Marketing OperationsRoutingMarketing

Marketing Ops

Central router for the marketing skill ecosystem.

$skillfish add ~skills/marketing-ops

Real Examples Get Started Models & Context

Real Conversations

See how the Marketing Ops skill responds to actual requests. These are representative examples of what your AI agent will produce.

You

We're paying for HubSpot Marketing Pro ($800/mo), Mutiny ($500/mo), Hotjar ($150/mo), Semrush ($400/mo), Clearbit ($600/mo), and Zapier ($150/mo). Total $2,600/mo. I need to audit what's actually being used and what to cut.

Agent

MarTech Stack Audit: $2,600/month

Audit methodology — run this for each tool:

Pull last 90-day login data from each platform (admin > user activity)
Check if there are active automations/workflows dependent on the tool
Identify what the output of this tool is used for downstream

Quick-hit cuts (likely low usage):

Mutiny ($500/mo): Personalization is high-value but requires significant traffic and dedicated ops attention. At <50K monthly visitors it's hard to justify. Ask: how many active experiences are running? If <3, pause it.

Clearbit ($600/mo): Great if your SDR team is actively using enrichment data AND your HubSpot workflows trigger off company data. If enrichment data sits unused in contact records, cut it. Check: is any sequence or scoring rule referencing Clearbit fields?

Zapier ($150/mo): Pull your Zap list — how many are active? Often teams have 3 active Zaps and 40 dormant ones. HubSpot's native workflows can replace most Zapier automation. Map the active ones first.

Keep without question: HubSpot (your marketing OS), Hotjar (actual UX data), Semrush (SEO — but check if you're on the right tier).

Decision framework:

Tool	Keep if	Cut if
Mutiny	5+ active experiments, dedicated ops	Set-and-forget, <3 experiences
Clearbit	SDR team queries it weekly	Just enriching fields nobody reads
Zapier	5+ business-critical Zaps	All Zaps replicable in HubSpot

Potential savings: $1,100–$1,250/month if Mutiny, Clearbit, and Zapier are cut.

You

We have 12,000 contacts in HubSpot. SDRs are working every lead the same way and burning out. We need lead scoring to prioritize. What attributes should we score and how do we set it up?

Agent

HubSpot Lead Scoring Setup

Step 1: Define your ideal customer profile attributes Pull your last 50 closed-won deals from HubSpot. What do they have in common? This is the basis for your scoring model.

Recommended scoring attributes:

Demographic / Fit scoring (max 100 points):

Job title contains: Director, VP, Head of, C-     +25 pts
Company size: 50–500 employees                   +20 pts
Industry matches ICP                              +20 pts
Work email domain (not gmail/yahoo)              +15 pts
HQ country matches target markets                +10 pts
LinkedIn profile captured                        +10 pts

Behavioral / Engagement scoring (max 100 points):

Pricing page visited                             +30 pts
Demo requested                                   +50 pts
Case study downloaded                            +20 pts
Webinar attended                                 +15 pts
Email opened 3+ times in 30 days                 +10 pts
Trial started                                    +40 pts
Returned to site 3+ times in 7 days              +20 pts

Negative scoring:

Student/university email domain                  -30 pts
Competitor domain                                -50 pts
Unsubscribed from email                          -20 pts
No activity in 90+ days                          -10 pts

Thresholds for SDR routing:

Score ≥ 120: Immediate SDR outreach (SLA: 4 hours)
Score 60–119: Nurture sequence, SDR touches at day 3 and day 7
Score < 60: Email nurture only, no SDR time

In HubSpot: Settings > Properties > HubSpot Score > Add attribute rules. Segment view: create a "Hot Leads" smart list with HubSpot Score ≥ 120.

Get Started

How to install and use this skill in your preferred environment.

Skills are designed for AI coding agents (Claude Code, Cursor, Windsurf) and IDE-based workflows where the agent can read files, run scripts, and act on your codebase. Web-based AI can use the knowledge and frameworks, but won't have tool access.

Models & Context

Which AI models and context windows work best with this skill.

Recommended Models

Best

Claude Opus 4 Claude Sonnet 4 GPT-4.1 Gemini 2.5 Pro Grok 3 Kimi K2

Good

Claude Haiku 4.5 GPT-4.1 mini Gemini 2.5 Flash Grok 3 mini

Larger models produce more detailed, production-ready outputs.

Context Window

This skill's SKILL.md is typically 3–10 KB — fits in any modern context window.

8K Skill only

32K+ Skill + conversation

100K+ Skill + references + codebase

All current frontier models (Claude, GPT, Gemini) support 100K+ context. Use the full window for complex multi-service work.

Pro tips for best results

1

Be specific

Include numbers — users, budget, RPS — so the skill can size the architecture.

2

Share constraints

Compliance needs, team size, and existing stack all improve the output.

3

Iterate

Start with a high-level design, then ask follow-ups for IaC, cost analysis, or security review.

4

Combine skills

Pair with companion skills below for end-to-end coverage.

Ready to try Marketing Ops?

Install the skill and start getting expert-level guidance in your workflow — any agent, any IDE.

$skillfish add ~skills/marketing-ops

← Browse all 169 skills