How do I install AAJ Marketing Engines?

Copy the http config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.

Does AAJ Marketing Engines need an API key?

No required environment variable is listed on this record.

What transport does AAJ Marketing Engines use?

AAJ Marketing Engines is reached over HTTP.

When was AAJ Marketing Engines last checked?

Last checked 2026-11-10. Deterministic marketing math for AI agents: LTV:CAC, pipeline coverage, A/B tests, pricing.

AAJ Marketing Engines MCP server

The math layer for marketing agents

73 marketing skills for AI agents, and 62 of them run real engines. Each engine is a dependency-free Node script. It takes your numbers and returns a number and a verdict: LTV:CAC and payback, pipeline coverage, A/B significance, budget splits, price ladders, NRR, market size, inference cost.

Most marketing skills are writing instructions. They help an agent draft a page, an email or a plan, so keep them. These add the arithmetic underneath. The agent that drafts your pricing page can check whether the price still covers inference cost. The agent that writes the board update can compute the forecast instead of estimating it. Same input, same output, and code you can read.

Works with Claude Code, OpenAI Codex, Cursor, Windsurf, Cline and any agent that supports the Agent Skills spec. Free, MIT, no API key, and the engines make no network calls.

Built by Saroj Jha / AAJ. Browsable library at skills.aajconsult.com.

If an engine saves you a spreadsheet, star the repo. Stars are how other founders, and the directories agents search, find it. Questions and engine requests go in Discussions.

Renamed on Oct 11, 2026. copywriting, marketing-psychology, programmatic-seo, marketing-loops and sales-enablement are now aaj-copywriting, aaj-marketing-psychology, aaj-programmatic-seo, aaj-marketing-loops and aaj-sales-enablement. Another popular library publishes skills under the same five names, so with the prefix both install side by side. The hosted MCP server still answers to the old names.

Quick start
Install as a Claude Code or Codex plugin
Use it from an MCP client
Recipes: vendor data in, a verdict out
What a runnable engine means
The catalog
- Strategy & Positioning — 12 skills, 9 engines
- Research & Personas — 4 skills, 3 engines
- SEO, GEO & AEO — 9 skills, 8 engines
- Content & Copy — 11 skills, 10 engines
- Conversion & Web — 5 skills, 4 engines
- Paid Media & Budgeting — 4 skills, 4 engines
- Analytics & Experimentation — 4 skills, 4 engines
- Sales & Pipeline — 12 skills, 9 engines
- Retention & Lifecycle — 3 skills, 2 engines
- Growth, Retention & RevOps — 9 skills, 9 engines
Engines at a glance
Methodology
Authoring & contributing
Credits & license

Quick start

# everything
npx skills add sarojkjha/aaj-marketing-skills

# one skill
npx skills add sarojkjha/aaj-marketing-skills --skill unit-economics

# see what's available
npx skills add sarojkjha/aaj-marketing-skills --list

Installs to .agents/skills/, and symlinks into .claude/skills/ for Claude Code.

Step-by-step instructions for every agent, Windows, Mac and Linux, and the hosted server: docs/install.md.

Then run any engine with no configuration at all:

node .agents/skills/unit-economics/resources/unit-economics.js --demo

AAJ Unit Economics -- subscription
------------------------------------------------------
Gross-margin LTV        $13,333   (3.0% monthly churn (~33.3 mo lifetime))
CAC                     $3,000
LTV : CAC               4.4:1
CAC payback             7.5 mo

[OK] LTV:CAC 4.4:1 is at or above the 3:1 floor.
[OK] CAC payback 7.5 mo is within the ~12-month guideline for subscription.

Swap the demo values for your own and it works the same way.

From a clone of this repo, paths are skills/<slug>/resources/… instead of .agents/skills/<slug>/resources/….

Install as a Claude Code or Codex plugin

Claude Code. In Claude Code 2.1.275 or later, one line adds the marketplace and opens the plugin:

/plugin install aaj-marketing-skills --marketplace sarojkjha/aaj-marketing-skills

On earlier versions, run two commands:

/plugin marketplace add sarojkjha/aaj-marketing-skills
/plugin install aaj-marketing-skills@aaj

The skills then appear as /aaj-marketing-skills:<skill>. The plugin also starts the local AAJ engines MCP server (platform/mcp/server.mjs, Node 18+), so Claude can call run_engine directly. It runs on your machine and AAJ receives nothing. Updates arrive when you run /plugin marketplace update aaj.

