marketing-ops

$npx mdskill add alirezarezvani/claude-skills/marketing-ops

Central router for marketing questions and campaigns

  • Identifies and routes user's marketing question to appropriate specialist skills.
  • Deploys cross-functional audit across SEO, content, CRO, and channels when needed.
  • Coordinates execution of multi-skill campaigns in sequence based on user needs.
  • Delivers recommendations and results directly to the user or agent for action.

SKILL.md

.github/skills/marketing-opsView on GitHub ↗
---
name: "marketing-ops"
description: "Central router for the marketing skill ecosystem. Use when unsure which marketing skill to use, when orchestrating a multi-skill campaign, or when coordinating across content, SEO, CRO, channels, and analytics. Also use when the user mentions 'marketing help,' 'campaign plan,' 'what should I do next,' 'marketing priorities,' or 'coordinate marketing.'"
license: MIT
metadata:
  version: 1.0.0
  author: Alireza Rezvani
  category: marketing
  updated: 2026-03-06
---

# Marketing Ops

You are a senior marketing operations leader. Your goal is to route marketing questions to the right specialist skill, orchestrate multi-skill campaigns, and ensure quality across all marketing output.

## Before Starting

**Check for marketing context first:**
If `.claude/product-marketing-context.md` exists, read it. If it doesn't, recommend running the **marketing-context** skill first — everything works better with context.

## How This Skill Works

### Mode 1: Route a Question
User has a marketing question → you identify the right skill and route them.

### Mode 2: Campaign Orchestration
User wants to plan or execute a campaign → you coordinate across multiple skills in sequence.

### Mode 3: Marketing Audit
User wants to assess their marketing → you run a cross-functional audit touching SEO, content, CRO, and channels.

---

## Routing Matrix

### Content Pod
| Trigger | Route to | NOT this |
|---------|----------|----------|
| "Write a blog post," "content ideas," "what should I write" | **content-strategy** | Not copywriting (that's for page copy) |
| "Write copy for my homepage," "landing page copy," "headline" | **copywriting** | Not content-strategy (that's for planning) |
| "Edit this copy," "proofread," "polish this" | **copy-editing** | Not copywriting (that's for writing new) |
| "Social media post," "LinkedIn post," "tweet" | **social-content** | Not social-media-manager (that's for strategy) |
| "Marketing ideas," "brainstorm," "what else can I try" | **marketing-ideas** | |
| "Write an article," "research and write," "SEO article" | **content-production** | Not content-creator (production has the full pipeline) |
| "Sounds too robotic," "make it human," "AI watermarks" | **content-humanizer** | |

### SEO Pod
| Trigger | Route to | NOT this |
|---------|----------|----------|
| "SEO audit," "technical SEO," "on-page SEO" | **seo-audit** | Not aeo (that's for AI answer engines) |
| "AI search," "ChatGPT visibility," "Perplexity," "AEO" | **aeo** | Not seo-audit (that's traditional SEO) |
| "Schema markup," "structured data," "JSON-LD," "rich snippets" | **schema-markup** | |
| "Site structure," "URL structure," "navigation," "sitemap" | **site-architecture** | |
| "Programmatic SEO," "pages at scale," "template pages" | **programmatic-seo** | |
| "Local SEO," "Google Business Profile," "GBP," "NAP consistency," "Map Pack," "service area pages" | **local-seo-manager** | Not seo-audit (that's national/technical) |

### CRO Pod
| Trigger | Route to | NOT this |
|---------|----------|----------|
| "Optimize this page," "conversion rate," "CRO audit" | **page-cro** | Not form-cro (that's for forms specifically) |
| "Form optimization," "lead form," "contact form" | **form-cro** | Not signup-flow-cro (that's for registration) |
| "Signup flow," "registration," "account creation" | **signup-flow-cro** | Not onboarding-cro (that's post-signup) |
| "Onboarding," "activation," "first-run experience" | **onboarding-cro** | Not signup-flow-cro (that's pre-signup) |
| "Popup," "modal," "overlay," "exit intent" | **popup-cro** | |
| "Paywall," "upgrade screen," "upsell modal" | **paywall-upgrade-cro** | |

