he-zhu/aaron-marketing-skills/report-generator)<a href="https://agentmods.dev/skills/aaron-he-zhu/aaron-marketing-skills/report-generator"><img src="https://agentmods.dev/badge/skills/aaron-he-zhu/aaron-marketing-skills/report-generator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/aaron-he-zhu/aaron-marketing-skills/report-generator"><img src="https://agentmods.dev/badge/skills/aaron-he-zhu/aaron-marketing-skills/report-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00076 | $0.03160 |
| Opus 5 | $0.00038 | $0.01580 |
| Sonnet 5 | $0.00015 | $0.00632 |
| Haiku 4.5 | $0.00008 | $0.00316 |
Grade A, and why
report-generator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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 undermemory/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, andowner_refvalues 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 opaquecreator_refvalues 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 anunknownplaceholder rather than deriving a decision. Save the report/card together tomemory/influencer/report-generator/YYYY-MM-DD-<topic>.mdonly with exact WARM-save authorization. Every saved report, template field, appendix, and handoff uses opaqueclient_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. - Promotes: only with separate exact authorization, promote durable evidence-backed facts (verified final ROI/ROAS, measured performance baselines, and headline learnings) to
memory/hot-cache.md. The Retro Card's qualitativerenew | retest | retire | unknowndecision, rationale, next hypothesis, and limitations remain WARM and are not creator-registry facts. This skill makes no creator-registry proposal: after a creator row is closed, only a separately authorized, evidence-backed actual rate, signed rights window/expiry, or measured performance baseline may be proposed by the owning workflow; creator-registry alone decides whether it becomes canonical. - Done when:
- The report matches the requested audience template (executive, client, team, or board).
- Every metric is paired with compatible source-dated context (target, benchmark, or prior period) or explicitly marked
Unknown/NEEDS_INPUT; the report does not manufacture context or recompute missing performance/return metrics. - The report ends with concrete recommendations and, where relevant, action items.
- When current tracker-state evidence proves
measuredorclosed, the report package preserves the matching performance-analyzer Retro Card with exact campaign/creator/state/measurement/decision-rule refs; a missing or invalid card produces anunknownplaceholder andNEEDS_INPUT, never a newly derived decision. - Saved/copyable output contains only opaque client/preparer/contact/owner/creator refs; any resolved labels/contact details exist only in a transient render for the declared audience, and external distribution is blocked without a fresh audience-scoped exact authorization.
- Primary next skill: content-quality-auditor
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago Changed · +8 lines 1c33850438c2
- 12d ago First seen · 124 lines · 76 tokens per session scan A 906d7fc95949
report-generator is a skill published in the GitHub repository aaron-he-zhu/aaron-marketing-skills (2,767 stars, last pushed today), licensed Apache-2.0. It adds 76 tokens to every session and 3,160 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
geo-visibility-check
One-shot GEO audit: does your brand appear in Claude, ChatGPT, and Gemini answers for the buyer questions that matter? Runs a prompt panel through the engines with citation tracing and reports per-prompt verdicts, who wins instead, and which sources the answers come from.
geo-optimizer-skill
Run geo audit first. It scores the site 0–100 across 8 categories and generates a prioritized action list.
geo-loop
Run one bounded eGEOagents loop iteration over a workspace domain - read the charter and fresh collector data, do ONE unit of work, write substrate artifacts, append one Timeline entry and one LOG line. Use for loop mode, /geo:loop, scheduled GEO runs, or continuous monitoring.
content-scoring
Score content against the 10 GEO criteria with evidence and prioritized fixes. Use when users ask to score, rate, evaluate, or estimate ranking strength.
competitive-analysis
Analyze AI-search competitors for a query and recommend ranking strategy. Use when users ask competitor analysis, who ranks, or competitive landscape.
schema-generator
Generate JSON-LD schema markup for pages and content types with an implementation checklist. Use when users ask for schema, structured data, rich snippets, or markup.