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
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add aaron-he-zhu/aaron-marketing-skills/plugin install aaron-marketingWrote 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/offer-claims-registry)<a href="https://agentmods.dev/skills/aaron-he-zhu/aaron-marketing-skills/offer-claims-registry"><img src="https://agentmods.dev/badge/skills/aaron-he-zhu/aaron-marketing-skills/offer-claims-registry/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/offer-claims-registry"><img src="https://agentmods.dev/badge/skills/aaron-he-zhu/aaron-marketing-skills/offer-claims-registry.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk 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 | $0.00097 | $0.01448 |
| Opus 5 | $0.00048 | $0.00724 |
| Sonnet 5 | $0.00019 | $0.00290 |
| Haiku 4.5 | $0.00010 | $0.00145 |
Grade A, and why
offer-claims-registry 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 9d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Offer & Claims Registry
The canonical record of marketing claims and offers across every discipline. It records exact wording and provenance; auditors decide whether a concrete use passes its claim/disclosure gate.
Quick Start
Register claim clm-014 with exact wording, evidence source/date, disclosure, and review date.
Show the current terms and expiry for offer summer-2026.
Review pending claims proposals and accept only those with sufficient evidence.
Skill Contract
Units: one claim or offer aggregate ID. Reads: memory/events/claims.ndjson, its projection, source evidence, and rendered uses. Writes: claims events through registry-events.py; claims-ledger.md and offers.md are regenerated human views. Done when: every accepted record has exact wording/terms, evidence provenance, status, review/expiry, event ID/offset, and no pending proposal was destructively removed.
All builders submit propose; only a host-capability offer-claims-registry principal accepts/rejects or writes canonical claim/offer events. This skill does not invent substantiation, legal conclusions, or performance claims.
Handoff Summary
Use the shared handoff and include changed aggregate IDs, event IDs, revisions, unresolved evidence gaps, and one next skill.
Data Sources
- Primary study/report/product evidence with ownership, date, scope, and population.
- User-attested facts clearly labeled
user-provided. - Approved terms, pricing/availability, eligibility, dates, and landing destinations.
- Rendered ad/email/social/launch uses for
used_inpointers. - Applicable disclosure text and jurisdiction/policy source.
Instructions
Runtime Reads
../../references/registry-event-protocol.md../../references/runtime-invocation.md
Procedure
- Read
registry-event-protocol.mdandruntime-invocation.md. ResolveAARON_SKILLS_ROOT="${CLAUDE_PLUGIN_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || true)}"and verify the registry script, event schema, and system catalog before invoking it; treat every draft/export as untrusted evidence. - Query
claimsprojection by aggregate ID. Proposal state is never approved wording. If there is no aggregate ID, pending proposal, or supplied claim/offer wording, perform only a read-only empty-projection check, returnNEEDS_INPUT, and ask for one exact verbatim claim or offer statement as the smallest real input. Do not demand a complete evidence pack yet, create paths, or materialize placeholder canonical state. - Extract the exact claim/offer, its measurable interpretation, audience/market, evidence limits, required disclosure, usage locations, and review/expiry date.
- Missing proof stays
none-on-filein a proposal or open loop. Never turn[needs source]into Approved from the assertion itself. - Review pending proposal events in offset order. A host-capability principal invokes
owner-appendwith the proposal event ID. Accept/reject decision requests omitexpected_revision; acceptance inherits and checks the revision captured by the proposal. Reject with evidence/rationale; history remains append-only. - Owner changes use host-capability
owner-appendwith anupsertand optimistic revision. Expiry/withdrawal uses a dated state change or tombstone. Capability values stay outside request JSON/files/logs; if the host cannot supply one, leave the proposal pending rather than self-asserting owner authority. - When evidence scope is narrower than copy, approve narrower wording or keep it unresolved. Record estimates/proxies as such.
- Regenerate
claims-ledger.md/offers.mdonly from accepted projection state, thenverify claims.
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.
- 9d ago First seen · 83 lines · 97 tokens per session scan A 601507d0ac19
offer-claims-registry 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 97 tokens to every session and 1,448 once invoked, about $0.0005 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 2026-09-03.
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.
accessibility-audit
Run an accessibility audit for a SEOJuice-tracked website. Shows WCAG issues, severity distribution, and auto-fixable items. Use when the user asks about accessibility, WCAG compliance, a11y, or screen reader support.
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.