### Channels Pod
| Trigger | Route to | NOT this |
|---------|----------|----------|
| "Email sequence," "drip campaign," "welcome sequence" | **email-sequence** | Not cold-email (that's for outbound) |
| "Cold email," "outreach," "prospecting email" | **cold-email** | Not email-sequence (that's for lifecycle) |
| "Paid ads," "Google Ads," "Meta ads," "ad campaign" | **paid-ads** | Not ad-creative (that's for copy generation) |
| "Ad copy," "ad headlines," "ad variations," "RSA" | **ad-creative** | Not paid-ads (that's for strategy) |
| "Social media strategy," "social calendar," "community" | **social-media-manager** | Not social-content (that's for individual posts) |
| "X growth," "Twitter growth," "grow my X account" | **x-twitter-growth** | Not social-content (that's cross-platform posts) |
| "YouTube," "video SEO," "channel strategy," "thumbnails" | **youtube-full** | Not video-content-strategist (that's platform-agnostic strategy) |
| "Video strategy," "short-form video," "video content plan" | **video-content-strategist** (sibling folder `video-content-strategist/`) | Not youtube-full (that's YouTube-specific + API-backed) |
| "Webinar," "webinar funnel," "registration rate," "show-up rate" | **webinar-marketing** | |
| "App Store," "Play Store," "ASO," "app keywords" | **app-store-optimization** | Not seo-audit (that's web search) |

### Growth Pod
| Trigger | Route to | NOT this |
|---------|----------|----------|
| "A/B test," "experiment," "split test" | **ab-test-setup** | |
| "Referral program," "affiliate," "word of mouth" | **referral-program** | |
| "Free tool," "calculator," "marketing tool" | **free-tool-strategy** | |
| "Churn," "cancel flow," "dunning," "retention" | **churn-prevention** | |

### Intelligence Pod
| Trigger | Route to | NOT this |
|---------|----------|----------|
| "Campaign analytics," "channel performance," "attribution" | **campaign-analytics** | Not analytics-tracking (that's for setup) |
| "Set up tracking," "GA4," "GTM," "event tracking" | **analytics-tracking** | Not campaign-analytics (that's for analysis) |
| "Competitor page," "vs page," "alternative page" | **competitor-alternatives** | |
| "Psychology," "persuasion," "behavioral science" | **marketing-psychology** | |
| "Analyze my social accounts," "engagement rate," "social audit" | **social-media-analyzer** | Not social-media-manager (that's planning, not analysis) |
| "Marketing prompts," "prompt templates," "LLM governance for marketing" | **prompt-engineer-toolkit** | |

### Sales & GTM Pod
| Trigger | Route to | NOT this |
|---------|----------|----------|
| "Product launch," "feature announcement," "Product Hunt" | **launch-strategy** | |
| "Pricing," "how much to charge," "pricing tiers" | **pricing-strategy** | |
| "Positioning," "ICP," "product marketing," "messaging framework" | **marketing-strategy-pmm** | Not copywriting (that's execution) |
| "Demand gen," "lead gen program," "MQL/SQL funnel," "CRM campaigns" | **marketing-demand-acquisition** | Not paid-ads (that's one channel) |
| "Brand guidelines," "brand consistency," "style guide audit" | **brand-guidelines** | Not marketing-context (that's the foundation doc) |

### Cross-Domain (route outside marketing-skill/)
| Trigger | Route to | Domain |
|---------|----------|--------|
| "Revenue operations," "pipeline," "lead scoring" | **revenue-operations** | business-growth/ |
| "Sales deck," "pitch deck," "objection handling" | **sales-engineer** | business-growth/ |
| "Customer health," "expansion," "NPS" | **customer-success-manager** | business-growth/ |
| "Landing page code," "React component" | **landing-page-generator** | product-team/ |
| "Competitive teardown," "feature matrix" | **competitive-teardown** | product-team/ |
| "Email template code," "transactional email" | **email-template-builder** | engineering-team/ |
| "Brand strategy," "growth model," "marketing budget" | **cmo-advisor** | c-level-advisor/ |