OpenAI Codex. Add the marketplace, then install the plugin (or browse it with /plugins inside Codex):

codex plugin marketplace add sarojkjha/aaj-marketing-skills
codex plugin add aaj-marketing-skills@aaj

codex plugin marketplace upgrade aaj picks up new skills. Codex reads .agents/plugins/marketplace.json, and both clients load every skill in skills/.

Use it from an MCP client

Instead of installing the skills into a project, you can expose all 73 skills and all 62 engines to any MCP client — Claude Desktop, Claude Code, Cursor, Windsurf — as five tools:

Tool	What it does
`list_engines`	Every runnable engine, grouped by category
`describe_engine`	One engine's input schema, units and worked example
`run_engine`	Runs it on your numbers, or the demo if you pass none
`search_skills`	Finds a skill by the problem, not the name
`get_skill`	The full method for one skill

Hosted, no install. Add this URL as a custom connector (a remote MCP server) in Claude, ChatGPT or any MCP client:

https://aaj-engines-mcp.sarojkjha10.workers.dev/mcp

No sign-in. The server runs the engines in memory and keeps no copy of what you send (what happens to your data). In Claude: Settings → Connectors → Add custom connector. Then ask, for example, "Use the AAJ engines to check my unit economics: CAC $1,200, ARPA $300 a month, 80% gross margin, 3% monthly churn."

Local. Clone the repo and point your client at one file. Node 18+, no dependencies, no build step:

{
  "mcpServers": {
    "aaj-engines": {
      "command": "node",
      "args": ["/absolute/path/to/aaj-marketing-skills/platform/mcp/server.mjs"]
    }
  }
}

Your agent can then find the right method for a problem and run the math on your numbers, rather than estimating. Run locally, AAJ receives nothing; your agent's model provider still sees what you give the agent.

What happens to your data

The engines are deterministic scripts. They make no network calls, write no files and take no actions in your tools; they compute and return text and JSON. Where your numbers travel depends on how you run them:

How you run it	Where your inputs go
Skill installed in your agent, or the local MCP server	The engine runs on your machine and AAJ receives nothing. Your AI agent still sends what you give it to its model provider (Anthropic, OpenAI and so on), under your own account's terms.
Hosted MCP server	Your agent's model provider, as above, plus AAJ's server on Cloudflare, which receives the engine inputs over HTTPS, runs them in memory and keeps no copy. Cloudflare keeps error logs (no inputs) for up to 7 days.

Don't pass customer names, emails or other personal data to an engine; none of them needs it.

Setup for each client, troubleshooting, and the smoke test: platform/mcp/README.md.

Recipes: vendor data in, a verdict out

Vendor MCP servers bring the data; the engines turn it into a verdict. Each recipe is a prompt to paste, a field-by-field mapping and the checks to make before you trust the result:

HubSpot deals into pipeline-and-forecast: weighted forecast, coverage against your win rate, and the lever to pull.
GA4 results into ab-test-significance: sample size before the test, a verdict after it.
Ahrefs or Semrush keyword data into aaj-programmatic-seo: whether a template-page build pays back.
Stripe export into unit-economics: gross-margin LTV, CAC payback, and whether your economics support growth.

What a runnable engine means

Most agent skills are instructions. These are too — but 62 of them also ship a dependency-free Node script that does the arithmetic and returns a judgement.

	Instruction-only skill	Skill with an engine
Output	Guidance the agent paraphrases	Deterministic numbers
Reproducible	No	Yes — same input, same output
Verifiable	You trust the model	You read the code
Runs without an agent	No	Yes, `node …`

Every engine accepts --demo (a worked example, no config), --help (the input schema), and a JSON payload for your own numbers. Engines validate input and fail loudly rather than returning a confident wrong answer.

The catalog

E marks a skill with a runnable engine. Phase refers to AAJ's Diagnose → Design → Execute method.

Strategy & Positioning

	Skill	What it does	Phase
E	`aaj-marketing-psychology`	Diagnoses which decision friction blocks the buyer, with a line between persuasion and manipulation.	Design
E	`ai-inference-pricing`	Checks that an AI plan's price still covers inference when usage spikes.	Design
	`brand-product-context`	Builds the shared brand brief every other skill reads first.	Diagnose
E	`campaign-orchestrator`	Diagnoses which play applies, then sequences the other skills in order.	Diagnose
E	`competitor-messaging-matrix`	Reads rival homepages side by side and says which claims are crowded, which are open, and whether your headline blends in.	Diagnose
E	`market-sizing`	Sizes TAM, SAM and SOM bottom-up, with SOM set by capacity rather than a share of the market.	Diagnose
E	`marketing-maturity-assessment`	Scores marketing as a system across six dimensions, and names the weak links to fix first for your stage.	Diagnose

