Hire an AI product ad hook planner

Everything it can hand back

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

• A list of strong phrases from your own material, each with where it came from
• Your phrases sorted into headlines, long copy, side notes, proof and demonstrations, with the most dramatic points marked
• The one want your buyers share, its smaller wants, and a hook for each with the proof and feeling behind it
• A running order for the hooks and a plan to test hooks that differ in appeal, not only in wording

How it does the job well

• Start from the user problem and the evidence for it, then the solution.
• Write decisions down with the reason and the options you rejected.
• Keep scope small enough to ship and learn. Name what is out of scope.
• Define how success will be measured before building.

Mistakes it avoids

• Treating opinions or one loud request as proven demand.
• Specs that skip edge cases, error states or dependencies.
• Roadmaps with dates but no owners or confidence levels.

What a good result looks like

An example, not your task: You need fresh hooks and angles and want them built from what your product already says.

• Phrase sheet. Strong phrases from your own material, each with its source, sorted into piles for headlines, long copy, side notes, proof and demonstrations.
• Most dramatic points. The strongest points in your material, marked, with a ten-word headline for each long idea.
• Shared want. The one want your buyers already have, written in their words.
• Smaller wants and hooks. Each smaller want, with a hook, how it works, the proof and the feeling behind it.
• Running order and test plan. The order to use the hooks in, and a plan to test hooks that differ in appeal, not wording.
• 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

• Every phrase on the step 1 sheet is in the product's own words and has its source. Anything the AI added is marked apart.
• Every claim in a hook appears in the step 1 file or in the material you gave, and each hook has its proof or a MISSING: proof line.
• Step 2 used the step 1 phrase sheet, not a new list.
• The shared want is one a buyer would say as their own. If there were no buyer words, it is marked as a guess.
• 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 Eugene Schwartz and Victor Schwab would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Mine the phrases. Reads your material, marks every strong phrase in your own words, and sorts them into piles for headlines, copy, proof and demos.
• Name the shared want. Takes the phrase sheet from the step before, names the want buyers already have, splits it into smaller wants and writes a hook for each.

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 product-review-mining 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/product-review-mining/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 product material, such as a product page, manual, spec sheet, book or transcript
• Customer reviews or buyer words (optional)
• A persona or a short description of your buyers (optional)

Tools and access

• Any good chat AI: Reading a long document and sorting phrases is text work any strong chat AI does well with this skill.
• Any good chat AI: Grouping wants and writing hooks is text work any strong chat AI does well with this skill.

Functions and deliverables

• Product ad hook planner: Share product pages or manuals and buyer evidence. Get a phrase library, possible shared needs and opening-line ideas.
  • A list of strong phrases from your own material, each with where it came from
  • Your phrases sorted into headlines, long copy, side notes, proof and demonstrations, with the most dramatic points marked
  • The one want your buyers share, its smaller wants, and a hook for each with the proof and feeling behind it
  • A running order for the hooks and a plan to test hooks that differ in appeal, not only in wording
• Product terminology guide writer: Turn a manual, book or product page into a product vocabulary sheet: strong phrases in your own words, sorted for headlines, proof and demos.
  • A list of strong phrases with their source locations
  • Piles sorted for headlines, long copy, side notes, proof and demonstrations
  • The most dramatic points, marked
  • A ten-word headline for each long idea
• Buyer wish hook planner: Describe your product and its buyers. Get the one want they share, its smaller parts and a hook for each.
  • The shared want, with a short buyer quote, or marked as a guess if you gave no buyer words
  • Three to six smaller wants, each with one hook
  • For each hook, how the product delivers, the proof you hold and the feeling it should leave
  • One line that lets the whole group in, and a running order for the hooks
  • A test plan for two to four hooks, plus a list of what is missing
• Product weakness line writer: Share a word you want to own and buyer evidence about a flaw. Get three honest lines that connect the flaw to that word.
  • A list of flaws buyers already see, with sources
  • The flaw whose turn leads to your word
  • Three admit-then-turn lines
  • Where to use each line, and how to test it
  • What not to say
• Product context file writer: Share product facts, audience and positioning. Get a reviewed context file that other marketing skills can reference.
  • A product marketing context file
  • A summary of what the file already holds
  • A change log of updates
  • Gaps you still need to fill
  Source: Corey Haines.
• Eugene Schwartz: Match a headline or sales page to what buyers already want and know. Apply Eugene Schwartz’s recorded approach to research, claims and proof.
  • Your problem worked on the way Eugene Schwartz would: their questions, their method, their push-back
  • The answer or the work, in Eugene Schwartz's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Victor Schwab: Review ad headlines and openings using Victor Schwab’s recorded approach. Name the reader, support the promise and plan how to track responses.
  • Your problem worked on the way Victor Schwab would: their questions, their method, their push-back
  • The answer or the work, in Victor Schwab'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 need fresh hooks and angles and want them built from what your product already says.
• You have a thick manual, book or transcript and need to find the lines worth using in ads and pages.
• Your ads all lean on one benefit and you suspect your buyers share a want you have not named.

Limits to check before starting

• Your product has no written material yet: build the Brand profile builder result first, then come back.
• You only need a headline for one ad: use the Ad headline writer.
• You want to plan ad angles from your market, not from your own product text: use the Ad angle planner.

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 or attach your product material. It builds the phrase sheet first.
• Add reviews or buyer words if you have them. It uses them to name the shared want.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/product-review-mining 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.