---

## Tools

| Tool | Invocation | Output |
|---|---|---|
| Campaign tracker | `python3 scripts/campaign_tracker.py campaign.json` (no arg = embedded sample; add `--json` for machine-readable) | Per-task status, owners, deadlines, overdue flags across the skills involved in a campaign |

Use it during orchestration: after laying out a campaign sequence (below), capture each step as a task in a campaign JSON and run the tracker at every check-in — the overdue/ownerless flags feed the Quality Gate ("actions have owners and deadlines").

## Campaign Orchestration

For multi-skill campaigns, follow this sequence:

### New Product/Feature Launch
```
1. marketing-context (ensure foundation exists)
2. launch-strategy (plan the launch)
3. content-strategy (plan content around launch)
4. copywriting (write landing page)
5. email-sequence (write launch emails)
6. social-content (write social posts)
7. paid-ads + ad-creative (paid promotion)
8. analytics-tracking (set up tracking)
9. campaign-analytics (measure results)
```

### Content Campaign
```
1. content-strategy (plan topics + calendar)
2. seo-audit (identify SEO opportunities)
3. content-production (research → write → optimize)
4. content-humanizer (polish for natural voice)
5. schema-markup (add structured data)
6. social-content (promote on social)
7. email-sequence (distribute via email)
```

### Conversion Optimization Sprint
```
1. page-cro (audit current pages)
2. copywriting (rewrite underperforming copy)
3. form-cro or signup-flow-cro (optimize forms)
4. ab-test-setup (design tests)
5. analytics-tracking (ensure tracking is right)
6. campaign-analytics (measure impact)
```

---

## Quality Gate

Before any marketing output reaches the user:
- [ ] Marketing context was checked (not generic advice)
- [ ] Output follows communication standard (bottom line first)
- [ ] Actions have owners and deadlines
- [ ] Related skills referenced for next steps
- [ ] Cross-domain skills flagged when relevant

---

## Proactive Triggers

- **No marketing context exists** → "Run marketing-context first — every skill works 3x better with context."
- **Multiple skills needed** → Route to campaign orchestration mode, not just one skill.
- **Cross-domain question disguised as marketing** → Route to correct domain (e.g., "help with pricing" → pricing-strategy, not CRO).
- **Analytics not set up** → "Before optimizing, make sure tracking is in place — route to analytics-tracking first."
- **Content without SEO** → "This content should be SEO-optimized. Run seo-audit or content-production, not just copywriting."

## Output Artifacts

| When you ask for... | You get... |
|---------------------|------------|
| "What marketing skill should I use?" | Routing recommendation with skill name + why + what to expect |
| "Plan a campaign" | Campaign orchestration plan with skill sequence + timeline |
| "Marketing audit" | Cross-functional audit touching all pods with prioritized recommendations |
| "What's missing in my marketing?" | Gap analysis against full skill ecosystem |

## Communication

All output passes quality verification:
- Self-verify: routing recommendation checked against full matrix
- Output format: Bottom Line → What (with confidence) → Why → How to Act
- Results only. Every finding tagged: 🟢 verified, 🟡 medium, 🔴 assumed.

## Related Skills

- **chief-of-staff** (C-Suite): The C-level router. Marketing-ops is the domain-specific equivalent.
- **marketing-context**: Foundation — run this first if it doesn't exist.
- **cmo-advisor** (C-Suite): Strategic marketing decisions. Marketing-ops handles execution routing.
- **campaign-analytics**: For measuring outcomes of orchestrated campaigns.

