Hire an AI marketing strategy framework reviewer

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A pass, warn or fail on each of thirteen tests, with the plan line behind it, and a score out of 100
• A call on the name for any new product, with a stretch score
• Each tactic with its short-term and long-term effect, and a sum for any discount
• A fad or trend call for each bet
• One move to back, a stop list, the money it needs and a pass or fail test with a date

How it does the job well

• Write for one named audience and one action. Each asset has a single job.
• Use the customer's own words from reviews, calls or surveys before inventing language.
• Every claim needs proof the business can show. Leave unproven claims out or mark them.
• Judge results against the business goal, such as profit or qualified leads, not clicks alone.

Mistakes it avoids

• Generic copy that could fit any brand.
• Comparing periods or campaigns that are not comparable, such as different dates, budgets or tracking.
• Calling a test winner before there is enough data.

What a good result looks like

An example, not your task: You have a marketing plan or launch idea and want it attacked before you spend on it.

• step-01-marketing-plan-law-checker.md. A pass, warn or fail on each of 13 laws, the plan line behind each, a score out of 100 and a fix list.
• step-02-brand-name-stretch-checker.md. What your name means now, a stretch score for any new product and a call on whether to use the name.
• step-03-long-run-effects-checker.md. Each tactic's effect now and in two years, the sum for any discount and a fad or trend call.
• step-04-one-bold-move-picker.md. One move to back, a stop list, the money it needs, an owner and a dated test.
• HAND-BACK SUMMARY. Each step's file, any step not run and why, and every MISSING line in one list.

How the work is checked

• Each verdict quotes a line from your plan, and the score can be rebuilt from the verdicts.
• The name call says what the name means now and what happens to the core product if the stretch fails.
• Every tactic has both a short-term and a long-term effect.
• Exactly one move is picked, and the rest are parked or cut.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way Al Ries and Jack Trout would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Checks the plan against the laws. Says what the plan is first in and which rung it holds, then marks each of thirteen tests pass, warn or fail with the plan line behind it.
• Checks the name stretch. Takes the fix list and compares what your name means today with what a new product would mean, then makes the call.
• Checks short-term gains against long-term costs. Writes the effect now and in two years for each tactic, does the sum for each discount and calls bets a fad or a trend.
• Picks the one bold move. Finds where each rival is least ready, scores the candidate moves and backs one, with a stop list, a budget check and a dated test.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id marketing-laws-check only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/marketing-laws-check/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• Your marketing plan, as rough as it is
• Your brand facts, such as name, buyers and budget (optional, but the verdicts are better with them)
• Product facts for any new product in the plan
• Your main rivals and what each is known for (optional)

Tools and access

• Any good chat AI: Reading a plan and judging each line against a test is text work any strong chat AI does with this skill.
• Any good chat AI: Weighing a name's meaning against a new product is text work that any strong chat AI does with this skill.
• Any good chat AI: Listing tactics and doing the small sums is text work any strong chat AI does with this skill.
• A spreadsheet: Weekly sales before, during and after a discount are easiest to line up in a sheet.
• Any good chat AI: Comparing rivals and scoring moves is text work any strong chat AI does with this skill.

Functions and deliverables

• Marketing strategy framework reviewer: Share your marketing plan, brand facts and product details. Get a framework-based critique, naming risks, trade-offs and one proposed move.
  • A pass, warn or fail on each of thirteen tests, with the plan line behind it, and a score out of 100
  • A call on the name for any new product, with a stretch score
  • Each tactic with its short-term and long-term effect, and a sum for any discount
  • A fad or trend call for each bet
  • One move to back, a stop list, the money it needs and a pass or fail test with a date
• Marketing strategy reviewer: Share your plan. Get thirteen buyer-positioning checks, quoted evidence, a score and a short fix list.
  • What the plan is first in, and the rung it holds
  • A pass, warn or fail on each of the thirteen tests, with the plan line behind it
  • A score out of 100
  • The strategy that fits your rung
  • A fix list in order of damage, and what to keep
• Brand name fit checker: Share your brand and proposed product. Check whether the existing name fits, what it could weaken and whether a new name is needed.
  • What the name means to buyers, in one line
  • A stretch score out of 100, with the working shown
  • One call to use the name, make a new one, or skip
  • The cost to the core product if the stretch fails
• Long-term strategy impact reviewer: Check your marketing plan for tactics that pay now and cost you later. Get each effect, a discount sum and a fad or trend call.
  • Each tactic with its short-term and long-term effect
  • A net sum for each discount
  • A fad or trend call for each bet, with how to dampen or ride it
  • Forecasts in the plan, and what you do if each is wrong
  • A list of changes
• Competitive strategy planner: Pick the one move to back from your marketing plan. Get a stop list for the rest, what it costs and a pass or fail test with a date.
  • Where each rival is least ready, with a source or a marked guess
  • A score out of four for each move
  • The one move to back, in one sentence a buyer would understand
  • A stop list: every other move parked or cut, and the money that frees
  • A money check, a named owner and a pass or fail test with a date
• Brand profile builder: Share your website. Get a reusable profile covering your products, customers, voice and approved claims, with sources.
  • A folder of eight plain files, from a start file for your AI to a claims list and a change log
  • A tag on every fact, and every claim marked approved, pending or banned
  • A two-sentence diagnosis of your biggest gap, and a list of what's missing and who can answer it
  • A short slice for your next step, if you name one
• Al Ries: Clarify what a brand should stand for using Al Ries’s recorded approach. Examine its category, focus, name and launch story.
  • Your problem worked on the way Al Ries would: their questions, their method, their push-back
  • The answer or the work, in Al Ries's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Jack Trout: Sharpen a brand’s place against rivals through Jack Trout’s recorded approach. Pick one clear idea, check the proof and avoid a blurred message.
  • Your problem worked on the way Jack Trout would: their questions, their method, their push-back
  • The answer or the work, in Jack Trout's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• You have a marketing plan or launch idea and want it attacked before you spend on it.
• Your plan has many small moves and no clear lead.
• You plan to put your name on a new product or a new group of customers.

Limits to check before starting

• You have no plan yet: write a rough draft first, or talk the idea through with a colleague, then come back.
• You want to judge only a new product name: use the Brand name fit checker on its own.
• You want to know if past tactics hurt you later: use the Long-term strategy impact reviewer on its own.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the handoff pack. It's a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Paste your plan first. Add your rivals and last year's discount figures if you have them. It works step by step and saves each result.
• Read the fails before you read the fixes. Check each quoted plan line is the one the verdict means.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/marketing-laws-check for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.