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/reactivation-specialistWrote 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/reactivation-specialist)<a href="https://agentmods.dev/skills/aaron-he-zhu/aaron-marketing-skills/reactivation-specialist"><img src="https://agentmods.dev/badge/skills/aaron-he-zhu/aaron-marketing-skills/reactivation-specialist/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/reactivation-specialist"><img src="https://agentmods.dev/badge/skills/aaron-he-zhu/aaron-marketing-skills/reactivation-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 68 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00215 | $0.03821 |
| Opus 5 | $0.00108 | $0.01911 |
| Sonnet 5 | $0.00043 | $0.00764 |
| Haiku 4.5 | $0.00021 | $0.00382 |
Grade A, and why
reactivation-specialist 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reactivation Specialist
Designs a closed-loop reactivation program for lapsed email cohorts — the win-back offer ladder, the re-consent (re-permission) capture step, and the sunset-confirm / suppression rule. It defines the lapsed cohort by a no-engagement window, stages an offer ladder that escalates then stops, requires re-engaged subjects to re-affirm opt-in, and specifies the terminal rule that either re-permissions a subject or suppresses them. It does not author the SEND N (Nurture / Lifecycle) sub-item notes: engagement-decay / sunset is owned by email-sequence-designer and preference-center / frequency options by preference-frequency-manager — this program feeds both owners its sunset-confirm and re-consent facts to fold in, and references their notes rather than re-emitting them. It does not design the everyday lifecycle flows, own the consent record, or compute the final EQS.
Quick Start
Build a win-back campaign for subscribers who haven't opened in [N] days on [ESP]. Here is my engagement export: [paste/path]. I can offer [incentive].
My unengaged tail is [X]% of the list and complaints are creeping up. Design a re-permission sweep with an offer ladder and a sunset-confirm rule.
I need to clean the dead weight off my list without a bulk delete. Design a reactivation program that re-consents the recoverable subjects and suppresses the rest.
Skill Contract
Expected output: a lapsed-cohort definition (the no-engagement window + how the cohort is pulled), a staged offer ladder (each step's trigger, timing, message intent, and escalation/stop rule), a re-consent / re-permission capture step (what re-affirms opt-in and how it is recorded), a sunset-confirm / suppression rule (the terminal branch that either re-permissions or suppresses each subject), a handoff of the sunset-confirm and re-consent facts to the SEND N sub-item owners (engagement-decay / sunset → email-sequence-designer; preference-center / frequency options → preference-frequency-manager) rather than an own sub-item score, and the standard handoff summary.
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 3baf8d99fcc4
- 13d ago First seen · 94 lines · 215 tokens per session scan A 19e9758da167
reactivation-specialist 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 215 tokens to every session and 3,821 once invoked, about $0.0011 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.