Research & Personas

	Skill	What it does	Phase
E	`customer-interview-synthesis`	Turns coded interview notes into ranked patterns and anecdotes, and says whether you can stop interviewing.	Diagnose
E	`customer-survey-design`	Designs surveys that produce usable answers, with sample sizing and segments.	Diagnose
	`persona-builder`	Builds personas from evidence rather than imagination.	Design
E	`review-mining`	Codes pasted reviews of you and your rivals into themes, switching reasons, feature asks and buyer language.	Diagnose

SEO, GEO & AEO

	Skill	What it does	Phase
E	`aaj-programmatic-seo`	Models whether a template-page build pays back before anything gets written.	Design
E	`agent-readiness-audit`	Scores whether an AI agent buying for a customer can find, evaluate and transact with you.	Diagnose
E	`content-decay`	Sorts a Search Console export into decaying, demand-drop, snippet-loss, rising and stable pages, and ranks what to refresh by clicks lost.	Diagnose
E	`geo-citation-tracker`	Measures whether AI engines name and cite you, and refuses to report noise as movement.	Execute
	`geo-content-optimization`	Rewrites a page to maximise the chance an AI engine cites it.	Execute
E	`search-demand-reader`	Reads a Search Console Queries export by intent and topic, and names the demand you already appear for but do not yet win.	Diagnose
E	`seo-content-brief`	Produces a writer-ready brief: intent, answer block, entities, internal links.	Design
E

Content & Copy

	Skill	What it does	Phase
E	`aaj-copywriting`	Rewrites page copy to ladder to the positioning, scored on claim-defensibility.	Execute
E	`ai-marketing-governance`	Scores whether a team's AI use is governed, and refuses citations that cannot be checked.	Execute
E	`brand-voice-definition`	Derives the measurable half of a voice guide from writing you agree sounds right, as a checkable profile.	Design
E	`brand-voice-governance`	Checks content block by block against your own voice rules, with a pass/revise verdict.	Execute
E	`case-study-and-proof`	Scores whether proof would convince a sceptic, and whether you may publish it at all.	Execute
E	`claims-and-proof-check`	Flags every claim in your copy that needs proof or consent, sentence by sentence, with the regulator's own guidance.	Execute
E	`comparison-pages`	Builds vs and alternatives pages with sourced, dated rival facts, and checks they admit where the rival wins.	Execute
E

Conversion & Web

	Skill	What it does	Phase
	`landing-page-brief`	Specs a landing page before anyone designs it.	Execute
E	`lead-magnet-and-free-tool-design`	Scores lead-magnet and free-tool ideas on the job they do against build effort, and judges live ones on qualified leads.	Design
E	`plg-upgrade-prompts`	Reads each upgrade prompt's funnel with honest intervals and names the prompt and stage to fix first.	Diagnose
E	`signup-flow-optimizer`	Scores signup friction and ranks what to remove by what it's worth.	Execute
E	`website-conversion-audit`	Audits a page for conversion friction and grades it.	Diagnose

Paid Media & Budgeting

	Skill	What it does	Phase
E	`ad-creative-testing`	Sizes a creative test before it runs, and refuses to name a winner the data cannot back.	Execute
E	`marketing-budget-planning`	Sizes a marketing budget by stage, shows where each figure comes from, and splits it by function.	Design
E	`paid-media-budget-allocation`	Splits spend across channels to hit a CAC target, with diminishing returns modelled.	Design
E	`paid-search-account-audit`	Audits a search account against its own target: tracking, waste, starved winners, pages. Fixes ranked by spend.	Diagnose

Analytics & Experimentation

	Skill	What it does	Phase
E	`ab-test-significance`	Checks whether an A/B result is significant, or sizes a test before you run it.	Execute
E	`incrementality-and-mmm`	Designs and reads holdout tests honestly, including whether they could ever have answered.	Diagnose
E	`marketing-report`	Turns funnel, spend and pipeline numbers into a board-ready narrative.	Execute
E	`unit-economics`	Computes LTV, CAC, payback and the ratio, then returns a verdict against named reference points.	Diagnose

Sales & Pipeline

	Skill	What it does	Phase
E	`aaj-sales-enablement`	Audits sales assets against what each deal stage needs, and ranks what to build by the revenue being lost.	Execute
E	`abm-program-design`	Checks whether the team can run the account list and whether the list hits the number.	Design
E	`buying-committee-map`	Maps who must say yes, what each must believe, and who you cannot reach, then orders the next conversations.	Design
	`cold-email-sequence`	Writes outbound sequences that survive a reply-rate audit.	Execute
	`discovery-call-framework`	Structures discovery so the call qualifies rather than pitches.	Execute
E	`lead-handoff-sla`	Checks whether MQLs get worked on time, whether sales takes them, and whether the threshold is in the right place.	Execute
E	`objection-handling`	Builds responses to the objections that lose deals, and checks the battlecard before reps use it.	Design
E

