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/preference-frequency-managerWrote 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/preference-frequency-manager)<a href="https://agentmods.dev/skills/aaron-he-zhu/aaron-marketing-skills/preference-frequency-manager"><img src="https://agentmods.dev/badge/skills/aaron-he-zhu/aaron-marketing-skills/preference-frequency-manager/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/preference-frequency-manager"><img src="https://agentmods.dev/badge/skills/aaron-he-zhu/aaron-marketing-skills/preference-frequency-manager.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 | $0.00166 | $0.03498 |
| Opus 5 | $0.00083 | $0.01749 |
| Sonnet 5 | $0.00033 | $0.00700 |
| Haiku 4.5 | $0.00017 | $0.00350 |
Grade A, and why
preference-frequency-manager 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.
Preference & Frequency Manager
Designs the subscriber-facing preference center and the frequency/topic opt-down ladder that gives a subject a step-down instead of a hard unsubscribe, and supplies the SEND N (Nurture / Lifecycle) sub-item note on preference-center / frequency options offered. It specifies the preference-page field set (topics, cadence tiers, channel toggles), the down-tier ladder (e.g., weekly → monthly → pause → sunset), and the mapping from each preference choice to the suppression/frequency rule the ESP and consent-registry must enforce. It is the N1-veto mitigation — the softer exit that keeps people on the list at a lower cadence — but it does not adjudicate the N1 unsubscribe veto, own the consent record, design the lifecycle flows, or compute the EQS.
Quick Start
Build a preference center for [product/audience] on [ESP]. Offer topics [list], cadence tiers [weekly/monthly], and a pause option instead of a hard unsubscribe.
Design a frequency opt-down ladder: on the unsubscribe page, offer step-down paths (reduce to monthly, pick topics, pause 90 days) before the full opt-out.
Opt-out rate is rising on [segment]. Design a preference page + down-tier ladder that gives fatigued subjects a lighter cadence before they leave, and map each choice to a suppression/frequency rule.
Skill Contract
Expected output: a preference-center field spec (topic groups, cadence tiers, channel toggles, save/confirm behavior), a frequency/topic opt-down ladder (the down-tier steps offered on the unsubscribe path and their order), a preference-choice → suppression/frequency mapping (what each selection tells the ESP and consent-registry to honor), a SEND N sub-item note on preference-center / frequency options offered, and the standard handoff summary.
- Reads: the topic set and cadence tiers to offer, the target segment (from the user or from list-segment-builder when present), the flow/cadence context (from email-sequence-designer when present, so the ladder's tiers match the program's send frequencies), and a manual
~~email platform(ESP) export of current preference-center fields and opt-out/preference-update signals when available. Consent and suppression facts are read from, and written back to, consent-registry. - Writes: a user-facing preference-center spec + opt-down ladder + choice-to-rule mapping, and a reusable handoff summary to
memory/email/preference-frequency-manager/YYYY-MM-DD-<preference-or-segment>.md. - Promotes: the chosen topic groups, cadence-tier definitions, down-tier ladder order, sunset threshold the ladder terminates into, the N sub-item note, and missing exports to
memory/hot-cache.mdandmemory/open-loops.md; propose durable preference/cadence-tier decisions aspending-decisionitems — never writedecisions.mddirectly. - Done when: the preference center has a defined topic set and at least two cadence tiers plus a pause option; the opt-down ladder specifies its ordered down-tier steps and the sunset it terminates into; every preference choice maps to an explicit suppression or frequency rule the ESP and consent-registry can honor; and the SEND N preference-center / frequency-options sub-item note is emitted (Pass/Partial/Fail rationale, not the full dimension score).
- Primary next skill: email-sequence-designer to wire the ladder's cadence tiers into the lifecycle flows and global governance, or email-quality-auditor to score the program and rule the N1 unsubscribe veto.
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 d34da47c22e2
- 13d ago First seen · 94 lines · 166 tokens per session scan A 43f377714c97
preference-frequency-manager is a skill published in the GitHub repository aaron-he-zhu/aaron-marketing-skills (2,767 stars, last pushed yesterday), licensed Apache-2.0. It adds 166 tokens to every session and 3,498 once invoked, about $0.0008 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.