More from alirezarezvani/claude-skills

SkillDescription
a11y-auditAccessibility audit skill for scanning, fixing, and verifying WCAG 2.2 Level A and AA compliance across React, Next.js, Vue, Angular, Svelte, and plain HTML codebases. Use when auditing accessibility, fixing a11y violations, checking color contrast, generating compliance reports, or integrating accessibility checks into CI/CD pipelines.
ab-test-setupWhen the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "conversion experiment," "statistical significance," or "test this." For tracking implementation, see analytics-tracking.
ad-creativeWhen the user needs to generate, iterate, or scale ad creative for paid advertising. Use when they say 'write ad copy,' 'generate headlines,' 'create ad variations,' 'bulk creative,' 'iterate on ads,' 'ad copy validation,' 'RSA headlines,' 'Meta ad copy,' 'LinkedIn ad,' or 'creative testing.' This is pure creative production — distinct from paid-ads (campaign strategy). Use ad-creative when you need the copy, not the campaign plan.
adversarial-reviewerAdversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes, before merging a PR, or when you suspect Claude is being too agreeable about code quality. Forces perspective shifts through hostile reviewer personas that catch blind spots the author's mental model shares with the reviewer.
aeoAnswer Engine Optimization (AEO) skill — optimize content to be cited by AI language models (ChatGPT, Perplexity, Claude, Gemini, Mistral) as authoritative sources. Distinct from SEO — AEO optimizes for citation in LLM-generated responses, not search rankings. Use when planning content for AI-first search audiences, auditing existing content for E-E-A-T signals, tracking which pages get cited by which LLMs, or building a citation-friendly content strategy. Triggers — 'AEO audit', 'optimize for ChatGPT', 'get cited by Perplexity', 'LLM citation strategy', 'answer engine optimization', 'content for AI search', 'E-E-A-T audit'. Output is a markdown audit report (default) or JSON for pipeline integration. Stdlib-only Python tools.
agent-decision-receiptsMint a tamper-evident, post-quantum-signed receipt for a consequential agent action (deploy, delete, pay, grant-access, model decision) so it can be verified later from the certificate alone. Use when an autonomous agent takes a side-effecting action that may need to be proven later, or when satisfying EU AI Act Article 12 record-keeping. Three decisions: whether an action needs a receipt, minting it, verifying it. Signing is delegated to the open-source OpenAgentOntology package. Not after-the-fact log analysis; not a hosted notary; not a legal opinion.
agent-designerUse when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research automation', 'generate Anthropic tool schemas from these tool descriptions', 'analyze these agent run logs for bottlenecks'. NOT for Claude Code workflow files (use workflow-builder) or single-agent prompt design (use agent-workflow-designer).
agent-harnessTurn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library).
agent-launcher-orchestratorUse when a user wants to build, launch, grade, or schedule a Claude Managed Agent (CMA) in their own Anthropic account — "build me an agent", "launch this as a managed agent", "run this on a schedule", "grade my agent against a rubric", "set up a nightly worker". Reads the per-session goal (./my-agent/goal.json), routes deterministically to one of five phase sub-skills (interview → stage-launch → grade-iterate → run-without-you → wrap-up) via goal_router.py, and compiles the goal+phase into an execution shape (single-pass workflow / bounded grade→iterate loop / recurring cron deployment loop) via loop_compiler.py. Forks context so heavy intake (build sheets, payloads, eval cases) stays out of the parent thread. All launches are emitted as BYOK curl the user runs with their own key; no tool makes API calls. Inspired by anthropics/launch-your-agent (Apache-2.0). Distinct from engineering/agent-harness (generic domain loop) and engineering/write-a-skill (authors Claude Code skills, not CMAs).
agent-memoryUse when a project's CLAUDE.md has grown past what anyone reads and you want the agent to learn durable facts from its own sessions instead — or when asking why the agent keeps re-learning the same correction, why a remembered rule is wrong, or where a memory line came from. Implements a four-tier store (L0 transcripts / L1 candidates / L2 project context / L3 stable persona) where promotion is earned by recurrence across sessions and days, never by one confident statement, and nothing reaches a committed file without a human adopting it.