Retention & Lifecycle

	Skill	What it does	Phase
E	`email-lifecycle-sequence`	Maps which lifecycle sequences exist, checks send load, writes the missing ones.	Execute
E	`lifecycle-and-retention`	Computes churn, NRR, GRR and quick ratio, then diagnoses which one to fix.	Design
	`onboarding-activation`	Defines the activation moment from data and finds where new users stall.	Execute

Growth, Retention & RevOps

	Skill	What it does	Phase
E	`aaj-marketing-loops`	Computes the loop factor, finds the throttling stage, projects users over time.	Design
E	`community-and-dark-social`	Maps where buyers already talk, decides whether to open your own community, and measures dark social by asking.	Execute
E	`creator-partnerships`	Pays creators for the buyers they reach, not their follower count, and judges the result on what it sold.	Execute
E	`first-marketing-hire`	Writes the first marketer's scorecard, then scores the panel's evidence and calls hire, no-hire or more evidence.	Design
E	`marketing-leadership-model`	Prices in-house, fractional and agency with ramp, search time and your own hours, and says which shape fits.	Diagnose
E	`partnerships-and-co-marketing`	Scores partners on audience overlap rather than fame, and judges the result on pipeline.	Execute
E	`product-launch`	Tiers a launch, scores readiness on a twelve-item gate, and builds the dated work-back plan.	Execute

Engines at a glance

Every runnable engine, and the command to try it:

Skill	Command
`aaj-copywriting`	`node .agents/skills/aaj-copywriting/resources/copy-scorer.js --demo`
`aaj-marketing-loops`	`node .agents/skills/aaj-marketing-loops/resources/loop-model.js --demo`
`aaj-marketing-psychology`	`node .agents/skills/aaj-marketing-psychology/resources/pattern-check.js --demo`
`aaj-programmatic-seo`	`node .agents/skills/aaj-programmatic-seo/resources/pseo-model.js --demo`
`aaj-sales-enablement`	`node .agents/skills/aaj-sales-enablement/resources/enablement-audit.js --demo`
`ab-test-significance`	`node .agents/skills/ab-test-significance/resources/significance.js --demo`
`abm-program-design`	`node .agents/skills/abm-program-design/resources/abm-design.js --demo`
`ad-creative-testing`	`node .agents/skills/ad-creative-testing/resources/creative-test.js --demo`
`agent-readiness-audit`	`node .agents/skills/agent-readiness-audit/resources/agent-readiness.js --demo`
`ai-inference-pricing`	`node .agents/skills/ai-inference-pricing/resources/inference-pricing.js --demo`
`ai-marketing-governance`	`node .agents/skills/ai-marketing-governance/resources/ai-governance.js --demo`
`brand-voice-definition`	`node .agents/skills/brand-voice-definition/resources/voice-derive.js --demo`
`brand-voice-governance`	`node .agents/skills/brand-voice-governance/resources/voice-check.js --demo`
`buying-committee-map`	`node .agents/skills/buying-committee-map/resources/buying-committee.js --demo`
`campaign-orchestrator`	`node .agents/skills/campaign-orchestrator/resources/decision-guides.js --demo`

Methodology

Every skill is tagged to a phase, and the ordering is deliberate — the catalog refuses to let you execute before you have diagnosed.

Diagnose (20 skills) — find out what is actually broken before choosing a fix.
Design (23 skills) — decide the approach, with the trade-offs stated.
Execute (30 skills) — build and ship it.

If you do not know where to start, campaign-orchestrator diagnoses which play applies and sequences the rest for you.

New to the catalog? Run brand-product-context first. It builds the shared brief every other skill reads.

Authoring & contributing

See AUTHORING_GUIDE.md for the standard every skill follows, and SKILL_TEMPLATE.md to start a new one.

Credits & license

MIT — use freely, commercially or otherwise.

Built by Saroj Jha / AAJ, a marketing consultancy for Seed–Series B startups. The Agent Skills spec and Corey Haines' coreyhaines31/marketingskills (MIT) were references for structure and topic coverage; all AAJ skills are independently written and grounded in AAJ's own tools and methodology.

AAJ Marketing Engines

Add this server

Host a copy with our keys and logs.

Server facts

Tools

Questions