by aaron-he-zhu
120 marketing skills + 8 commands for Claude Code & AI agents across 7 disciplines — SEO/GEO, influencer, paid ads, email, product launch, organic social & brand narrative — on one shared contract, with 8 auditor gates: CORE-EEAT · CITE · STAR · ROAS · SEND · RAMP · ECHO · TALE.
# Add to your Claude Code skills
git clone https://github.com/aaron-he-zhu/aaron-marketing-skillsGuides for using ai agents skills like aaron-marketing-skills.
Last scanned: 6/29/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-06-29T08:58:04.099Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}aaron-marketing-skills is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by aaron-he-zhu. 120 marketing skills + 8 commands for Claude Code & AI agents across 7 disciplines — SEO/GEO, influencer, paid ads, email, product launch, organic social & brand narrative — on one shared contract, with 8 auditor gates: CORE-EEAT · CITE · STAR · ROAS · SEND · RAMP · ECHO · TALE. It has 2,381 GitHub stars.
Yes. aaron-marketing-skills passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/aaron-he-zhu/aaron-marketing-skills" and add it to your Claude Code skills directory (see the Installation section above).
aaron-marketing-skills is primarily written in Python. It is open-source under aaron-he-zhu on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh aaron-marketing-skills against similar tools.
No comments yet. Be the first to share your thoughts!
120 marketing skills — brand narrative, SEO/GEO, influencer, paid ads, email, launch, social — on one contract.
English | Deutsch | Español | Français | Italiano | 日本語 | 한국어 | Português | 简体中文 | 繁體中文
A library of Claude Skills and slash commands that turns a chat agent into a marketing operator. Seven disciplines and a shared protocol layer, at a glance:
| Layer | Skills | Lifecycle (phase directories) | Framework → gate | Entrypoint |
|---|---|---|---|---|
| Narrative | 16 | trace → architect → land → evaluate | TALE truth / system / effectiveness profiles | /aaron-marketing:narrative |
| SEO/GEO | 16 | survey → implement → tune → evaluate | CORE-EEAT → content-quality-auditor · CITE → domain-authority-auditor |
/aaron-marketing:seo-geo |
| Social | 16 | explore → craft → host → observe | ECHO asset / program-maturity profiles | /aaron-marketing:social |
| 16 | setup → engage → nurture → deliver | SEND → email-quality-auditor (EQS) |
/aaron-marketing:email |
|
| Paid ads | 16 | research → orchestrate → activate → scale | ROAS → ad-account-auditor (RQS) |
/aaron-marketing:ad |
| Influencer | 16 | scout → target → activate → report | STAR → creator-content-auditor (SQS); fit-scorer produces the Suitability (S) read |
/aaron-marketing:influencer |
| Launch | 16 | research → assemble → mobilize → prove | RAMP preflight / execution / outcome profiles | /aaron-marketing:launch |
| Protocol layer | 8 | — (shared machinery, outside the phase flows) | 7 truth registries (entity · creator · offer/claims · consent · launch · channel · narrative) + HOT/WARM/COLD memory | — |
/aaron-marketing:auto routes any natural-language goal across all of it. Skills and commands are plain Markdown; small Bash/Python-stdlib runtimes provide hooks, validation, scoring, registry events, connectors, and CI checks (no pip, no build step). Every skill runs at Tier 1 with data you provide; connectors only automate retrieval or an explicitly approved mutation.
The authoritative typed topology is references/system-catalog.json; see the generated system architecture for the readable four-layer map, all 120 paths, registry owners, auditor sinks, and distribution profiles.
The pre-merge standalone repos are now signpost repos pointing here — seo-geo-claude-skills (final 20-skill line preserved at tag
v9.9.12) and influencer-marketing-agent-skills (final IMPACT line at tagstandalone-final). Sibling-repo policy: docs/repo-family.md.
| Principle | What it means in practice |
|---|---|
| Keyless by default | Every skill works at Tier 1 with data you paste or pull from free/first-party sources. Paid tools and MCP servers are an opt-in convenience, never a precondition. Paid-ads skills score from your own-account manual export — keyed ad APIs are never required. |
| Content-first, executable contracts | Skills remain Markdown. Small Bash/Python-stdlib runtimes make scoring, state, safety, and conformance deterministic without adding package dependencies. |
| One shared contract | All 120 skills expose the same seven sections and self-declare discipline + phase metadata, so the library behaves like one operating system: each skill knows its inputs, outputs, and the next best skill to hand off to. |
| Gated quality | Eight benchmarks drive eight auditor-class gates that emit structured, machine-checkable verdicts — not vibes. Success/failure/batch hooks surface invalid writes through bounded checks. Pre-commit/CI protect committed Git content from PII; they do not validate ignored runtime artifacts. |
| Truth lives in events | Seven append-only registry streams are canonical; owner-controlled projections expose entity, creator, claims, consent, launch, channel, and narrative state without destructive queues. |
| Memory across turns | A HOT/WARM/COLD memory model carries findings, scores, and open loops between skills and sessions, sanitized on the way in. |
| Plain voice | Skills ship an AI-slop detector and a banned-phrase list so output reads like a human wrote it. |
Use it with Claude Code, any Agent Skills-compatible host, or a plain git clone:
| Host | Install |
|---|---|
| Claude Code | /plugin marketplace add aaron-he-zhu/aaron-marketing-skills then /plugin install aaron-marketing@aaron |
| Codex · Cursor · OpenCode · Antigravity · Gemini CLI · Copilot CLI · OpenClaw · Hermes · 70+ hosts | npx skills add aaron-he-zhu/aaron-marketing-skills |
| SkillHub.cn (中文社区) | skillhub install <frontmatter-slug> (e.g. aaron-campaign-architect or legacy unprefixed slugs like keyword-research) |
| Any host | git clone https://github.com/aaron-he-zhu/aaron-marketing-skills |
In Claude Code, marketplace add only registers the catalog — run /plugin install aaron-marketing@aaron (or pick it from /plugin) to actually enable the skills and commands. To pull a single skill on a generic host: npx skills add aaron-he-zhu/aaron-marketing-skills -s keyword-research. Browse the bundle on the skills.sh registry. Per-agent directories, frontmatter quirks, and what degrades outside the plugin: docs/agent-compatibility.md (verified 120/120 installable, 2026-07).
Installing the plugin adds nothing to your /mcp list — the MCP catalogue lives in docs/mcp-catalog.json, deliberately outside the plugin-root .mcp.json path that Claude Code auto-registers, so it is a copy-paste reference only (see Connectors).
If your host supports automatic skill routing, just describe the goal:
Research keywords for my SaaS product targeting small teams
Find TikTok creators for a skincare launch and score their fit
Audit this Google Ads account before I scale — exports attached
Or use the slash commands — /auto for routing, or a discipline entrypoint:
/aaron-marketing:auto turn our pricing page into an AI-citable comparison hub
/aaron-marketing:seo-geo https://example.com/blog/my-article --phase tune
/aaron-marketing:auto infers intent and runs the smallest useful workflow, stopping only at blocking